Shihua Zhang

SuhZhang's activity

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

upvoted a paper 15 days ago

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper • 2610.34467 • Published 17 days ago • 39

upvoted a paper 21 days ago

LLM2R: From Large Language Models to 3D Reassemblers

Paper • 2610.18604 • Published 29 days ago • 25

upvoted a paper 23 days ago

PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design

Paper • 2610.20628 • Published Sep 29 • 9

upvoted 2 papers 26 days ago

Routing Policy Optimization for Online Diffusion Reinforcement Learning

Paper • 2610.22282 • Published 27 days ago • 28

Velox: Spatial Memory Makes World Models Efficient

Paper • 2610.22311 • Published 27 days ago • 22

upvoted a paper 28 days ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 29 days ago • 139

upvoted 3 papers about 1 month ago

CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments

Paper • 2609.38087 • Published Sep 29 • 16

Residual Transferability in Neural Image Watermarking

Paper • 2609.32241 • Published Sep 26 • 11

Structured Residual Connectivity Matters for Diffusion Transformers

Paper • 2609.33203 • Published Sep 27 • 16

upvoted 2 papers 2 months ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published Sep 9 • 100

H3-World: Turning Language Understanding into World Control

Paper • 2609.01560 • Published Sep 1 • 54

upvoted 2 papers 4 months ago

BadWAM: When World-Action Models Dream Right but Act Wrong

Paper • 2607.15207 • Published Jul 16 • 43

Orca: The World is in Your Mind

Paper • 2606.30534 • Published Jun 29 • 211

upvoted 5 papers 5 months ago

World Action Models: A Survey

Paper • 2606.20781 • Published Jun 18 • 59

You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences

Paper • 2606.15956 • Published Jun 14 • 12

Geometric Action Model for Robot Policy Learning

Paper • 2606.17046 • Published Jun 15 • 111

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 113

dMoE: dLLMs with Learnable Block Experts

Paper • 2605.30876 • Published May 29 • 33

upvoted 2 papers 6 months ago

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Paper • 2605.20315 • Published May 19 • 26

Make Geometry Matter for Spatial Reasoning

Paper • 2603.26639 • Published Mar 27 • 30