Junhao Shen

shenjunhao's activity

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

upvoted a paper 5 days ago

Work Agents: Systems, Capabilities, and Optimization

Paper • 2610.35845 • Published 6 days ago • 120

upvoted a paper 6 days ago

HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games

Paper • 2610.31162 • Published 10 days ago • 61

upvoted a paper 8 days ago

What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models

Paper • 2610.23987 • Published 18 days ago • 46

upvoted 2 papers 10 days ago

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

Paper • 2610.28698 • Published 12 days ago • 86

Training the Whole Agent, Not Just the Model

Paper • 2610.28069 • Published 12 days ago • 20

upvoted a paper 11 days ago

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

Paper • 2610.26770 • Published 13 days ago • 34

upvoted a paper 13 days ago

Execution Before Memory: Diagnosing Memory Failures in Video World Models

Paper • 2610.23542 • Published 16 days ago • 35

upvoted a paper 16 days ago

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

Paper • 2610.21095 • Published 17 days ago • 36

upvoted a paper 23 days ago

Learning Multimodal Embeddings with Evidence-Aligned Readout

Paper • 2609.33659 • Published Sep 27 • 12

upvoted 3 papers about 2 months ago

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published Sep 8 • 120

Omni-Streaming Thinking

Paper • 2609.15128 • Published Sep 14 • 22

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published Sep 10 • 167

upvoted a collection about 2 months ago

SenseNova-U1.5

Collection

5 items • Updated Sep 11 • 41

upvoted a paper about 2 months ago

Omni Interaction Agent Technical Report

Paper • 2609.08977 • Published Sep 8 • 88

upvoted 6 papers 2 months ago

GameWAM: A World Action Model for Video Games

Paper • 2608.26200 • Published Aug 25 • 37

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published Aug 27 • 75

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published Aug 20 • 34

EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking

Paper • 2608.20886 • Published Aug 21 • 11

ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models

Paper • 2608.14022 • Published Aug 14 • 24

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

Paper • 2608.14441 • Published Aug 14 • 29