Chengsong Huang

ChengsongHuang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 1 day ago

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Paper • 2510.25992 • Published 3 days ago • 25

The End of Manual Decoding: Towards Truly End-to-End Language Models

Paper • 2510.26697 • Published 2 days ago • 90

upvoted 3 papers 3 days ago

SPICE: Self-Play In Corpus Environments Improves Reasoning

Paper • 2510.24684 • Published 4 days ago • 11

VisCoder2: Building Multi-Language Visualization Coding Agents

Paper • 2510.23642 • Published 8 days ago • 20

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published 4 days ago • 82

upvoted a paper 5 days ago

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Paper • 2510.14901 • Published 16 days ago • 44

upvoted 2 papers 8 days ago

Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1

Paper • 2510.19600 • Published 10 days ago • 66

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Paper • 2510.19779 • Published 10 days ago • 58

updated 2 datasets 9 days ago

HINT-lab/sft_Qwen_Qwen3-1.7B

Viewer • Updated 9 days ago • 7.5k • 24

HINT-lab/sft_Qwen_Qwen3-0.6B

Viewer • Updated 9 days ago • 7.5k • 42

upvoted a paper 12 days ago

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

Paper • 2510.15444 • Published 16 days ago • 144

published 2 datasets 16 days ago

HINT-lab/sft_Qwen_Qwen3-1.7B

Viewer • Updated 9 days ago • 7.5k • 24

HINT-lab/sft_Qwen_Qwen3-0.6B

Viewer • Updated 9 days ago • 7.5k • 42

upvoted a paper 17 days ago

Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity

Paper • 2510.01171 • Published Oct 1 • 17

upvoted a paper 19 days ago

Demystifying Reinforcement Learning in Agentic Reasoning

Paper • 2510.11701 • Published 19 days ago • 31

updated a dataset 19 days ago

HINT-lab/sft_Qwen_Qwen3-0.6B-Base

Viewer • Updated 19 days ago • 7.5k • 18

upvoted 2 papers 20 days ago

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels

Paper • 2510.06499 • Published 25 days ago • 31

ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review

Paper • 2510.08867 • Published 23 days ago • 4

upvoted a paper 22 days ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published 23 days ago • 255

upvoted a paper 30 days ago

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

Paper • 2510.02283 • Published about 1 month ago • 91