Chengsong Huang

ChengsongHuang's activity

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

upvoted 2 papers 2 days ago

HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences

Paper • 2601.18724 • Published 4 days ago • 7

A Pragmatic VLA Foundation Model

Paper • 2601.18692 • Published 4 days ago • 41

upvoted a paper 9 days ago

Agentic Reasoning for Large Language Models

Paper • 2601.12538 • Published 12 days ago • 183

upvoted a paper 10 days ago

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge

Paper • 2601.08808 • Published 17 days ago • 38

upvoted 2 papers 11 days ago

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published 15 days ago • 39

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 17 days ago • 146

upvoted a paper 14 days ago

Alterbute: Editing Intrinsic Attributes of Objects in Images

Paper • 2601.10714 • Published 15 days ago • 30

upvoted a paper 15 days ago

Controlled Self-Evolution for Algorithmic Code Optimization

Paper • 2601.07348 • Published 18 days ago • 113

upvoted 3 papers 17 days ago

Dr. Zero: Self-Evolving Search Agents without Training Data

Paper • 2601.07055 • Published 19 days ago • 20

BabyVision: Visual Reasoning Beyond Language

Paper • 2601.06521 • Published 20 days ago • 192

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published 19 days ago • 208

upvoted 2 papers 18 days ago

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

Paper • 2601.06002 • Published 21 days ago • 51

Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

Paper • 2601.05432 • Published 22 days ago • 164

upvoted a paper 21 days ago

Token-Level LLM Collaboration via FusionRoute

Paper • 2601.05106 • Published 22 days ago • 39

upvoted 2 papers 22 days ago

RelayLLM: Efficient Reasoning via Collaborative Decoding

Paper • 2601.05167 • Published 22 days ago • 29

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Paper • 2601.03986 • Published 23 days ago • 34

upvoted a paper 23 days ago

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

Paper • 2601.03193 • Published 24 days ago • 46

upvoted a paper 24 days ago

Recursive Language Models

Paper • 2512.24601 • Published about 1 month ago • 78

upvoted 2 papers 25 days ago

Diversity or Precision? A Deep Dive into Next Token Prediction

Paper • 2512.22955 • Published Dec 28, 2025 • 8

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

Paper • 2512.24615 • Published about 1 month ago • 119