DETAILED ACTION
This action is in response to the submission filed 23 October 2026 for application 18/492,508. Currently claims 1-28 are pending and have been examined.
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 .
Information Disclosure Statement
Information disclosure statements (IDS) were submitted on 6 May 2025, 7 April 2025, and 13 February 2025. The submissions are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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.
Claims 22, 24, 26, and 28 are being interpreted under 35 U.S.C. 112(f).
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.
Claims 19-21 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.
Claims 19 and 21 recite the limitations "… the instructions…" and “…the apparatus…” in line 2. There is insufficient antecedent basis for this limitation in the claim. Claim 20 depends from claim 19 and hence, is rejected for the same reason.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 4, 8, 10, 11, 15, 17, 18, 22, 24, and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Salimans et al (PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS, 2022) in view of Tseng et al (Using Kernel Density Estimation in Knowledge Distillation to Construct the Prediction Model for Bipolar Disorder Patients, 2023).
Regarding claim 1:
Salimans teaches: An apparatus for training a diffusion model, 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, to cause the apparatus to ([Page 1, Abstract] First, we present new parameterizations of diffusion models. [Page 6, Last but Paragraph] For computational efficiency, and for comparisons to established methods in the literature, we use unconditional CIFAR-10 as the benchmark. [Page 16, Paragraph 1] We run our experiments on TPUv4, using 8 TPU chips for CIFAR-10, and 64 chips for the other data sets. Note: Chips correspond to processors and computational efficiency corresponds to one or more memories coupled with the one or more processors and storing instructions operable):
randomly select, for each iteration of a step distillation training process, a teacher model ([Page 3, Section 3, Paragraph 1] To make diffusion models more efficient at sampling time, we propose progressive distillation: an algorithm that iteratively halves the number of required sampling steps by distilling a slow teacher diffusion model);
apply, at each iteration, a clipped input space within step distillation of the randomly selected teacher model ([Page 3, Section 3, Paragraph 2] We start the progressive distillation procedure with a teacher diffusion model that is obtained by training in the standard way. At every iteration of progressive distillation, we then initialize the student model with a copy of the teacher, using both the same parameters and same model definition. Like in standard training, we then sample data from the training set and add noise to it, before forming the training loss by applying the student denoising model to this noisy data zt. [Page 5, Paragraph 1] This is not much of a problem when taking many steps, since the effect of early missteps is limited by clipping of the zt iterates);
and update, at each iteration, parameters of the diffusion model based on guidance from the randomly selected teacher model ([Page 7, Section 5.2, Paragraph 1] For CIFAR-10 we start progressive distillation from a teacher model taking 8192 steps. For the bigger data sets we start at 1024 steps. At every iteration of distillation we train for 50 thousand parameter updates, except for the distillation to 2 and 1 sampling steps, for which we use 100 thousand updates).
However, Salimans does not explicitly disclose: of a group of teacher models.
Tseng teaches, in an analogous system: of a group of teacher models ([Page 2, Last but one Paragraph] the group of teacher models).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the apparatus of Salimans to incorporate the teachings of Tseng to use a group of teacher models. One would have been motivated to do this modification because doing so would give the benefit of being conditional distributions for the input data and can be used as the learning targets for the student model as taught by Tseng [Page 2, Last but one Paragraph].
Regarding claim 3:
The system of Salimans and Tseng teaches: The apparatus of claim 1 (as shown above).
Salimans further teaches: further comprising applying a signal-to-noise ratio (SNR) loss in accordance with a schedule during the step distillation training process ([Page 2, Section 2, Paragraph 1] A diffusion model has latent variables z = fzt j t 2 [0; 1]g and is specified by a noise schedule comprising differentiable functions t; t such that t = log[2t =2t ], the log signal-to-noise-ratio, decreases monotonically with t. [Page 4, Paragraph 3] Unlike our procedure for training the original model, we always run progressive distillation in discrete time: we sample this discrete time such that the highest time index corresponds to a signal-to noise ratio of zero, i.e. 1 = 0, which exactly matches the distribution of input noise z1 N(0; I) that is used at test time. We found this to work slightly better than starting from a non-zero signal to-noise ratio).
Regarding claim 4:
The system of Salimans and Tseng teaches: The apparatus of claim 3 (as shown above).
Salimans further teaches: wherein the schedule disables the SNR loss for at least a first iteration or first gradient update within the step distillation training process ([Page 4, Paragraph 2] After running distillation to learn a student model taking N sampling steps, we can repeat the procedure with N=2 steps: The student model then becomes the new teacher, and a new student model is initialized by making a copy of this model. [Page 4, Paragraph 2] Unlike our procedure for training the original model, we always run progressive distillation in discrete time: we sample this discrete time such that the highest time index corresponds to a signal-to noise ratio of zero, i.e. 1 = 0, which exactly matches the distribution of input noise z1 N(0; I) that is used at test time. Note: signal-to noise ratio of zero corresponds to disabling SNR loss).
