DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This action is response to the application filed on 10/23/2023. Claims 1-28 are pending in the application and have been examined.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 02/13/2025, 04/15/2025 and 07/20/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
The drawings are objected to under 37 CFR 1.83(a) because they fail to show figure 8 as described in the specification. The specification mentions “two teacher models 802, and one student model 806 are specified”. However, the drawing mentions two teacher models 802 and one student model 804.
Any structural detail that is essential for a proper understanding of the disclosed invention should be shown in the drawing. MPEP § 608.02(d). Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that use the word “means” or “step” but are nonetheless not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph because the claim limitation(s) recite(s) sufficient structure, materials, or acts to entirely perform the recited function. Such claim limitation(s) is/are: means for initializing and means for training in claim 22.
Because this/these claim limitation(s) is/are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are not being interpreted to cover only the corresponding structure, material, or acts described in the specification as performing the claimed function, and equivalents thereof.
If applicant intends to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to remove the structure, materials, or acts that performs the claimed function; or (2) present a sufficient showing that the claim limitation(s) does/do not recite sufficient structure, materials, or acts to perform the claimed function.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 22, 23,24,25,26,27, and 28 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 22 recites the limitation “means for initializing” invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. The disclosure is devoid of any means or step to perform the initialization of the baseline diffusion model. Claim 23-28 are rejected as being dependent on rejected base claim 22 without curing any of the deficiencies. Therefore, the claim is indefinite and is rejected under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph.
Applicant may:
(a) Amend the claim so that the claim limitation will no longer be interpreted as a limitation under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph;
(b) Amend the written description of the specification such that it expressly recites what structure, material, or acts perform the entire claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(c) Amend the written description of the specification such that it clearly links the structure, material, or acts disclosed therein to the function recited in the claim, without introducing any new matter (35 U.S.C. 132(a)).
If applicant is of the opinion that the written description of the specification already implicitly or inherently discloses the corresponding structure, material, or acts and clearly links them to the function so that one of ordinary skill in the art would recognize what structure, material, or acts perform the claimed function, applicant should clarify the record by either:
(a) Amending the written description of the specification such that it expressly recites the corresponding structure, material, or acts for performing the claimed function and clearly links or associates the structure, material, or acts to the claimed function, without introducing any new matter (35 U.S.C. 132(a)); or
(b) Stating on the record what the corresponding structure, material, or acts, which are implicitly or inherently set forth in the written description of the specification, perform the claimed function. For more information, see 37 CFR 1.75(d) and MPEP §§ 608.01(o) and 2181.
Claim 5, 12, 19, and 26 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 5, 12, 19, and 26 recites the limitation “the control neural network receives a first input received at the baseline model and an auxiliary input”. It does not distinctly define the meets and bound of the type of model mentioned. The claims never recite the type of baseline model where the control neural network receives a first input. For the purpose of the examination, this limitation is interpreted as the control neural network receives a first input received at the baseline diffusion model and an auxiliary input.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 4, 5, 7, 8, 9, 11, 12, 14, 15, 16, 18, 19, 21, 22, 23, 25, 26, 28 are rejected under 35 U.S.C. 102 (a)(1) as being anticipated by Li, “SnapFusion: Text-Image Diffusion Model on Mobile Devices within Two Seconds.”
Regarding Claim 1, Li teaches
an apparatus for training a control neural network, (Li, pg.1, abstract, “We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation”. Based on the reference, the control neural network is being interpreted as UNet.)
comprising: one or more processors; and one or more memories coupled with the one or more processors and storing instructions operable, when executed by the one or more processors (Li, pg.1, abstract, “As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale” suggesting the use of processors/storing instructions)
initialize a baseline diffusion model for training the control neural network, each stage of a control neural network training pipeline corresponding to an element of the baseline diffusion model (Li, pg.2, section 2.1, “we choose Stable Diffusion v1.5(SD-v1.5) as the baseline” and pg.4, fig. 3, shows the initialization of the baseline diffusion model as text encoder, VAE decoder, UNet etc.)
train, the control neural network, in a stage-wise manner, each stage of the control neural network training pipeline receiving an input from a previous stage of the control neural network training pipeline and the corresponding element of the diffusion model (Li, pg.5, section 4.1, “First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model” showing [AltContent: textbox (This part of the figure shows the step distillation process where the teacher is used to train the student in a stage-wise manner.)]that the 16 step is used as teacher to train the 8-step efficient U-net. Each stage uses the diffusion [AltContent: ]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
elements like Unet and pg.4, Figure 3, shows the stage-wise manner training concept as well.)
