Xin Li

lixin67's activity

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

upvoted 5 papers 4 days ago

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Paper • 2603.04257 • Published 8 days ago • 19

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

Paper • 2603.01236 • Published 11 days ago • 11

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published 9 days ago • 113

Phi-4-reasoning-vision-15B Technical Report

Paper • 2603.03975 • Published 8 days ago • 19

MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning

Paper • 2603.03379 • Published 10 days ago • 28

liked a dataset 7 days ago

inclusionAI/VenusBench-GD

Viewer • Updated Dec 20, 2025 • 1 • 2.25k • 10

upvoted a paper 15 days ago

Multi-agent cooperation through in-context co-player inference

Paper • 2602.16301 • Published 22 days ago • 24

upvoted 3 papers 16 days ago

REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

Paper • 2602.14234 • Published 25 days ago • 26

GLM-5: from Vibe Coding to Agentic Engineering

Paper • 2602.15763 • Published 23 days ago • 107

Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Paper • 2602.16855 • Published 26 days ago • 48

upvoted a collection 29 days ago

UI-Venus

Collection

12 items • Updated 6 days ago • 37

upvoted 9 papers 29 days ago

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

Paper • 2602.10560 • Published 30 days ago • 29

BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

Paper • 2602.09849 • Published about 1 month ago • 16

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

Paper • 2602.10090 • Published about 1 month ago • 51

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

Paper • 2602.10063 • Published about 1 month ago • 72

Code2World: A GUI World Model via Renderable Code Generation

Paper • 2602.09856 • Published about 1 month ago • 198

UI-Venus-1.5 Technical Report

Paper • 2602.09082 • Published Feb 9 • 155

OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration

Paper • 2602.05400 • Published Feb 5 • 347

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 29 days ago • 189

Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments

Paper • 2602.01244 • Published Feb 1 • 16