Haoxiang Zhang

IPF's activity

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

updated a dataset about 5 hours ago

i-DeepSearch/qwen35-cu13-on12

Viewer • Updated about 5 hours ago • 205

published a dataset about 6 hours ago

i-DeepSearch/qwen35-cu13-on12

Viewer • Updated about 5 hours ago • 205

updated a dataset about 6 hours ago

i-DeepSearch/observation-masking-eval-logs

Preview • Updated about 6 hours ago • 9.16k • 2

commented a paper 2 days ago

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

Paper • 2606.11709 • Published 18 days ago • 1 •

1

upvoted a paper 2 days ago

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

Paper • 2606.11709 • Published 18 days ago • 1

updated 2 models 3 days ago

Eubiota/eubiota-14b-step22

Updated 3 days ago • 17

Eubiota/eubiota-14b-step16

Updated 3 days ago • 17

published 2 models 3 days ago

Eubiota/eubiota-14b-step16

Updated 3 days ago • 17

Eubiota/eubiota-14b-step22

Updated 3 days ago • 17

updated a dataset 3 days ago

IPF/opsd-meta

Updated 3 days ago • 17

published a dataset 3 days ago

IPF/opsd-meta

Updated 3 days ago • 17

upvoted an article 6 days ago

view article

Article

GLM-5.2: Built for Long-Horizon Tasks

• 

zai-org

•

11 days ago

• 107

upvoted a paper 6 days ago

Learning from Language Feedback via Variational Policy Distillation

Paper • 2605.15113 • Published May 18 • 11

upvoted a paper 11 days ago

Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion

Paper • 2606.14885 • Published 16 days ago • 11

upvoted 2 papers 16 days ago

Latent Reasoning with Normalizing Flows

Paper • 2606.06447 • Published 24 days ago • 8

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Paper • 2606.04703 • Published 25 days ago • 25

upvoted a paper 18 days ago

Agents' Last Exam

Paper • 2606.05405 • Published 25 days ago • 366

upvoted a paper 19 days ago

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 97

upvoted a paper 22 days ago

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Paper • 2606.02404 • Published 27 days ago • 59

upvoted a paper 24 days ago

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Paper • 2510.04618 • Published Oct 6, 2025 • 134