Xin Li

lixin67's activity

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

upvoted a paper 12 days ago

Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception

Paper • 2610.37037 • Published 15 days ago • 30

upvoted a paper 17 days ago

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Paper • 2609.33304 • Published Sep 27 • 11

upvoted a paper 19 days ago

Focused Omni-Modal GUI Agents

Paper • 2610.26203 • Published 23 days ago • 32

upvoted a paper 22 days ago

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 27 days ago • 28

upvoted 3 papers 23 days ago

Data World: Scaling Data Environments from Scratch

Paper • 2610.21656 • Published 27 days ago • 38

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

Paper • 2610.20939 • Published 28 days ago • 43

OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use

Paper • 2610.22200 • Published 27 days ago • 71

upvoted 3 papers 26 days ago

Cortex: Consolidating Context into Parametric Memory

Paper • 2610.20399 • Published 28 days ago • 69

Long-Horizon RL Needs Muon

Paper • 2610.20256 • Published 28 days ago • 11

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published Aug 19 • 48

upvoted 4 papers 27 days ago

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

Paper • 2610.07987 • Published Oct 6 • 58

ClawLoop: Self-Improving Agents via Harness-Native Training Loop

Paper • 2610.14118 • Published Oct 9 • 27

DoSA: Dots Sparse Attention

Paper • 2610.13990 • Published Sep 26 • 67

VideoJev: System One Model for Video Understanding and Interaction

Paper • 2610.18615 • Published 29 days ago • 85

upvoted 5 papers about 1 month ago

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

Paper • 2610.11366 • Published Oct 8 • 12

TokenRouter: Efficient Serving System for Token-Level LLM Routing

Paper • 2610.12242 • Published Oct 8 • 119

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Paper • 2610.11959 • Published Oct 8 • 82

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Paper • 2610.07767 • Published Oct 6 • 44

SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting

Paper • 2610.04109 • Published Oct 2 • 21

upvoted a paper about 2 months ago

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published Sep 18 • 73