Haoxiang Zhang

IPF's activity

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

upvoted a paper 1 day ago

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling

Paper • 2605.08083 • Published 4 days ago • 57

upvoted a collection 1 day ago

Qwen3.6

Collection

4 items • Updated 20 days ago • 331

upvoted a paper 1 day ago

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published Mar 29 • 146

upvoted 6 papers 3 days ago

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Paper • 2604.10098 • Published Apr 11 • 80

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published 27 days ago • 157

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 14 days ago • 264

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents

Paper • 2605.05185 • Published 6 days ago • 95

A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

Paper • 2605.06200 • Published 5 days ago • 13

From Context to Skills: Can Language Models Learn from Context Skillfully?

Paper • 2604.27660 • Published 9 days ago • 152

upvoted a paper 4 days ago

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Paper • 2605.05242 • Published 9 days ago • 91

upvoted a paper 5 days ago

AgentIR: Reasoning-Aware Retrieval for Deep Research Agents

Paper • 2603.04384 • Published Mar 4 • 4

upvoted an article 23 days ago

view article

Article

Qwen3.5: Nobody Agrees on Attention Anymore

• 

mlabonne

•

Feb 17

• 24

upvoted a paper 28 days ago

CocoaBench: Evaluating Unified Digital Agents in the Wild

Paper • 2604.11201 • Published 29 days ago • 36

upvoted 4 papers about 1 month ago

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published Apr 9 • 262

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published Apr 9 • 289

OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

Paper • 2502.11271 • Published Feb 16, 2025 • 19

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published Apr 8 • 71

upvoted an article about 1 month ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 890

upvoted a paper about 1 month ago

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Paper • 2503.09516 • Published Mar 12, 2025 • 40

upvoted a collection about 1 month ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.62k