QIngwei Lin
- Papers
- 21
Cite
Notes
Only stored in your browser.
Authored papers
21Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
arXiv 2026
UFO2: The Desktop AgentOS
arXiv 2025
SWE-bench Goes Live!
arXiv 2025
VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model
arXiv 2025
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
arXiv 2025
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
arXiv 2025
Text2Grad: Reinforcement Learning from Natural Language Feedback
arXiv 2025
UFO^3: Weaving the Digital Agent Galaxy
arXiv 2025
UFO: A UI-Focused Agent for Windows OS Interaction
arXiv 2024
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
arXiv 2024
Large Action Models: From Inception to Implementation
arXiv 2024
Large Language Model-Brained GUI Agents: A Survey
arXiv 2024
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
arXiv 2024
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
arXiv 2024
EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
arXiv 2024
TaskWeaver: A Code-First Agent Framework
arXiv 2023
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
arXiv 2023
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
arXiv 2023
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
arXiv 2023
Conservative State Value Estimation for Offline Reinforcement Learning
conservative-state-value-estimation-for
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
arXiv 2022
Affiliations
Frequent co-authors
10from 21 papers