systematic investigation

6 papers

• BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
• Diversity-Aware Policy Optimization for Large Language Model Reasoning
• Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
• Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
• The Curse of Multi-Modalities: Evaluating Hallucinations of Large Multimodal Models across Language, Visual, and Audio
• Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference