Yuansheng Ni

yuanshengni's activity

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

upvoted a paper 8 days ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published 10 days ago • 255

upvoted a paper 10 days ago

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

Paper • 2604.05117 • Published 13 days ago • 35

upvoted a paper 11 days ago

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents

Paper • 2603.20691 • Published 29 days ago • 10

upvoted a paper 23 days ago

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

Paper • 2603.24440 • Published 24 days ago • 96

upvoted a collection 24 days ago

OpenResearcher

Collection

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated 25 days ago • 17

upvoted a paper 24 days ago

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

Paper • 2603.20278 • Published Mar 17 • 94

upvoted 2 papers about 2 months ago

VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction

Paper • 2602.13294 • Published Feb 9 • 13

InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

Paper • 2602.14367 • Published Feb 16 • 17

upvoted a paper 2 months ago

Context Forcing: Consistent Autoregressive Video Generation with Long Context

Paper • 2602.06028 • Published Feb 5 • 36

upvoted a paper 3 months ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper • 2601.05905 • Published Jan 9 • 20

upvoted 2 papers 5 months ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published Dec 1, 2025 • 74

InnoGym: Benchmarking the Innovation Potential of AI Agents

Paper • 2512.01822 • Published Dec 1, 2025 • 36

upvoted a paper 6 months ago

VisCoder2: Building Multi-Language Visualization Coding Agents

Paper • 2510.23642 • Published Oct 24, 2025 • 22

upvoted a collection 6 months ago

VisCoder2

Collection

Building Multi-Language Visualization Coding Agents • 7 items • Updated Oct 29, 2025 • 4

upvoted 5 papers 6 months ago

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published Oct 21, 2025 • 115

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

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

Paper • 2510.08540 • Published Oct 9, 2025 • 110

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 277

upvoted a paper 7 months ago

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

Paper • 2509.26346 • Published Sep 30, 2025 • 19