Bingzheng Wei

Bingzheng's activity

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

upvoted a paper about 22 hours ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 2 days ago • 460

upvoted 2 papers 1 day ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published 3 days ago • 126

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Paper • 2608.31106 • Published 3 days ago • 93

upvoted a paper 2 days ago

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Paper • 2608.29335 • Published 5 days ago • 60

upvoted 2 papers 3 days ago

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published 8 days ago • 269

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 8 days ago • 193

upvoted 2 papers 6 days ago

Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

Paper • 2608.26872 • Published 7 days ago • 79

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 7 days ago • 79

upvoted 2 papers 9 days ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published 10 days ago • 79

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published 10 days ago • 205

upvoted 3 papers 13 days ago

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

Paper • 2608.19799 • Published 14 days ago • 65

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

Paper • 2608.20335 • Published 14 days ago • 83

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 14 days ago • 274

upvoted 4 papers 14 days ago

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Paper • 2608.13558 • Published 21 days ago • 92

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

Paper • 2608.16590 • Published 17 days ago • 149

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

Paper • 2608.17310 • Published 16 days ago • 106

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

Paper • 2608.14036 • Published 20 days ago • 169

upvoted 3 papers 15 days ago

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

Paper • 2608.16157 • Published 17 days ago • 107

Abra: Scaling Diffusion Image Training

Paper • 2608.17286 • Published 16 days ago • 10

From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

Paper • 2608.16002 • Published 15 days ago • 7