Shihua Zhang

SuhZhang's activity

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

upvoted a paper 4 days ago

CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments

Paper • 2609.38087 • Published 6 days ago • 24

upvoted 2 papers 5 days ago

Residual Transferability in Neural Image Watermarking

Paper • 2609.32241 • Published 9 days ago • 13

Structured Residual Connectivity Matters for Diffusion Transformers

Paper • 2609.33203 • Published 8 days ago • 17

upvoted a paper 24 days ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published 26 days ago • 162

upvoted a paper about 1 month ago

H3-World: Turning Language Understanding into World Control

Paper • 2609.01560 • Published Sep 1 • 53

upvoted 3 papers 3 months ago

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

Paper • 2607.15207 • Published Jul 16 • 45

Orca: The World is in Your Mind

Paper • 2606.30534 • Published Jun 29 • 512

World Action Models: A Survey

Paper • 2606.20781 • Published Jun 18 • 59

upvoted 4 papers 4 months ago

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

Paper • 2606.15956 • Published Jun 14 • 13

Geometric Action Model for Robot Policy Learning

Paper • 2606.17046 • Published Jun 15 • 118

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 115

dMoE: dLLMs with Learnable Block Experts

Paper • 2605.30876 • Published May 29 • 33

upvoted 6 papers 5 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

ViMU: Benchmarking Video Metaphorical Understanding

Paper • 2605.14607 • Published May 14 • 12

On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment

Paper • 2605.11882 • Published May 12 • 15

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Paper • 2604.28185 • Published Apr 30 • 90

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

Paper • 2604.23775 • Published Apr 26 • 45

upvoted 2 papers 6 months ago

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published Apr 9 • 53

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers

Paper • 2603.27666 • Published Mar 29 • 16