Haoxiang Zhang

IPF's activity

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

upvoted a paper 2 days ago

TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

Paper • 2610.17540 • Published 21 days ago • 4

upvoted 2 papers 4 days ago

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

Paper • 2606.30406 • Published Jun 29 • 30

Memory Tax: Dissecting the Net Value of Agent Memory

Paper • 2610.34073 • Published 9 days ago • 30

upvoted a paper 6 days ago

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

Paper • 2610.32285 • Published 11 days ago • 54

upvoted 2 papers 12 days ago

REMORY: Learning Residual Memory for Context Compaction

Paper • 2610.11287 • Published 26 days ago • 55

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Paper • 2609.04280 • Published Sep 3 • 30

upvoted 3 papers 14 days ago

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

Paper • 2610.26860 • Published 15 days ago • 113

Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight

Paper • 2610.08077 • Published 28 days ago • 172

BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business

Paper • 2610.20424 • Published 20 days ago • 239

upvoted 3 papers 15 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 19 days ago • 165

Learning to Think and Explore in 3D World

Paper • 2610.21783 • Published 19 days ago • 71

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

Paper • 2610.18784 • Published 20 days ago • 123

upvoted 2 papers 16 days ago

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published Sep 17 • 32

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 19 days ago • 50

upvoted 3 papers 17 days ago

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published Jul 31 • 98

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 21 days ago • 65

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Paper • 2610.22200 • Published 19 days ago • 78

upvoted 3 papers 18 days ago

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

Paper • 2610.21412 • Published 19 days ago • 25

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published 21 days ago • 64

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 21 days ago • 166