REVIEW 6 cited by
Vision-Language Models Can Self-Improve Reasoning via Reflection
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Chain-of-thought (CoT) has proven to improve the reasoning capability of large language models (LLMs). However, due to the complexity of multimodal scenarios and the difficulty in collecting high-quality CoT data, CoT reasoning in multimodal LLMs has been largely overlooked. To this end, we propose a simple yet effective self-training framework, R3V, which iteratively enhances the model's Vision-language Reasoning by Reflecting on CoT Rationales. Our framework consists of two interleaved parts: (1) iteratively bootstrapping positive and negative solutions for reasoning datasets, and (2) reflection on rationale for learning from mistakes. Specifically, we introduce the self-refine and self-select losses, enabling the model to refine flawed rationale and derive the correct answer by comparing rationale candidates. Experiments on a wide range of vision-language tasks show that R3V consistently improves multimodal LLM reasoning, achieving a relative improvement of 23 to 60 percent over GPT-distilled baselines. Additionally, our approach supports self-reflection on generated solutions, further boosting performance through test-time computation.
Forward citations
Cited by 6 Pith papers
-
Egocentric Bias in Vision-Language Models
Most vision-language models fail Level-2 visual perspective taking: they report the camera's view rather than the 180°-rotated string, even though they often recognize that another agent sees differently.
-
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
An attention-based action head with multi-patch supervision outperforms coordinate-generation baselines on GUI grounding, and a verifier further improves accuracy.
-
Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning
A self-critique, revision, and verification loop makes small vision-language models produce more detailed and more executable robot plans, beating their own baselines and, on the paper's judge-based evaluation, plans ...
-
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
VReST combines Monte Carlo tree search with a self-reward signal inside a vision-language model to get higher accuracy than CoT, ToT, or voting baselines on MathVista, MathVision, and CharXiv, while spending several t...
-
Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
Using a two-stage SFT-plus-GRPO pipeline, the authors train 3B and 7B multimodal models that beat prior open-source models on four math reasoning benchmarks, while showing that reflective 'aha moment' text is not a re...
-
Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
On a PMC-VQA subset, GRPO-based RL fine-tuning of Qwen2-VL-2B-Instruct outperforms SFT in accuracy, but the study has no error bars and several prose claims conflict with its own table.
Discussion (0). Sign in to comment.