rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper
•
2501.04519
•
Published
•
272
•
42
Ksenia Se
Kseniase
AI & ML interests
None yet
Recent Activity
replied to
their
post
4 days ago
9 Multimodal Chain-of-Thought methods
How Chain-of-Thought (CoT) prompting can unlock models' full potential across images, video, audio and more? Finding special multimodal CoT techniques is the answer.
Here are 9 methods of Multimodal Chain-of-Thought (MCoT). Most of them are open-source:
1. KAM-CoT -> https://huggingface.co/papers/2401.12863
This lightweight framework combines CoT prompting with knowledge graphs (KGs) and achieves 93.87% accuracy
2. Multimodal Visualization-of-Thought (MVoT) -> https://huggingface.co/papers/2501.07542
Lets models generate visual reasoning traces, using a token discrepancy loss to improve visual quality
3. Compositional CoT (CCoT) -> https://huggingface.co/papers/2311.17076
Uses scene graph (SG) representations generated by the LMM itself to improve performance on compositional and general multimodal benchmarks
4. URSA -> https://huggingface.co/papers/2501.04686
Brings System 2-style thinking to multimodal math reasoning, using a 3-module CoT data synthesis process with CoT distillation, trajectory-format rewriting and format unification
5. MM-Verify -> https://huggingface.co/papers/2502.13383
Introduces a verification mechanism with MM-Verifier and MM-Reasoner that implements synthesized high-quality CoT data for multimodal reasoning
6. Duty-Distinct CoT (DDCoT) -> https://huggingface.co/papers/2310.16436
Divides the reasoning responsibilities between LMs and visual models, integrating the visual recognition capabilities into the joint reasoning process
7. Multimodal-CoT from Amazon Web Services -> https://huggingface.co/papers/2302.00923
A two-stage framework separates rationale generation from answer prediction, allowing the model to reason more effectively using multimodal inputs
8. Graph-of-Thought (GoT) -> https://huggingface.co/papers/2305.16582
This two-stage framework models reasoning as a graph of interconnected ideas, improving performance on text-only and multimodal tasks
More in the comments👇
posted
an
update
4 days ago
9 Multimodal Chain-of-Thought methods
How Chain-of-Thought (CoT) prompting can unlock models' full potential across images, video, audio and more? Finding special multimodal CoT techniques is the answer.
Here are 9 methods of Multimodal Chain-of-Thought (MCoT). Most of them are open-source:
1. KAM-CoT -> https://huggingface.co/papers/2401.12863
This lightweight framework combines CoT prompting with knowledge graphs (KGs) and achieves 93.87% accuracy
2. Multimodal Visualization-of-Thought (MVoT) -> https://huggingface.co/papers/2501.07542
Lets models generate visual reasoning traces, using a token discrepancy loss to improve visual quality
3. Compositional CoT (CCoT) -> https://huggingface.co/papers/2311.17076
Uses scene graph (SG) representations generated by the LMM itself to improve performance on compositional and general multimodal benchmarks
4. URSA -> https://huggingface.co/papers/2501.04686
Brings System 2-style thinking to multimodal math reasoning, using a 3-module CoT data synthesis process with CoT distillation, trajectory-format rewriting and format unification
5. MM-Verify -> https://huggingface.co/papers/2502.13383
Introduces a verification mechanism with MM-Verifier and MM-Reasoner that implements synthesized high-quality CoT data for multimodal reasoning
6. Duty-Distinct CoT (DDCoT) -> https://huggingface.co/papers/2310.16436
Divides the reasoning responsibilities between LMs and visual models, integrating the visual recognition capabilities into the joint reasoning process
7. Multimodal-CoT from Amazon Web Services -> https://huggingface.co/papers/2302.00923
A two-stage framework separates rationale generation from answer prediction, allowing the model to reason more effectively using multimodal inputs
8. Graph-of-Thought (GoT) -> https://huggingface.co/papers/2305.16582
This two-stage framework models reasoning as a graph of interconnected ideas, improving performance on text-only and multimodal tasks
More in the comments👇
upvoted
a
paper
5 days ago
Mutual Theory of Mind for Human-AI Communication
Organizations
Kseniase's activity
commented
a
paper
3 months ago