Ksenia Se's picture

1 89 3

Ksenia Se

Kseniase

·

https://www.turingpost.com/

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

View all activity

Organizations

Kseniase's activity

published an article 14 days ago

Article

What is Qwen-Agent framework? Inside the Qwen family

By

and 1 other •

14 days ago

• 8

published an article 15 days ago

Article

🌁#92: Fight for Developers and the Year of Orchestration

By

•

15 days ago

• 5

published an article 17 days ago

Article

🦸🏻#14: What Is MCP, and Why Is Everyone – Suddenly!– Talking About It?

By

•

17 days ago

• 117

published an article 20 days ago

Article

How to Reduce Memory Use in Reasoning Models

By

and 1 other •

20 days ago

• 12

published an article 23 days ago

Article

🌁#91: We are failing in AI literacy

By

and 1 other •

23 days ago

• 3

published an article 23 days ago

Article

🌁#90: Why AI’s Reasoning Tests Keep Failing Us

By

•

about 1 month ago

• 9

published an article 24 days ago

Article

🦸🏻#13: Action! How AI Agents Execute Tasks with UI and API Tools

By

•

24 days ago

• 8

published an article 25 days ago

Article

🦸🏻#12: How Do Agents Learn from Their Own Mistakes? The Role of Reflection in AI

By

•

25 days ago

• 6

published an article 27 days ago

Article

Everything You Need to Know about Knowledge Distillation

By

and 1 other •

27 days ago

• 21

published an article about 1 month ago

Article

Inside the family of Smol models

By

and 1 other •

Feb 27

• 9

published an article about 1 month ago

Article

🌁#89: AI in Action: How AI Engineers, Self-Optimizing Models, and Humanoid Robots Are Reshaping 2025

By

•

Feb 25

• 4

published an article about 1 month ago

Article

🦸🏻#11: How Do Agents Plan and Reason?

By

•

Feb 24

• 10

published an article about 1 month ago

Article

Topic 28: What is Mixture-of-Mamba?

By

and 1 other •

Feb 20

• 3

published an article about 1 month ago

Article

🌁#88: Can DeepSeek Inspire Global Collaboration?

By

•

Feb 17

• 3

published an article about 2 months ago

Article

🦸🏻#10: Does Present-Day GenAI Actually Reason?

By

•

Feb 15

• 7

published an article about 2 months ago

Article

Topic 27: What are Chain-of-Agents and Chain-of-RAG?

By

and 1 other •

Feb 13

• 13

published an article about 2 months ago

Article

🌁#87: Why DeepResearch Should Be Your New Hire

By

•

Feb 10

• 5

published an article about 2 months ago

Article

What is test-time compute and how to scale it?

By

and 1 other •

Feb 6

• 66