Regarding Claim 2, Li teaches
The apparatus of claim 1, wherein the control neural network training pipeline includes: a control neural network architecture compression stage corresponding to a compressed UNet architecture of the baseline diffusion model (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage corresponding to a guidance conditioned student model of the baseline diffusion model (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
a step distillation stage corresponding to a step distilled student model of the baseline diffusion model (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 4, Li teaches
The apparatus in claim 1, wherein the control neural network is trained to emulate behavior of the baseline diffusion model in a single forward pass (Li, pg.4, section 3.1, “Inspired by the idea of elastic depth [48, 49], we apply stochastic forward propagation to execute each cross-attention and ResNet block by probability p(·,I), where I refers to identity mapping that skips the corresponding block”)
Regarding Claim 5, Li teaches
The apparatus in Claim 1, wherein: the control neural network receives a first input received at the baseline model and an auxiliary input (Li, pg.4, figure 3, shows the input
z
t
which is received at the baseline model and c as an auxiliary input)
[AltContent: rect][AltContent: rect][AltContent: textbox (Input received at the baseline model)]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
[AltContent: textbox (auxiliary input)]
the control neural network generates a first output based on receiving the first input and the auxiliary input (Li, pg.4, figure 3, shows the UNet generating an output
v
^
θ
c
(conditioned output) based off receiving
z
t
as an input and c as an auxiliary input and pg.6, section 4.2, “Given the UNet inputs, time step t, noisy latent
z
t
,and text embedding c, the teacher UNet performs two DDIM denoising steps, from time t to t′ and then to t′′ (0 ≤ t′′ < t′ < t ≤ 1)). This process can be formulated as:
PNG
media_image3.png
72
692
media_image3.png
Greyscale
”
[AltContent: textbox (output based on receiving inputs )]showing that the UNet receives
z
t
and outputs
v
^
t
=
v
^
θ
c
[AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
the first output modulates a second output of the baseline diffusion model (Li, pg.6, section 4.2, “We propose to perform classifier-free guidance to both the teacher and student before calculating the
loss. Specifically, for Eq. (7) and (8), after obtaining the v-prediction output of UNet, we add the CFGstep. Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
[AltContent: rect][AltContent: textbox (Second output of the baseline model modulated by the first output )]After replacing the UNet output with its guided version, all the other procedures remain the same for both the teacher and the student” where
v
^
n
c
and
v
^
n
∅
are the student models. However, it specifies that that CFG is performed on both teacher and student which means that the conditioned output (first output) of the teacher model is combined with unconditioned output thereby modulating the second output and pg. 4, figure 3, shows
v
^
θ
∅
(unconditioned output) being provide to classifier-free guidance (CFG) which are equations 7-10.)
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 7, Li teaches,
The apparatus in Claim 1, wherein a baseline diffusion model training pipeline includes, at least, a compression stage, (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage, (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
and a step distillation step (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 8, Li teaches
a method of training a control neural network, (Li, pg.1, abstract, “We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation”. Based on the reference, the control neural network is being interpreted as UNet.)
comprising: initializing a baseline diffusion model for training the control neural network, each stage of a control neural network training pipeline corresponding to an element of the baseline diffusion model (Li, pg.2, section 2.1, “we choose Stable Diffusion v1.5(SD-v1.5) as the baseline” and pg.4, fig. 3, shows the initialization of the baseline diffusion model as text encoder, VAE decoder, UNet etc.)
and training , the control neural network, in a stage-wise manner, each stage of the control neural network training pipeline receiving an input from a previous stage of the control neural network training pipeline and the corresponding element of the diffusion model (Li, pg.5, section 4.1, “First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model” showing that the 16 step is used as teacher to train the 8-step efficient U-net. Each stage uses the diffusion elements like UNet and pg.4, Figure 3, shows the stage-wise manner training concept as well.)
