Russ Salakhutdinov

Training a Generally Curious Agent

Dissecting Adversarial Robustness of Multimodal LM Agents

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Wayward Concepts In Multimodal Models

Video Active Perception: Efficient Inference-Time Long-Form Video Understanding with Vision-Language Models

Tree Search for Language Model Agents

Evaluating Deep Unlearning in Large Language Models

Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation

State Combinatorial Generalization In Decision Making With Conditional Diffusion Models

Stylus: Automatic Adapter Selection for Diffusion Models

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference

Distributional Distance Classifiers for Goal-Conditioned Reinforcement Learning

MultiIoT: Towards Large-scale Multisensory Learning for the Internet of Things