Xin Liu

xinliuthu's activity

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

liked 2 datasets 1 day ago

supergoose/flan_combined_task1544_conll2002_named_entity_recognition_answer_generation

Viewer • Updated Mar 10, 2025 • 13.9k • 74 • 4

knowledgator/Scientific-text-classification

Viewer • Updated Feb 27, 2024 • 78.6k • 115 • 15

upvoted 3 papers 1 day ago

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Paper • 2609.00196 • Published 15 days ago • 36

Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers

Paper • 2608.18972 • Published 27 days ago • 14

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

Paper • 2510.08999 • Published 8 days ago • 20

upvoted 2 papers 3 days ago

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

Paper • 2609.06245 • Published 10 days ago • 34

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

Paper • 2609.08183 • Published 7 days ago • 414

upvoted a paper 4 days ago

FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience

Paper • 2609.03241 • Published 12 days ago • 97

upvoted 2 papers 5 days ago

Unifying Conformal Language Tasks with In-Context Ensembles

Paper • 2609.03005 • Published 13 days ago • 10

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 12 days ago • 148

upvoted a paper 6 days ago

Environment Evolution for Terminal Agents

Paper • 2609.04128 • Published 12 days ago • 22

upvoted 5 papers 8 days ago

Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

Paper • 2608.21450 • Published 27 days ago • 29

ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval

Paper • 2609.01865 • Published 14 days ago • 8

Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

Paper • 2608.28478 • Published 18 days ago • 20

Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation

Paper • 2608.30396 • Published 15 days ago • 12

UI-Venus-2 Technical Report

Paper • 2609.00028 • Published 19 days ago • 65

upvoted a paper 10 days ago

DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory

Paper • 2609.00768 • Published 14 days ago • 23

upvoted 3 papers 11 days ago

EM^2Mem: Event-Centric Multimodal Memory for Large Language Models

Paper • 2609.00551 • Published 14 days ago • 14

Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering

Paper • 2608.30468 • Published 15 days ago • 38

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published 15 days ago • 384