Regarding claim 8:
Claim 8 is substantially similar to claim 1 and therefore is rejected on similar grounds as claim 1.
Regarding claim 10:
Claim 10 is substantially similar to claim 3 and therefore is rejected on similar grounds as claim 3.
Regarding claim 11:
Claim 11 is substantially similar to claim 4 and therefore is rejected on similar grounds as claim 4.
Regarding claim 15:
Claim 15 is substantially similar to claim 1 and therefore is rejected on similar grounds as claim 1.
Regarding claim 17:
Claim 17 is substantially similar to claim 3 and therefore is rejected on similar grounds as claim 3.
Regarding claim 18:
Claim 18 is substantially similar to claim 4 and therefore is rejected on similar grounds as claim 4.
Regarding claim 22:
Claim 22 is substantially similar to claim 1 and therefore is rejected on similar grounds as claim 1.
Regarding claim 24:
Claim 24 is substantially similar to claim 3 and therefore is rejected on similar grounds as claim 3.
Regarding claim 25:
Claim 25 is substantially similar to claim 4 and therefore is rejected on similar grounds as claim 4.
Claims 2, 9, 16, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Salimans et al (PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS, 2022) in view of Tseng et al (Using Kernel Density Estimation in Knowledge Distillation to Construct the Prediction Model for Bipolar Disorder Patients, 2023) and further in view of Li et al (SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds, 2023).
Regarding claim 2:
The system of Salimans and Tseng teaches: The apparatus of claim 1 (as shown above).
However, the system of Salimans and Tseng does not explicitly disclose: wherein the group of teacher models include a guidance conditioned teacher model and a classifier free guidance (CFG) teacher model.
Li teaches, in an analogous system: wherein the group of teacher models include a guidance conditioned teacher model and a classifier free guidance (CFG) teacher model ([Page 3, Section Latent Diffusion Model / Stable Diffusion, Paragraph 1] When synthesizing images, an important technique, classifier-free guidance (CFG) [33], is adopted to improve quality. The guidance scale w can be adjusted to control the strength of conditional information on the generated images to achieve the trade-off between quality and diversity).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined teachings of Salimans and Tseng to incorporate the teachings of Li wherein the group of teacher models include a guidance conditioned teacher model and a classifier free guidance (CFG) teacher model. One would have been motivated to do this modification because doing so would give the benefit of improving quality as taught by Li [Page 3, Section Latent Diffusion Model / Stable Diffusion, Paragraph 1].
Regarding claim 9:
Claim 9 is substantially similar to claim 2 and therefore is rejected on similar grounds as claim 2.
Regarding claim 16:
Claim 16 is substantially similar to claim 2 and therefore is rejected on similar grounds as claim 2.
Regarding claim 23:
Claim 23 is substantially similar to claim 2 and therefore is rejected on similar grounds as claim 2.
Claims 5, 6, 12, 13, 19, 20, 26, and 27 are rejected under 35 U.S.C. 103 as being unpatentable over Salimans et al (PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS, 2022) in view of Tseng et al (Using Kernel Density Estimation in Knowledge Distillation to Construct the Prediction Model for Bipolar Disorder Patients, 2023) and further in view of Weng et al (ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image, 2023).
Regarding claim 5:
The system of Salimans and Tseng teaches: The apparatus of claim 1 (as shown above).
However, the system of Salimans and Tseng does not explicitly disclose: wherein execution of the instructions further caused the apparatus to perform, at an end of the step distillation training process, an end-to-end fine-tuning process on the diffusion model to regularize the diffusion model.
Weng teaches, in an analogous system: wherein execution of the instructions further caused the apparatus to perform, at an end of the step distillation training process, an end-to-end fine-tuning process on the diffusion model to regularize the diffusion model ([Page 1, Abstract] Then during optimization, we use the posed parametric body as additional geometry constraint to regularize the diffusion model. [Page 3, Paragraph 3] These methods require end-to-end training, and therefore have limited generalization capability due to the scarcity of available 3D human scans. ZeroAvatar is analogous to the optimization-based model-based HMR methods in that we optimize a 3D representation of the human body to achieve consistency with the input image).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined teachings of Salimans and Tseng to incorporate the teachings of Weng wherein execution of the instructions further caused the apparatus to perform, at an end of the step distillation training process, an end-to-end fine-tuning process on the diffusion model to regularize the diffusion model. One would have been motivated to do this modification because doing so would give the benefit of optimizing a 3D representation to achieve consistency with the input image as taught by Weng [Page 3, Paragraph 3].
Regarding claim 6:
The system of Salimans and Tseng teaches: The apparatus of claim 5 (as shown above).
