Bingxiang He

hbx's activity

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

upvoted a paper 4 days ago

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

Paper • 2608.14441 • Published 8 days ago • 26

upvoted a paper 5 days ago

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

Paper • 2608.14290 • Published 8 days ago • 31

upvoted 2 papers 9 days ago

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Paper • 2608.12307 • Published 10 days ago • 111

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Paper • 2608.10299 • Published 12 days ago • 132

upvoted a paper 21 days ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published 23 days ago • 184

upvoted a paper about 1 month ago

Weak-to-Strong Generalization via Direct On-Policy Distillation

Paper • 2607.05394 • Published Jul 8 • 147

upvoted 4 papers about 2 months ago

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 43

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Paper • 2606.24530 • Published Jun 23 • 66

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published Jun 23 • 159

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

Paper • 2606.23654 • Published Jun 22 • 80

upvoted a paper 2 months ago

Rethinking the Role of Efficient Attention in Hybrid Architectures

Paper • 2606.15378 • Published Jun 13 • 20

upvoted a collection 3 months ago

Rethinking OPD

Collection

This collection includes the models used in the paper "Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recip • 5 items • Updated Jun 3 • 4

upvoted 3 papers 3 months ago

Advancing Creative Physical Intelligence in Large Multimodal Models

Paper • 2605.26396 • Published May 25 • 21

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Paper • 2605.18643 • Published May 18 • 31

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Paper • 2605.13301 • Published May 13 • 166

upvoted 2 papers 4 months ago

CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing

Paper • 2605.02910 • Published May 6 • 23

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 115

upvoted a paper 5 months ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published Mar 9 • 59

upvoted a paper 6 months ago

P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads

Paper • 2602.09443 • Published Feb 10 • 59

upvoted a collection 8 months ago

JustRL

Collection

3 items • Updated May 2 • 5