Xin Liu

xinliuthu's activity

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

upvoted 2 papers 6 days ago

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published 14 days ago • 12

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

Paper • 2610.12341 • Published 13 days ago • 48

upvoted a paper 9 days ago

UniWAM: Unified World-Action Model

Paper • 2610.02054 • Published 20 days ago • 83

upvoted 3 papers 10 days ago

Beyond the Current Scene: Event-Referential Grasping with Active View Selection

Paper • 2609.39375 • Published 21 days ago • 55

Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability Alignment

Paper • 2609.38972 • Published 21 days ago • 30

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding

Paper • 2610.07342 • Published 16 days ago • 21

upvoted 2 papers 13 days ago

Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers

Paper • 2608.26762 • Published 25 days ago • 24

PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEs

Paper • 2609.34715 • Published 23 days ago • 65

upvoted a paper 14 days ago

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published 20 days ago • 92

upvoted 2 papers 15 days ago

SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

Paper • 2609.33616 • Published 24 days ago • 27

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Paper • 2609.38155 • Published 22 days ago • 116

upvoted 3 papers 17 days ago

When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections

Paper • 2609.32488 • Published 25 days ago • 27

Knowledge Pull Requests for Continual Document Authoring

Paper • 2609.26634 • Published 29 days ago • 13

APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants

Paper • 2609.37559 • Published 22 days ago • 47

upvoted a paper 18 days ago

ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces

Paper • 2609.33326 • Published 24 days ago • 37

upvoted a paper 20 days ago

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

Paper • 2601.06362 • Published about 1 month ago • 10

upvoted a paper 22 days ago

Training Object Permanence in World Models

Paper • 2609.28654 • Published 28 days ago • 169

upvoted a paper 23 days ago

Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?

Paper • 2609.27891 • Published Aug 21 • 33

upvoted a paper 24 days ago

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published 29 days ago • 165

upvoted a paper 26 days ago

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Paper • 2609.13814 • Published Sep 12 • 191