Wei Liu

GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning

SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks

Empowering Channel-of-Mobile-Experts with Informative Hybrid-Capabilities Reasoning

FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation

MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs

MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning

Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties

Evidence-R1: Fine-Grained Evidence-Driven Explicit Reasoning and Implicit Reflection for Enhancing RAG Explainability via Reinforcement Learning

Meta-Researcher: Empowering Planning and Reflection Mechanisms in Large Reasoning Models for Advanced Deep Research Abilities

GUI-PRA: Process Reward Agent for GUI Tasks

Arithmetic-Bench: Evaluating Multi-Step Reasoning in LLMs with Basic Arithmetic

Prompt-Guided Distillation from Multimodal Large Language Models to Task-specific Models for Multimodal Sentiment Analysis