Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 312
Anwar
abdoali5672
AI & ML interests
None yet
Recent Activity
upvoted a paper 24 minutes ago
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models upvoted a paper 28 minutes ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and MitigationOrganizations
None yet
upvoted 2
papers 24 minutes ago
upvoted a paper 28 minutes ago
upvoted a paper 29 minutes ago
upvoted 4
papers 9 days ago
Self-Distilled RLVR
Paper • 2604.03128 • Published • 160
LightThinker++: From Reasoning Compression to Memory Management
Paper • 2604.03679 • Published • 35
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 200
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 107
upvoted a paper 10 days ago
upvoted a paper 11 days ago
upvoted 9
papers 14 days ago
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Paper • 2604.02268 • Published • 93
Generative World Renderer
Paper • 2604.02329 • Published • 101
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers
Paper • 2603.24414 • Published • 183
Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
Paper • 2604.00007 • Published • 19
Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training
Paper • 2602.07824 • Published • 18
daVinci-LLM:Towards the Science of Pretraining
Paper • 2603.27164 • Published • 33
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 143
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 337
Terminal Agents Suffice for Enterprise Automation
Paper • 2604.00073 • Published • 95
upvoted a paper 16 days ago