Xiangnan Wu

XiangnanW's activity

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

upvoted a paper 7 days ago

Turns Matter: Advancing Streaming Video RL via Turn-Level Credit

Paper • 2611.06728 • Published 9 days ago • 70

upvoted a paper 9 days ago

Wave Forcing: Towards Speed-of-Light Streaming Video Generation

Paper • 2611.00859 • Published 13 days ago • 129

upvoted a paper 16 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 18 days ago • 116

upvoted a paper 21 days ago

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds

Paper • 2610.28698 • Published 24 days ago • 73

upvoted a paper 23 days ago

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

Paper • 2610.26770 • Published 25 days ago • 33

upvoted a paper 29 days ago

Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability

Paper • 2610.14158 • Published Oct 9 • 12

upvoted 3 papers 3 months ago

EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking

Paper • 2608.20886 • Published Aug 21 • 11

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published Aug 3 • 52

LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger

Paper • 2607.28374 • Published Jul 30 • 13

upvoted 3 papers 4 months ago

HumanCLAW: Can Vision-Language Models Act Through a Body?

Paper • 2607.27180 • Published Jul 29 • 73

PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation

Paper • 2606.26916 • Published Jun 25 • 4

Multi-Block Diffusion Language Models

Paper • 2606.29215 • Published Jun 30 • 41

upvoted a paper 6 months ago

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

Paper • 2605.26115 • Published May 25 • 55

upvoted a paper 7 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 120

upvoted an article 8 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 183

upvoted a paper 10 months ago

ToolACE-MCP: Generalizing History-Aware Routing from MCP Tools to the Agent Web

Paper • 2601.08276 • Published Jan 13 • 7

upvoted a paper 11 months ago

DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

Paper • 2512.04324 • Published Dec 3, 2025 • 160

upvoted a paper over 1 year ago

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Paper • 2506.07961 • Published Jun 9, 2025 • 12