Songcheng Cai

SongchengCai's activity

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

upvoted a paper 4 days ago

ReproBridge: Building Reproducibility into ML Research Artifacts

Paper • 2611.08452 • Published 9 days ago • 33

upvoted a paper 18 days ago

ReGE: Stronger Agents through Experience Synthesis

Paper • 2610.33861 • Published 22 days ago • 14

upvoted a paper 23 days ago

StopLoss: Teaching Agents to Predict Failure and Stop Early

Paper • 2610.25525 • Published 28 days ago • 16

upvoted 2 papers 24 days ago

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published Oct 14 • 72

PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews

Paper • 2610.21046 • Published about 1 month ago • 22

upvoted 2 papers about 1 month ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published Oct 1 • 18

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published Sep 29 • 29

upvoted a paper 3 months ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published Aug 26 • 54

upvoted a paper 4 months ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Paper • 2607.12463 • Published Jul 14 • 42

upvoted a paper 6 months ago

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

Paper • 2605.10434 • Published May 11 • 31

upvoted 4 papers 7 months ago

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

Paper • 2604.24763 • Published Apr 27 • 71

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

Paper • 2604.11626 • Published Apr 13 • 24

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 118

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

Paper • 2604.05117 • Published Apr 6 • 33

upvoted a paper 8 months ago

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

Paper • 2603.20278 • Published Mar 17 • 103

upvoted a paper 9 months ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published Feb 9 • 13

upvoted a paper 12 months ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published Dec 1, 2025 • 73

upvoted 3 papers about 1 year 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

UniVideo: Unified Understanding, Generation, and Editing for Videos

Paper • 2510.08377 • Published Oct 9, 2025 • 81