-
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper • 2502.14768 • Published • 47 -
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper • 2502.12853 • Published • 29 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 18 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 47
🐌 Focus
shanshan wang
cooleel
AI & ML interests
Applied AI, Document AI, Multimodality models, AI infrastructure, RL
Recent Activity
authored a paper about 15 hours ago
H2OVL-Mississippi Vision Language Models Technical Report upvoted an article about 15 hours ago
NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models liked a model about 15 hours ago
nvidia/Nemotron-3.5-ParseOrganizations
-
Prompt-to-Leaderboard
Paper • 2502.14855 • Published • 7 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper • 2502.16894 • Published • 33 -
Generating Skyline Datasets for Data Science Models
Paper • 2502.11262 • Published • 7 -
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
Paper • 2502.12501 • Published • 6
-
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Paper • 2502.14768 • Published • 47 -
S^2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Paper • 2502.12853 • Published • 29 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 18 -
Distillation Scaling Laws
Paper • 2502.08606 • Published • 47
-
Prompt-to-Leaderboard
Paper • 2502.14855 • Published • 7 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper • 2502.16894 • Published • 33 -
Generating Skyline Datasets for Data Science Models
Paper • 2502.11262 • Published • 7 -
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
Paper • 2502.12501 • Published • 6
models 0
None public yet