Wenjing Yang

OmniEarth-Bench: Probing Cognitive Abilities of MLLMs for Earth's Multi-sphere Observation Data

Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation

Beyond Rational Illusion: Behaviorally Realistic Strategic Classification

Lifelong Unlearning for Multimodal Large Language Models

Identifying Outcome-Oriented Root Causes via Cross Regression

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Environment Inference for Learning Generalizable Dynamical System

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Elastic Robust Unlearning of Specific Knowledge in Large Language Models

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models

Enhanced Semantic Alignment in Transformer Tracking via Position Learning and Force-Directed Attention

Leveraging VLMs for MUDA：A Category-Specific Prompting with Multi-Modal Low-Rank Adapter