[AltContent: rect][AltContent: textbox (This part of the figure shows the step distillation process where the teacher is used to train the student in a stage-wise manner.)]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 9, Li teaches
The method of claim 8, wherein the control neural network training pipeline includes: a control neural network architecture compression stage corresponding to a compressed UNet architecture of the baseline diffusion model (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage corresponding to a guidance conditioned student model of the baseline diffusion model (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
a step distillation stage corresponding to a step distilled student model of the baseline diffusion model (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 11, Li teaches
The method of claim 8, wherein the control neural network is trained to emulate behavior of the baseline diffusion model in a single forward pass (Li, pg.4, section 3.1, “Inspired by the idea of elastic depth [48, 49], we apply stochastic forward propagation to execute each cross-attention and ResNet block by probability p(·,I), where I refers to identity mapping that skips the corresponding block”)
Regarding Claim 12, Li teaches
The method of Claim 8, wherein: the control neural network receives a first input received at the baseline model and an auxiliary input (Li, pg.4, figure 3, shows the input
z
t
which is received at the baseline model and c as an auxiliary input)
[AltContent: rect][AltContent: rect][AltContent: textbox (Input received at the baseline model)]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
[AltContent: textbox (auxiliary input)]
the control neural network generates a first output based on receiving the first input and the auxiliary input (Li, pg.4, figure 3, shows the UNet generating an output
v
^
θ
c
(conditioned output) based off receiving
z
t
as an input and c as an auxiliary input and pg.6, section 4.2, “Given the UNet inputs, time step t, noisy latent
z
t
,and text embedding c, the teacher UNet performs two DDIM denoising steps, from time t to t′ and then to t′′ (0 ≤ t′′ < t′ < t ≤ 1)). This process can be formulated as:
PNG
media_image3.png
72
692
media_image3.png
Greyscale
”
showing that the UNet receives
z
t
and outputs
v
^
t
=
v
^
θ
c
[AltContent: rect][AltContent: textbox (output based on receiving inputs )]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
the first output modulates a second output of the baseline diffusion model (Li, pg.6, section 4.2, “We propose to perform classifier-free guidance to both the teacher and student before calculating the loss. Specifically, for Eq. (7) and (8), after obtaining the v-prediction output of UNet, we add the CFGstep. Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
After replacing the UNet output with its guided version, all the other procedures remain the same for both the teacher and the student” where
v
^
n
c
and
v
^
n
∅
are the student models. However, it specifies that that CFG is performed on both teacher and student which means that the conditioned output (first output) of the teacher model is combined with unconditioned output thereby modulating the second output and pg. 4, figure 3, shows
v
^
θ
∅
(unconditioned output) being provide to classifier-free guidance (CFG) which are equations 7-10.)
[AltContent: rect][AltContent: textbox (Second output of the baseline model modulated by the first output )]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 14, Li teaches,
The method of Claim 8, wherein a baseline diffusion model training pipeline includes, at least, a compression stage, (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage, (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
and a step distillation step (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 15, Li teaches
A non-transitory computer-readable medium having program code recorded thereon for training a control neural network, (Li, pg.1, abstract, “As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale” suggesting presence of a non-transitory computer-readable medium and “We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation”. Based on the reference, the control neural network is being interpreted as UNet.)
the program code executed by a processor, (Li, pg.1, abstract, “As a result, high-end GPUs and cloud-based inference are required to run diffusion models at scale” suggesting the use of processors/storing instructions)
and comprising: program code to initialize a baseline diffusion model for training the control neural network, each stage of a control neural network training pipeline corresponding to an element of the baseline diffusion model (Li, pg.2, section 2.1, “we choose Stable Diffusion v1.5(SD-v1.5) as the baseline” and pg.4, fig. 3, shows the initialization of the baseline diffusion model as text encoder, VAE decoder, UNet etc.)
and program code to train, the control neural network, in a stage-wise manner, each stage of the control neural network training pipeline receiving an input from a previous stage of the control neural network training pipeline and the corresponding element of the diffusion model (Li, pg.5, section 4.1, “First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model” showing that the 16 step is used as teacher to train the 8-step efficient U-net. Each stage uses the diffusion elements like UNet and pg.4, Figure 3, shows the stage-wise manner training concept as well.)
[AltContent: textbox (This part of the figure shows the step distillation process where the teacher is used to train the student in a stage-wise manner.)][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 16, Li teaches
The non-transitory computer-readable medium of claim 15, wherein the control neural network training pipeline includes: a control neural network architecture compression stage corresponding to a compressed UNet architecture of the baseline diffusion model (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage corresponding to a guidance conditioned student model of the baseline diffusion model (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
a step distillation stage corresponding to a step distilled student model of the baseline diffusion model (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 18, Li teaches
The non-transitory computer-readable medium of claim 15, wherein the control neural network is trained to emulate behavior of the baseline diffusion model in a single forward pass (Li, pg.4, section 3.1, “Inspired by the idea of elastic depth [48, 49], we apply stochastic forward propagation to execute each cross-attention and ResNet block by probability p(·,I), where I refers to identity mapping that skips the corresponding block”)
Regarding Claim 19, Li teaches
[AltContent: textbox (Input received at the baseline model)]The non-transitory computer-readable medium of claim 15, wherein: the control neural network receives a first input received at the baseline model and an auxiliary input (Li, pg.4, figure 3, shows the input
z
t
which is received at the baseline model and c as an auxiliary input)
[AltContent: rect][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
[AltContent: textbox (auxiliary input)]
the control neural network generates a first output based on receiving the first input and the auxiliary input (Li, pg.4, figure 3, shows the UNet generating an output
v
^
θ
c
(conditioned output) based off receiving
z
t
as an input and c as an auxiliary input and pg.6, section 4.2, “Given the UNet inputs, time step t, noisy latent
z
t
,and text embedding c, the teacher UNet performs two DDIM denoising steps, from time t to t′ and then to t′′ (0 ≤ t′′ < t′ < t ≤ 1)). This process can be formulated as:
PNG
media_image3.png
72
692
media_image3.png
Greyscale
”
showing that the UNet receives
z
t
and outputs
v
^
t
=
v
^
θ
c
[AltContent: textbox (output based on receiving inputs )][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
the first output modulates a second output of the baseline diffusion model (Li, pg.6, section 4.2, “We propose to perform classifier-free guidance to both the teacher and student before calculating the loss. Specifically, for Eq. (7) and (8), after obtaining the v-prediction output of UNet, we add the CFGstep. Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
After replacing the UNet output with its guided version, all the other procedures remain the same for both the teacher and the student” where
v
^
n
c
and
v
^
n
∅
are the student models. However, it specifies that that CFG is performed on both teacher and student which means that the conditioned output (first output) of the teacher model is combined with unconditioned output thereby modulating the second output and pg. 4, figure 3, shows
v
^
θ
∅
(unconditioned output) being provide to classifier-free guidance (CFG) which are equations 7-10.)
[AltContent: textbox (Second output of the baseline model modulated by the first output )][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 21, Li teaches,
The non-transitory computer-readable medium of claim 15, wherein a baseline diffusion model training pipeline includes, at least, a compression stage, (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage, (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
and a step distillation step (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 22, Li teaches
an apparatus for training a control neural network, (Li, pg.1, abstract, “We achieve so by introducing efficient network architecture and improving step distillation. Specifically, we propose an efficient UNet by identifying the redundancy of the original model and reducing the computation of the image decoder via data distillation”. Based on the reference, the control neural network is being interpreted as UNet.)
comprising: means for initializing a baseline diffusion model for training the control neural network, each stage of a control neural network training pipeline corresponding to an element of the baseline diffusion model (Li, pg.2, section 2.1, “we choose Stable Diffusion v1.5(SD-v1.5) as the baseline” and pg.4, fig. 3, shows the initialization of the baseline diffusion model as text encoder, VAE decoder, UNet etc.)
means for training, the control neural network, in a stage-wise manner, each stage of the control neural network training pipeline receiving an input from a previous stage of the control neural network training pipeline and the corresponding element of the diffusion model (Li, pg.5, section 4.1, “First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model” showing that the 16 step is used as teacher to train the 8-step efficient U-net. Each stage uses the diffusion elements like UNet and pg.4, Figure 3, shows the stage-wise manner [AltContent: textbox (This part of the figure shows the step distillation process where the teacher is used to train the student in a stage-wise manner.)]training concept as well.)
[AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 23, Li teaches
The apparatus of claim 22, wherein the control neural network training pipeline includes: a control neural network architecture compression stage corresponding to a compressed UNet architecture of the baseline diffusion model (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage corresponding to a guidance conditioned student model of the baseline diffusion model (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
a step distillation stage corresponding to a step distilled student model of the baseline diffusion model (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Regarding Claim 25, Li teaches
The apparatus of Claim 22, wherein the control neural network is trained to emulate behavior of the baseline diffusion model in a single forward pass (Li, pg.4, section 3.1, “Inspired by the idea of elastic depth [48, 49], we apply stochastic forward propagation to execute each cross-attention and ResNet block by probability p(·,I), where I refers to identity mapping that skips the corresponding block”)
Regarding Claim 26, Li teaches
The apparatus of Claim 22, wherein: the control neural network receives a first input received at the baseline model and an auxiliary input (Li, pg.4, figure 3, shows the input
z
t
which is received at the baseline model and c as an auxiliary input)
[AltContent: rect][AltContent: rect][AltContent: textbox (Input received at the baseline model)]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
[AltContent: textbox (auxiliary input)]
the control neural network generates a first output based on receiving the first input and the auxiliary input (Li, pg.4, figure 3, shows the UNet generating an output
v
^
θ
c
(conditioned output) based off receiving
z
t
as an input and c as an auxiliary input and pg.6, section 4.2, “Given the UNet inputs, time step t, noisy latent
z
t
,and text embedding c, the teacher UNet performs two DDIM denoising steps, from time t to t′ and then to t′′ (0 ≤ t′′ < t′ < t ≤ 1)). This process can be formulated as:
PNG
media_image3.png
72
692
media_image3.png
Greyscale
”
showing that the UNet receives
z
t
and outputs
v
^
t
=
v
^
θ
c
[AltContent: textbox (output based on receiving inputs )][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
the first output modulates a second output of the baseline diffusion model (Li, pg.6, section 4.2, “We propose to perform classifier-free guidance to both the teacher and student before calculating the loss. Specifically, for Eq. (7) and (8), after obtaining the v-prediction output of UNet, we add the CFGstep. Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
After replacing the UNet output with its guided version, all the other procedures remain the same for both the teacher and the student” where
v
^
n
c
and
v
^
n
∅
are the student models. However, it specifies that that CFG is performed on both teacher and student which means that the conditioned output (first output) of the teacher model is combined with unconditioned output thereby modulating the second output and pg. 4, figure 3, shows
v
^
θ
∅
(unconditioned output) being provide to classifier-free guidance (CFG) which are equations 7-10.)
[AltContent: textbox (Second output of the baseline model modulated by the first output )][AltContent: rect]
PNG
media_image1.png
333
793
media_image1.png
Greyscale
Regarding Claim 28, Li teaches,
The apparatus of Claim 22, wherein a baseline diffusion model training pipeline includes, at least, a compression stage, (Li, pg. 4, section 3, “we investigate the architecture redundancy of SD-v1.5 to obtain efficient neural network” and section 3.1, “we perform online network changes of UNet using the model from robust training with the constructed evolution action set: A ∈ {A+,− Cross-Attention[i,j] , A+,− ResNet[i,j] }, where A+,− denotes the action to remove (−) or add (+) a cross-attention or ResNet block at the corresponding position” showing the compressed UNet architecture.)
a guidance conditioning stage, (Li, pg. 6, section 4.2, “we propose to perform classifier-free guidance to both the teacher and student before calculating the loss” which supports the idea of guidance conditioning and ““Take Eq. (8) for an example,
v
^
t
s
is replaced with the following guided version,
PNG
media_image2.png
40
442
media_image2.png
Greyscale
” where the student UNet is replaced with the guided version)
and a step distillation step (Li, pg.5, section 4, “Besides proposing the efficient architecture of the diffusion model, we further consider reducing the number of iterative denoising steps for UNet to achieve more speedup” and section 4.1“First, we do step distillation on SD-v1.5 to obtain the UNet with 16 steps that reaches the performance of the 50-step model. Second, we use the same strategy to get our 16-step efficient UNet. Finally, we use the 16-step SD-v1.5 as the teacher to conduct step distillation on the efficient UNet that is initialized from its 16-step counterpart. This will give us the 8-step efficient UNet, which is our final UNet model”)
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 3, 6, 10, 13, 17, 20, 24, 27 are rejected under 35 U.S.C. 103 as being unpatentable over Li in view of Zhang, “Adding Conditional Control to Text-to-Image Diffusion Model”
Regarding Claim 3, Li teaches,
The apparatus of Claim 1(and thus the rejection of claim 1 is incorporated), but fails to mention the weights and parameters of the baseline diffusion model.
However, Zhang teaches,
the weights and parameters of the baseline diffusion model are maintained during the training of the control neural network (Zhang, pg.4, section 3.1, “The trainable copy takes an external conditioning vector c as input. When this structure is applied to large models like Stable Diffusion, the locked parameters preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions.”)
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li and Zhang’s teaching and maintain weights and parameters of the baseline diffusion model during the training of the control neural network. The motivation to do so is “to preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 6, Li teaches
The apparatus of Claim 1 (and thus the rejection of claim 1 is incorporated), but fails to mention pre-trained diffusion model.
