Weili Guan

Boost Post-Training Quantization via Null Space Optimization for Large Language Models

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting

CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization

From Bias to Balance: Exploring and Mitigating Spatial Bias in LVLMs

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data

Unified Transferability Metrics for Time Series Foundation Models

Embodied Crowd Counting

Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator

Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation

Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin

MeMAD: Structured Memory of Debates for Enhanced Multi-Agent Reasoning

HYBRID MODEL COLLABORATION FOR SIGN LANGUAGE TRANSLATION WITH VQ-VAE AND RAG ENHANCED LLMS

Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing

Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding