10 papers
ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour
Jianhang Xie, Sicheng Tan, Vishnu Naresh Boddeti +1
Fully homomorphic encryption (FHE) provides strong cryptographic guarantees for private inference, but deploying transformer models under FHE remains prohibitively expensive. A key…
QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding
Wei Ao, Lan Wang, Vishnu Naresh Boddeti
The performance of vision-language models (VLMs) in video understanding declines with increasing video duration, as video moments unrelated to the query confuse their language comp…
Compositional Generative Modeling from Decentralized Data
Mashrur M. Morshed, Vishnu Naresh Boddeti
Learning the compositional nature of the physical world requires joint observation of interacting factors. However, because practical data is often decentralized, these factors are…
InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning
Gautam Sreekumar, Vishnu Naresh Boddeti
Large multimodal models (LMMs) encode physical laws observed during training, such as momentum conservation, as parametric knowledge. It allows LMMs to answer physical reasoning qu…
Rapid prediction of cardiac activation in the left ventricle with geometric deep learning: a step towards cardiac resynchronization therapy planning
Ehsan Naghavi, Haifeng Wang, Vahid Ziaei Rad +5
Cardiac resynchronization therapy (CRT) is a common intervention for patients with dyssynchronous heart failure, yet approximately one-third of recipients fail to respond, partly d…
Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift
Gautam Sreekumar, Vishnu Naresh Boddeti
We study the problem of learning robust discriminative representations of causally related latent variables given the underlying causal graph and a training set comprising passivel…