Xin Liu

xinliu97's activity

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

upvoted a paper 4 days ago

D-JEPA: A Decision-Aligned Latent World Model

Paper • 2609.24749 • Published 13 days ago • 17

upvoted a paper 7 days ago

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Paper • 2609.24058 • Published 14 days ago • 55

upvoted a paper 8 days ago

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

Paper • 2609.25804 • Published 13 days ago • 162

upvoted a paper 9 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 495

upvoted a paper 10 days ago

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Paper • 2609.24220 • Published 14 days ago • 68

upvoted a paper 11 days ago

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 17 days ago • 150

upvoted a paper 12 days ago

Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation

Paper • 2609.20744 • Published 18 days ago • 53

upvoted 2 papers 13 days ago

In-Context Robot Learning with VLM Agents

Paper • 2609.19138 • Published 19 days ago • 29

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

Paper • 2609.17488 • Published 20 days ago • 815

upvoted a paper 16 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 28 days ago • 376

upvoted a paper 18 days ago

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published about 1 month ago • 117

upvoted a paper 20 days ago

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

Paper • 2609.09134 • Published 27 days ago • 11

upvoted 3 papers 22 days ago

One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation

Paper • 2608.25936 • Published Aug 26 • 16

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published Sep 2 • 31

Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout

Paper • 2609.09123 • Published 27 days ago • 55

upvoted 3 papers 23 days ago

CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements

Paper • 2609.07498 • Published 28 days ago • 34

SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution

Paper • 2609.05594 • Published about 1 month ago • 36

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 27 days ago • 327