Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data
Paper • 2608.23256 • Published • 22
Fang
Youqing
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
None yet
upvoted a paper 24 days ago
upvoted a paper 26 days ago
upvoted 3
papers 2 months ago
Group Entropy-Controlled Policy Optimization
Paper • 2607.16850 • Published • 30
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
Paper • 2607.11849 • Published • 29
Scalable Visual Pretraining for Language Intelligence
Paper • 2607.09657 • Published • 56
upvoted a paper 4 months ago
upvoted a paper 6 months ago
upvoted 3
papers 9 months ago
Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
Paper • 2512.10739 • Published • 47
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Paper • 2512.10534 • Published • 33
OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification
Paper • 2512.10756 • Published • 36
upvoted a paper 10 months ago
upvoted a paper about 1 year ago
liked a
Space over 1 year ago
upvoted 3
papers over 1 year ago
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space
Paper • 2504.13835 • Published • 39
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 312
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
Paper • 2503.14478 • Published • 48
liked a
Space over 1 year ago
liked a
Space almost 2 years ago
authored a
paper about 2 years ago