However, the system of Salimans and Tseng does not explicitly disclose: wherein the end-to-end fine-tuning process regularizes a score function estimate.
Weng teaches, in an analogous system: wherein the end-to-end fine-tuning process regularizes a score function estimate ([Page 1, Abstract] This is achieved by score distillation, a methodology that uses pre-trained text-to-image diffusion models to optimize the parameters of a 3D neural presentation, e.g. Neural Radiance Field (NeRF). Then during optimization, we use the posed parametric body as additional geometry constraint to regularize the diffusion model. [Page 3, Figure 2, Paragraph 1] Then, we optimize the appearance and refine the geometry of the person using Score Distillation Sampling [Page 3, Paragraph 3] These methods require end-to-end training, and therefore have limited generalization capability due to the scarcity of available 3D human scans. ZeroAvatar is analogous to the optimization-based model-based HMR methods in that we optimize a 3D representation of the human body to achieve consistency with the input image).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined teachings of Salimans and Tseng to incorporate the teachings of Weng wherein the end-to-end fine-tuning process regularizes a score function estimate. One would have been motivated to do this modification because doing so would give the benefit of optimizing a 3D representation to achieve consistency with the input image as taught by Weng [Page 3, Paragraph 3].
Regarding claim 12:
Claim 12 is substantially similar to claim 5 and therefore is rejected on similar grounds as claim 5.
Regarding claim 13:
Claim 13 is substantially similar to claim 6 and therefore is rejected on similar grounds as claim 6.
Regarding claim 19:
Claim 19 is substantially similar to claim 5 and therefore is rejected on similar grounds as claim 5.
Regarding claim 20:
Claim 20 is substantially similar to claim 6 and therefore is rejected on similar grounds as claim 6.
Regarding claim 26:
Claim 26 is substantially similar to claim 5 and therefore is rejected on similar grounds as claim 5.
Regarding claim 27:
Claim 27 is substantially similar to claim 6 and therefore is rejected on similar grounds as claim 6.
Claims 7, 14, 21, and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Salimans et al (PROGRESSIVE DISTILLATION FOR FAST SAMPLING OF DIFFUSION MODELS, 2022) in view of Tseng et al (Using Kernel Density Estimation in Knowledge Distillation to Construct the Prediction Model for Bipolar Disorder Patients, 2023) and further in view of Ntavelis et al (Autodecoding Latent 3D Diffusion Models, 2023).
Regarding claim 7:
The system of Salimans and Tseng teaches: The apparatus of claim 1 (as shown above).
However, the system of Salimans and Tseng does not explicitly disclose: wherein execution of the instructions further caused the apparatus to perform a diffusion inference based on training the diffusion model.
Ntavelis teaches, in an analogous system: wherein execution of the instructions further caused the apparatus to perform a diffusion inference based on training the diffusion model ([Page 1, Abstract] Then during optimization, we use the posed parametric body as additional geometry constraint to regularize the diffusion model. [Page 3, Paragraph 3] These methods require end-to-end training, and therefore have limited generalization capability due to the scarcity of available 3D human scans. ZeroAvatar is analogous to the optimization-based model-based HMR methods in that we optimize a 3D representation of the human body to achieve consistency with the input image).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the combined teachings of Salimans and Tseng to incorporate the teachings of Ntavelis wherein execution of the instructions further caused the apparatus to perform a diffusion inference based on training the diffusion model. One would have been motivated to do this modification because doing so would give the benefit of designing and training denoising diffusion models 3D-aware content suitable for efficient usage with datasets of various scales as taught by Ntavelis [Page 2, Paragraph 2].
Regarding claim 14:
Claim 14 is substantially similar to claim 7 and therefore is rejected on similar grounds as claim 7.
Regarding claim 21:
Claim 21 is substantially similar to claim 7 and therefore is rejected on similar grounds as claim 7.
Regarding claim 28:
Claim 28 is substantially similar to claim 7 and therefore is rejected on similar grounds as claim 7.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu et al (InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation, 2023) discloses the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Fréchet Inception Distance) of 23.3 on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation [3], by a significant margin (37.2 → 23.3 in FID). By utilizing an expanded network with 1.7B parameters, we further improve the FID to 22.4. We call our one-step models InstaFlow.
Ho et al (Denoising Diffusion Probabilistic Models, 2020) discloses high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHAITANYA RAMESH JAYAKUMAR whose telephone number is (571)272-3369. The examiner can normally be reached Mon-Fri 9am-1pm.
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, Omar Fernandez Rivas can be reached at (571)272-2589. 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.
/C.R.J./Examiner, Art Unit 2128
/OMAR F FERNANDEZ RIVAS/Supervisory Patent Examiner, Art Unit 2128
Prosecution Insights