Chao Shen

DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning

ProMoS: Prototype-Guided Distillation for Generalist Graph Anomaly Detection

SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA

Domain-Specialized Tree of Thought through Plug-and-Play Predictors

Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations

MCP-Radar: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models

Enhancing Query-Free Jailbreaks on Text-to-Image Models with Bimodal Guidance

Prediction Inconsistency Helps Generalizable Detection of Adversarial Examples

STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning