Chenliang Xu

Training Large Reasoning Models Efficiently via Progressive Thought Encoding

Intentional-Gesture: Deliever your Thoughts by Gestures for Speech

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

DRIFT: Directional Reasoning Injection for Fine-Tuning MLLMs

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

ZeroSep: Separate Anything in Audio with Zero Training

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability

Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives

Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?

MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models

BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models

Forward Learning with Differential Privacy

Scaling Concept With Text-Guided Diffusion Models

Enhancing Adversarial Transferability Through Exploiting Multiple Randomized Trajectories for Better Global Guidance

Towards good practice in boosting the targeted adversarial attack

Is Forward Gradient an Effective Tool for Explaining Black-box Models?