Xing Han Lù

xhluca's activity

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

upvoted a paper 15 days ago

Grounding Computer Use Agents on Human Demonstrations

Paper • 2511.07332 • Published 16 days ago • 101

upvoted a paper about 1 month ago

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

Paper • 2510.03204 • Published Oct 3 • 6

upvoted a paper about 2 months ago

The Markovian Thinker

Paper • 2510.06557 • Published Oct 8 • 30

upvoted a paper 4 months ago

MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining

Paper • 2012.13978 • Published Dec 27, 2020 • 1

upvoted an article 5 months ago

view article

Article

How to Train Your LLM Web Agent: A Statistical Diagnosis

• 

Jul 8

•

14

upvoted 2 papers 5 months ago

How to Train Your LLM Web Agent: A Statistical Diagnosis

Paper • 2507.04103 • Published Jul 5 • 50

LineRetriever: Planning-Aware Observation Reduction for Web Agents

Paper • 2507.00210 • Published Jun 30 • 6

upvoted a paper 6 months ago

Build the web for agents, not agents for the web

Paper • 2506.10953 • Published Jun 12 • 21

upvoted an article 7 months ago

view article

Article

MIEB: The Benchmark That Stress-Tests Image-Text Embeddings Like Never Before

• 

Apr 24

•

14

upvoted 2 papers 8 months ago

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

Paper • 2504.08942 • Published Apr 11 • 28

DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning

Paper • 2504.07128 • Published Apr 2 • 86

upvoted 4 papers 9 months ago

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval

Paper • 2503.08644 • Published Mar 11 • 16

SafeArena: Evaluating the Safety of Autonomous Web Agents

Paper • 2503.04957 • Published Mar 6 • 21

Societal Alignment Frameworks Can Improve LLM Alignment

Paper • 2503.00069 • Published Feb 27 • 17

How to Get Your LLM to Generate Challenging Problems for Evaluation

Paper • 2502.14678 • Published Feb 20 • 18

upvoted a collection 9 months ago

CHASE

Collection

Generate challenging synthetic data to evaluate LLMs • 5 items • Updated Feb 21 • 4

upvoted a paper 9 months ago

MMTEB: Massive Multilingual Text Embedding Benchmark

Paper • 2502.13595 • Published Feb 19 • 42

upvoted an article 10 months ago

view article

Article

Train 400x faster Static Embedding Models with Sentence Transformers

• 

Jan 15

•

219

upvoted a paper 12 months ago

The BrowserGym Ecosystem for Web Agent Research

Paper • 2412.05467 • Published Dec 6, 2024 • 22

upvoted a paper about 1 year ago

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

Paper • 2410.01679 • Published Oct 2, 2024 • 27