2 citations · 6 across the 10 of their papers we have counts for
11 papers
Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need
Bhishma Dedhia, Yuval Kansal, Niraj K. Jha
Language models traditionally used for cross-domain generalization have recently demonstrated task-specific reasoning. However, their top-down training approach on general corpora…
Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
Bhishma Dedhia, David Bourgin, Krishna Kumar Singh +5
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationall…
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
Bhishma Dedhia, Niraj K. Jha
Several accounts of human cognition posit that our intelligence is rooted in our ability to form abstract composable concepts, ground them in our environment, and reason over these…
Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
Hongjie Wang, Bhishma Dedhia, Niraj K. Jha
Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of t…
Im-Promptu: In-Context Composition from Image Prompts
Bhishma Dedhia, Michael Chang, Jake C. Snell +2
Large language models are few-shot learners that can solve diverse tasks from a handful of demonstrations. This implicit understanding of tasks suggests that the attention mechanis…
SCouT: Synthetic Counterfactuals via Spatiotemporal Transformers for Actionable Healthcare
Bhishma Dedhia, Roshini Balasubramanian, Niraj K. Jha
The Synthetic Control method has pioneered a class of powerful data-driven techniques to estimate the counterfactual reality of a unit from donor units. At its core, the technique…
FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?
Shikhar Tuli, Bhishma Dedhia, Shreshth Tuli +1
The existence of a plethora of language models makes the problem of selecting the best one for a custom task challenging. Most state-of-the-art methods leverage transformer-based m…
Lower Bounds for Policy Iteration on Multi-action MDPs
Kumar Ashutosh, Sarthak Consul, Bhishma Dedhia +3
Policy Iteration (PI) is a classical family of algorithms to compute an optimal policy for any given Markov Decision Problem (MDP). The basic idea in PI is to begin with some initi…
On Minimizing Channel-Aware Age of Information in a Multi-Sensor Setting
Bhishma Dedhia, Sharayu Moharir
We propose a variant of the Age of Information (AoI) metric called Channel-Aware Age of Information (CA-AoI). Unlike AoI, CA-AoI takes into account the channel conditions between t…
Analysis of Lower Bounds for Simple Policy Iteration
Sarthak Consul, Bhishma Dedhia, Kumar Ashutosh +1
Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iter…
Saliency Prediction for Omnidirectional Images Considering Optimization on Sphere Domain
Bhishma Dedhia, Jui-Chiu Chiang, Yi-Fan Char
There are several formats to describe the omnidirectional images. Among them, equirectangular projection (ERP), represented as 2D image, is the most widely used format. There exist…