However, Zhang teaches,
wherein the baseline diffusion model is trained prior to training the control neural network (Zhang, pg. 3, section 3, “ControlNet is a neural network architecture that can enhance large pretrained text-to-image diffusion models with spatially localized, task-specific image conditions”).
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li’s and Zhang’s teachings and train the diffusion model prior to the training of the control neural network. The motivation to do so is “to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 10, Li teaches,
The method of Claim 8 (and thus the rejection of claim 8 is incorporated), but fails to mention the weights and parameters of the baseline diffusion model.
However, Zhang teaches,
the weights and parameters of the baseline diffusion model are maintained during the training of the control neural network (Zhang, pg.4, section 3.1, “The trainable copy takes an external conditioning vector c as input. When this structure is applied to large models like Stable Diffusion, the locked parameters preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions.”)
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li and Zhang’s teaching and maintain weights and parameters of the baseline diffusion model during the training of the control neural network. The motivation to do so is “to preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 13, Li teaches,
The method of Claim 8 (and thus the rejection of claim 8 is incorporated), but fails to mention pre-trained diffusion model.
However, Zhang teaches,
wherein the baseline diffusion model is trained prior to training the control neural network (Zhang, pg. 3, section 3, “ControlNet is a neural network architecture that can enhance large pretrained text-to-image diffusion models with spatially localized, task-specific image conditions”).
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li’s and Zhang’s teachings and train the diffusion model prior to the training of the control neural network. The motivation to do so is “to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 17, Li teaches,
The non-transitory computer-readable medium of claim 15 (and thus the rejection of claim 15 is incorporated), but fails to mention the weights and parameters of the baseline diffusion model.
However, Zhang teaches,
the weights and parameters of the baseline diffusion model are maintained during the training of the control neural network (Zhang, pg.4, section 3.1, “The trainable copy takes an external conditioning vector c as input. When this structure is applied to large models like Stable Diffusion, the locked parameters preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions.”)
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li and Zhang’s teaching and maintain weights and parameters of the baseline diffusion model during the training of the control neural network. The motivation to do so is “to preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 20, Li teaches,
The non-transitory computer-readable medium of claim 15 (and thus the rejection of claim 15 is incorporated), but fails to mention pre-trained diffusion model.
However, Zhang teaches,
wherein the baseline diffusion model is trained prior to training the control neural network (Zhang, pg. 3, section 3, “ControlNet is a neural network architecture that can enhance large pretrained text-to-image diffusion models with spatially localized, task-specific image conditions”).
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li’s and Zhang’s teachings and train the diffusion model prior to the training of the control neural network. The motivation to do so is “to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 24, Li teaches,
The apparatus of claim 22 (and thus the rejection of claim 22 is incorporated), but fails to mention the weights and parameters of the baseline diffusion model.
However, Zhang teaches,
the weights and parameters of the baseline diffusion model are maintained during the training of the control neural network (Zhang, pg.4, section 3.1, “The trainable copy takes an external conditioning vector c as input. When this structure is applied to large models like Stable Diffusion, the locked parameters preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions.”)
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li and Zhang’s teaching and maintain weights and parameters of the baseline diffusion model during the training of the control neural network. The motivation to do so is “to preserve the production-ready model trained with billions of images, while the trainable copy reuses such large scale pretrained model to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
Regarding Claim 27, Li teaches,
The apparatus of claim 22 (and thus the rejection of claim 22 is incorporated), but fails to mention pre-trained diffusion model.
However, Zhang teaches,
wherein the baseline diffusion model is trained prior to training the control neural network (Zhang, pg. 3, section 3, “ControlNet is a neural network architecture that can enhance large pretrained text-to-image diffusion models with spatially localized, task-specific image conditions”).
It would’ve been obvious to one of the ordinary skills in the art before the filling date of the claimed invention to combine Li’s and Zhang’s teachings and train the diffusion model prior to the training of the control neural network. The motivation to do so is “to establish a deep, robust, and strong backbone for handling diverse input conditions” (Zhang, pg.4, section 3.1)
ConclusionAny inquiry concerning this communication or earlier communications from the examiner should be directed to PRAYUKTA GHIMIRE whose telephone number is (571)270-5484. The examiner can normally be reached M-F, 9 am to 5 pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kakali Chaki can be reached at (571) 272-3719. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/P.N.G./Examiner, Art Unit 2122
/KAKALI CHAKI/Supervisory Patent Examiner, Art Unit 2122
Prosecution Insights