Xin Liu

xinliuthu's activity

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

upvoted a paper about 23 hours 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 11 days ago • 10

upvoted a paper 2 days ago

Training Object Permanence in World Models

Paper • 2609.28654 • Published 8 days ago • 238

upvoted a paper 3 days ago

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

Paper • 2609.27891 • Published Aug 21 • 31

upvoted a paper 4 days ago

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

Paper • 2609.25804 • Published 9 days ago • 160

upvoted 2 papers 6 days ago

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

Paper • 2609.13814 • Published 19 days ago • 224

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Paper • 2609.13231 • Published 29 days ago • 18

upvoted a paper 7 days ago

EvoOntology: A Self-Evolving Ontology Layer for Data Agents

Paper • 2609.15779 • Published 17 days ago • 159

upvoted a paper 8 days ago

VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering

Paper • 2609.19879 • Published 14 days ago • 33

upvoted a paper 9 days ago

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published 16 days ago • 812

upvoted a paper 10 days ago

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

Paper • 2609.17523 • Published 16 days ago • 31

upvoted 3 papers 11 days ago

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

Paper • 2609.10355 • Published 22 days ago • 18

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

Paper • 2609.15478 • Published 17 days ago • 34

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 24 days ago • 376

upvoted a paper 12 days ago

StepAudio 3 Realtime Technical Report

Paper • 2609.14005 • Published 19 days ago • 129

upvoted a paper 13 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 16 days ago • 146

upvoted 2 papers 14 days ago

ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs

Paper • 2609.10895 • Published 22 days ago • 54

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published 23 days ago • 136

upvoted 2 papers 15 days ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published 24 days ago • 147

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

Paper • 2609.09143 • Published 23 days ago • 29

upvoted a paper 18 days ago

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Paper • 2609.00196 • Published Aug 31 • 37