Chengsong Huang

ChengsongHuang's activity

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

upvoted a paper about 9 hours ago

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Paper • 2601.03986 • Published about 22 hours ago • 26

upvoted a paper about 11 hours ago

UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision

Paper • 2601.03193 • Published 2 days ago • 36

upvoted a paper 2 days ago

Recursive Language Models

Paper • 2512.24601 • Published 8 days ago • 35

upvoted 2 papers 3 days ago

Diversity or Precision? A Deep Dive into Next Token Prediction

Paper • 2512.22955 • Published 11 days ago • 6

Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization

Paper • 2512.24615 • Published 8 days ago • 102

upvoted a paper 14 days ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 21 days ago • 92

upvoted 4 papers 15 days ago

Reinforcement Learning for Self-Improving Agent with Skill Library

Paper • 2512.17102 • Published 21 days ago • 32

MemEvolve: Meta-Evolution of Agent Memory Systems

Paper • 2512.18746 • Published 18 days ago • 28

Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies

Paper • 2512.19673 • Published 17 days ago • 61

SAM Audio: Segment Anything in Audio

Paper • 2512.18099 • Published 20 days ago • 21

upvoted 2 papers 16 days ago

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

Paper • 2512.18880 • Published 18 days ago • 24

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published 21 days ago • 203

upvoted 5 papers 17 days ago

Animate Any Character in Any World

Paper • 2512.17796 • Published 21 days ago • 10

SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories

Paper • 2512.17419 • Published 20 days ago • 9

Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

Paper • 2512.17260 • Published 20 days ago • 48

When Reasoning Meets Its Laws

Paper • 2512.17901 • Published 20 days ago • 56

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Paper • 2512.17012 • Published 21 days ago • 42

upvoted 2 papers 21 days ago

Fast and Accurate Causal Parallel Decoding using Jacobi Forcing

Paper • 2512.14681 • Published 23 days ago • 39

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

Paper • 2512.15687 • Published 22 days ago • 18

upvoted a paper 22 days ago

Olmo 3

Paper • 2512.13961 • Published 24 days ago • 22