Gaowen Liu

Real-Time Robot Execution with Masked Action Chunking

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning

Dynamic Optimizations of LLM Ensembles with Two-Stage Reinforcement Learning Agents

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

RankFlow: Property-aware Transport for Protein Optimization

Robust Reward Sequence Modeling with Multi-Scale Consistency for Model-Based Reinforcement Learning

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance

Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners

A Neurosymbolic Agent System for Compositional Visual Reasoning

Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization

MGD$^3$ : Mode-Guided Dataset Distillation using Diffusion Models

Efficient Multimodal Dataset Distillation via Generative Models

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

A First-order Generative Bilevel Optimization Framework for Diffusion Models

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

UOE: Unlearning One Expert is Enough for Mixture-of-Experts LLMs

Prompt Diffusion Robustifies Any-Modality Prompt Learning

PokéLLMon: A Grounding and Reasoning Benchmark for Large Language Models in Pokémon Battles

MGD$^3$: Mode-Guided Dataset Distillation using Diffusion Models

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification

Robust Quantum Neural Networks Against Dynamic Noise Landscape in the NISQ Era