Lina Yao

Continuity-Regularized Flow Matching for Offline Reinforcement Learning

Adaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRA

Unifying Stable Optimization and Reference Regularization in RLHF

On the Geometry of Uncertainty: Equivariant Uncertainty Estimation for Molecular Vector Properties

Little By Little: Continual Learning via Self-Activated Sparse Mixture-of-Rank Adaptive Learning

Unifying Counterfactual Data Augmentation and Architectural Inductive Biases in Offline Reinforcement Learning

RegionDoc-R1: Reinforcing Semantic Layout-Aware Learning for Document Understanding

FERA: Uncertainty-aware Federated Reasoning for Large Language Models

MediBench: A Benchmark for VAEs in Medical Imaging Across Fidelity, Structure, and Latent Utility

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization

PiLoRA: Gradient-Informed Parameter-Importance-Aware Low-Rank Adaptation

Contextual Bandits with LLM-Derived Priors and Adaptive Calibration

Counterfactual Implicit Feedback Modeling

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models

Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Consistency Guaranteed Causal Graph Recovery with Large Language Models

CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models