Songcheng Cai

SongchengCai's activity

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

New activity in TIGER-Lab/SWE-QA-Pro-SFT-Trajectories about 14 hours ago

[bot] Conversion to Parquet

#1 opened about 15 hours ago by

parquet-converter

updated a dataset 1 day ago

TIGER-Lab/SWE-QA-Pro-SFT-Trajectories

Viewer • Updated 1 day ago • 1k • 17

published a dataset 1 day ago

TIGER-Lab/SWE-QA-Pro-SFT-Trajectories

Viewer • Updated 1 day ago • 1k • 17

updated a dataset about 1 month ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated May 19 • 260 • 104 • 5

upvoted a paper about 1 month ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published May 11 • 29

upvoted a paper about 2 months ago

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Paper • 2604.24763 • Published Apr 27 • 71

upvoted a paper 2 months ago

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Paper • 2604.11626 • Published Apr 13 • 103

authored a paper 2 months ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 265

upvoted 3 papers 3 months ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 265

Watch Before You Answer: Learning from Visually Grounded Post-Training

Paper • 2604.05117 • Published Apr 6 • 36

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published Mar 17 • 101

liked a dataset 3 months ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated May 19 • 260 • 104 • 5

published a dataset 3 months ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated May 19 • 260 • 104 • 5

upvoted a paper 4 months ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published Feb 9 • 13

upvoted a paper 7 months ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published Dec 1, 2025 • 78

authored a paper 8 months ago

VisCoder2: Building Multi-Language Visualization Coding Agents

Paper • 2510.23642 • Published Oct 24, 2025 • 22

upvoted 2 papers 8 months ago

VisCoder2: Building Multi-Language Visualization Coding Agents

Paper • 2510.23642 • Published Oct 24, 2025 • 22

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions

Paper • 2510.10666 • Published Oct 12, 2025 • 29

upvoted 2 papers 9 months ago

UniVideo: Unified Understanding, Generation, and Editing for Videos

Paper • 2510.08377 • Published Oct 9, 2025 • 81

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 276