Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper 4 days ago

Inverse Scaling in Test-Time Compute

Paper • 2507.14417 • Published 13 days ago • 25

upvoted a paper 7 days ago

Yume: An Interactive World Generation Model

Paper • 2507.17744 • Published 8 days ago • 77

upvoted a paper 14 days ago

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment

Paper • 2505.11821 • Published May 17 • 14

upvoted a paper 17 days ago

One Token to Fool LLM-as-a-Judge

Paper • 2507.08794 • Published 20 days ago • 31

upvoted a paper 20 days ago

Scaling RL to Long Videos

Paper • 2507.07966 • Published 21 days ago • 151

upvoted a paper 21 days ago

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving

Paper • 2507.06804 • Published 24 days ago • 15

upvoted a paper 30 days ago

Scaling Speculative Decoding with Lookahead Reasoning

Paper • 2506.19830 • Published Jun 24 • 12

upvoted a collection about 1 month ago

Self-Calibration

Collection

Efficient Test-Time Scaling via Self-Calibration https://arxiv.org/abs/2503.00031 • 7 items • Updated Jun 8 • 2

upvoted 2 papers about 1 month ago

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Paper • 2506.16406 • Published Jun 19 • 123

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Paper • 2506.09033 • Published Jun 10 • 7

upvoted 4 papers about 2 months ago

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models

Paper • 2506.06395 • Published Jun 5 • 128

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

Paper • 2505.15778 • Published May 21 • 17

POSS: Position Specialist Generates Better Draft for Speculative Decoding

Paper • 2506.03566 • Published Jun 4 • 6

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Paper • 2505.21497 • Published May 27 • 106

upvoted a paper 2 months ago

WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

Paper • 2505.16421 • Published May 22 • 19

upvoted a paper 3 months ago

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Paper • 2504.13828 • Published Apr 18 • 17

upvoted 4 papers 4 months ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 280

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Paper • 2504.01990 • Published Mar 31 • 300

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

Paper • 2504.07096 • Published Apr 9 • 75

Optimizing Language Model's Reasoning Abilities with Weak Supervision

Paper • 2405.04086 • Published May 7, 2024 • 2