Sandeep P. Chinchali

We'll Fix it in Post: Improving Text-to-Video Generation with Zero Training

MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation

DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing

MuSED-FM: A Benchmark for Evaluating Multivariate Time Series Foundation Models

VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features

A Framework for Finding Local Saddle Points in Two-Player Zero-Sum Black-Box Games

Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval

Context Matters: Leveraging Contextual Features for Time Series Forecasting