Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 308
Jancee Rod C.
theycallmejan
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
OpenWorldLib: A Unified Codebase and Definition of Advanced World ModelsOrganizations
None yet
upvoted 3
papers 3 days ago
upvoted a paper 4 months ago
upvoted 2
papers 9 months ago
upvoted 5
papers 10 months ago
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 274
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Paper • 2506.06395 • Published • 135
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
Paper • 2506.06751 • Published • 71
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 265
Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
Paper • 2505.24726 • Published • 282
upvoted 4
papers 11 months ago
Emerging Properties in Unified Multimodal Pretraining
Paper • 2505.14683 • Published • 134
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
Paper • 2505.10554 • Published • 120
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
Paper • 2505.07916 • Published • 135
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Paper • 2505.04921 • Published • 187
upvoted 2
papers 12 months ago
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 141
ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
Paper • 2504.10514 • Published • 48
upvoted 3
papers about 1 year ago