Reasoning Models Struggle to Control their Chains of Thought
Paper
• 2603.05706 • Published
• 24
Haoning Wu, Teo PRO
teowu
AI & ML interests
Lead of Q-Future: https://github.com/Q-Future. I love MLLMs/LMMs/LVLMs/(any names you call them). Part of two great MoE VLMs as core contributors: Kimi-VL & Aria. Living and Cooking in Singapore Now.
Recent Activity
upvoted a paper 2 days ago
Reasoning Models Struggle to Control their Chains of Thought liked
a dataset 10 days ago
VLR-CVC/DocVQA-2026 updated
a model 12 days ago
moonshotai/Kimi-K2.5 Organizations
upvoted a paper 2 days ago
upvoted 2 papers about 1 month ago
upvoted a paper 8 months ago
upvoted a collection 9 months ago
upvoted an article 9 months ago
Article
🤔👀🎬🖥️📖 Kimi-VL-A3B-Thinking-2506: A Quick Navigation
•
77
upvoted 3 papers 9 months ago
upvoted a collection 11 months ago
upvoted 3 papers 11 months ago
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper
• 2504.08837 • Published
• 43
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper
• 2504.10479 • Published
• 306
Kimi-VL Technical Report
Paper
• 2504.07491 • Published
• 137
upvoted 6 papers about 1 year ago
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
• 2502.14786 • Published
• 159
Qwen2.5-VL Technical Report
Paper
• 2502.13923 • Published
• 214
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation
Paper
• 2411.13281 • Published
• 20
Redundancy Principles for MLLMs Benchmarks
Paper
• 2501.13953 • Published
• 29
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper
• 2501.12948 • Published
• 441
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper
• 2501.12599 • Published
• 126
upvoted a paper over 1 year ago