From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Paper
•
2504.16080
•
Published
•
15
Personal Coding Assistant
AI & ML interests
Code language models.
Recent Activity
coding-assistant-custom's activity
sayakpaul
authored
a
paper
5 days ago
lvwerra
authored
a
paper
20 days ago
Post
3514
simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL
I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
- 5 replies
Post
2593
Mistral AI Small 3.1 24B is not only commercial free but also the best model in a single GPU deployment.
I packed up all the information you need to know in a single picture. Hope this helps! :)
I packed up all the information you need to know in a single picture. Hope this helps! :)
- 1 reply
sayakpaul
authored
a
paper
about 2 months ago
Post
1571
Gemma 3 Release in a nutshell
(seems like function calling is not supported whereas the announcement said so)
(seems like function calling is not supported whereas the announcement said so)
Post
3648
Inference-time scaling meets Flux.1-Dev (and others) 🔥
Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.
I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.
Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗
The steps are simple:
For each round:
1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.
If you have more compute budget, go to the next search round. Scale the noise pool (
This constitutes the random search method as done in the paper by Google DeepMind.
Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗
Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.
I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.
Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗
The steps are simple:
For each round:
1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.
If you have more compute budget, go to the next search round. Scale the noise pool (
2 ** search_round) and repeat 1 - 3.This constitutes the random search method as done in the paper by Google DeepMind.
Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗
lvwerra
authored
a
paper
3 months ago
Post
3017
Simple Paper Review #5
I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University
The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.
The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.
I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.
https://arxiv.org/abs/2501.17161
I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University
The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.
The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.
I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.
https://arxiv.org/abs/2501.17161
Post
4405
A brief summary of the o3-mini
The OpenAI o3-mini model is a significant improvement over the o1-mini, reaching o1 performance levels. While generally good, its performance isn't universally better than previous models (o1, o1-prev.) or GPT-4o across all benchmarks. This means workflows should be re-evaluated with each model upgrade.
The o3-mini has "low," "medium," and "high" versions, with "low" being the base model used for benchmarking. It's speculated that the higher versions simply involve more processing. A fair comparison with other models like Gemini 2.0 Thinking or DeepSeek-R1 would likely need to use the "low" version and a similar "think more" mechanism.
The system card is recommended reading due to its comprehensive benchmark data.
https://openai.com/index/openai-o3-mini/
The OpenAI o3-mini model is a significant improvement over the o1-mini, reaching o1 performance levels. While generally good, its performance isn't universally better than previous models (o1, o1-prev.) or GPT-4o across all benchmarks. This means workflows should be re-evaluated with each model upgrade.
The o3-mini has "low," "medium," and "high" versions, with "low" being the base model used for benchmarking. It's speculated that the higher versions simply involve more processing. A fair comparison with other models like Gemini 2.0 Thinking or DeepSeek-R1 would likely need to use the "low" version and a similar "think more" mechanism.
The system card is recommended reading due to its comprehensive benchmark data.
https://openai.com/index/openai-o3-mini/
Post
2076
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc.
We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:
* Models and datasets:
finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:
* Models and datasets:
finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
- 1 reply
Post
2033
Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
Post
2026
We have authored a post to go over the state of video generation in the Diffusers ecosystem 🧨
We cover the models supported, the knobs of optims our users can fire, fine-tuning, and more 🔥
5-6GBs for HunyuanVideo, sky is the limit 🌌 🤗
https://huggingface.co./blog/video_gen
We cover the models supported, the knobs of optims our users can fire, fine-tuning, and more 🔥
5-6GBs for HunyuanVideo, sky is the limit 🌌 🤗
https://huggingface.co./blog/video_gen
Post
1740
New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the
@akhaliq
)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.
Link: https://deep-diver.github.io/ai-paper-reviewer/
This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)
Post
2036
Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.
The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).
Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.
However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)
https://arxiv.org/abs/2501.09891
Post
2078
Simple Summarization on DeepSeek-R1 from DeepSeek AI
The RL stage is very important.
↳ However, it is difficult to create a truly helpful AI for people solely through RL.
↳ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
↳ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model:
deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
The RL stage is very important.
↳ However, it is difficult to create a truly helpful AI for people solely through RL.
↳ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
↳ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.
Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.
Model:
deepseek-ai
Paper: https://github.com/deepseek-ai/DeepSeek-R1
- 1 reply
lvwerra
authored
a
paper
3 months ago
Post
4429
Commits speak louder than words 🤪
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
Post
2248
In the past seven days, the Diffusers team has shipped:
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
-
- 1 reply
chansung
authored
a
paper
5 months ago