Songcheng Cai

SongchengCai's activity

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

upvoted a paper about 12 hours ago

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

Paper • 2605.10434 • Published 1 day ago • 23

upvoted a paper 14 days ago

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

Paper • 2604.24763 • Published 16 days ago • 70

upvoted a paper 26 days ago

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

Paper • 2604.11626 • Published 30 days ago • 101

updated a dataset 29 days ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated 29 days ago • 260 • 156 • 5

authored a paper 29 days ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 262

upvoted 2 papers about 1 month ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 262

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

Paper • 2604.05117 • Published Apr 6 • 35

upvoted a paper about 2 months ago

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

Paper • 2603.20278 • Published Mar 17 • 96

liked a dataset about 2 months ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated 29 days ago • 260 • 156 • 5

published a dataset about 2 months ago

TIGER-Lab/SWE-QA-Pro-Bench

Viewer • Updated 29 days ago • 260 • 156 • 5

upvoted a paper 3 months ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published Feb 9 • 13

upvoted a paper 5 months ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published Dec 1, 2025 • 75

authored a paper 7 months ago

VisCoder2: Building Multi-Language Visualization Coding Agents

Paper • 2510.23642 • Published Oct 24, 2025 • 22

upvoted 5 papers 7 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 • 28

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

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Paper • 2510.08540 • Published Oct 9, 2025 • 110

upvoted 2 papers 8 months ago

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Paper • 2509.00676 • Published Aug 31, 2025 • 85

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Paper • 2509.01055 • Published Sep 1, 2025 • 81