Bingzheng Wei

Bingzheng's activity

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

upvoted 2 papers about 4 hours ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 1 day ago • 55

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 1 day ago • 148

upvoted 3 papers 4 days ago

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

Paper • 2608.19799 • Published 5 days ago • 61

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Paper • 2608.20335 • Published 5 days ago • 75

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 5 days ago • 259

upvoted 4 papers 5 days ago

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Paper • 2608.13558 • Published 12 days ago • 91

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published 8 days ago • 145

Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements

Paper • 2608.17310 • Published 7 days ago • 104

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 11 days ago • 163

upvoted 5 papers 6 days ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 8 days ago • 93

Abra: Scaling Diffusion Image Training

Paper • 2608.17286 • Published 7 days ago • 10

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Paper • 2608.16002 • Published 6 days ago • 7

AVA-Encoder: Towards Agent-Native Video Representation Learning

Paper • 2608.12313 • Published 13 days ago • 41

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published 10 days ago • 438

upvoted 6 papers 7 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 8 days ago • 123

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

Paper • 2608.15265 • Published 10 days ago • 59

Agentic Transaction: Towards ACID-Compliant Agent Systems

Paper • 2608.13900 • Published 11 days ago • 27

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 11 days ago • 169

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 12 days ago • 55

Intern-S2-Preview: Scientific Agentic Foundation Model

Paper • 2608.13505 • Published 12 days ago • 70