Somnath Basu Roy Chowdhury

Inference-time Unlearning Using Conformal Prediction

Somnath Basu Roy Chowdhury, Rahul Kidambi, Avinava Dubey, David Wang et autres

Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve retraining a subset of model parameters based on a forget set. While …

Inference-time Unlearning Using Conformal Prediction

Somnath Basu Roy Chowdhury, Rahul Kidambi, Avinava Dubey, David Wang et autres

Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve retraining a subset of model parameters based on a forget set. While …

us (code pays fourni par la source)

EUGens: Efficient, Unified, and General Dense Layers

Sang Min Kim, Byeongchan Kim, Arijit Sehanobish, Somnath Basu Roy Chowdhury et autres

Efficient neural networks are essential for scaling machine learning models to real-time applications and resource-constrained environments. Fully-connected feedforward layers (FFLs) introduce computation and parameter count bottlenecks within neural network architectures. To address this challenge, in this work, we propose a new class …

EUGens: Efficient, Unified, and General Dense Layers

Sang Min Kim, Byeongchan Kim, Arijit Sehanobish, Somnath Basu Roy Chowdhury et autres

Efficient neural networks are essential for scaling machine learning models to real-time applications and resource-constrained environments. Fully-connected feedforward layers (FFLs) introduce computation and parameter count bottlenecks within neural network architectures. To address this challenge, in this work, we propose a new class …

Unraveling the high-performance mechanism of Mo2C catalysts in methylcyclohexane dehydrogenation

Somnath Basu Roy Chowdhury, Beena Mol Babu, Tata Sanjay Kanna Sharma, Jayasmita Jana et autres

kr (code pays fourni par la source)

Fundamental Limits of Perfect Concept Erasure

Somnath Basu Roy Chowdhury, Avinava Dubey, Ahmad Beirami, Rahul Kidambi et autres

Concept erasure is the task of erasing information about a concept (e.g., gender or race) from a representation set while retaining the maximum possible utility -- information from original representations. Concept erasure is useful in several applications, such as removing sensitive concepts …

Exploring Safety-Utility Trade-Offs in Personalized Language Models

Anvesh Rao Vijjini, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi

Anvesh Rao Vijjini, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

us (code pays fourni par la source)

Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularity

Jake Varley, Sumeet Singh, Deepali Jain, Krzysztof Choromański et autres

We present an embodied AI system which receives open-ended natural language instructions from a human, and controls two arms to collaboratively accomplish potentially long-horizon tasks over a large workspace. Our system is modular: it deploys state of the art Large Language Models …

us (code pays fourni par la source)

Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning

Arijit Sehanobish, Avinava Dubey, Krzysztof Choromański, Somnath Basu Roy Chowdhury et autres

Recent efforts to scale Transformer models have demonstrated rapid progress across a wide range of tasks (Wei et al., 2022). However, fine-tuning these models for downstream tasks is expensive due to their large parameter counts. Parameter-efficient fine-tuning (PEFT) approaches have emerged as …

Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

Somnath Basu Roy Chowdhury, Krzysztof Choromański, Arijit Sehanobish, Avinava Dubey et autres

Machine unlearning is the process of efficiently removing the influence of a training data instance from a trained machine learning model without retraining it from scratch. A popular subclass of unlearning approaches is exact machine unlearning, which focuses on techniques that explicitly …

Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers

Krzysztof Choromański, Arijit Sehanobish, Somnath Basu Roy Chowdhury, Han X. Lin et autres

We present a new class of fast polylog-linear algorithms based on the theory of structured matrices (in particular low displacement rank) for integrating tensor fields defined on weighted trees. Several applications of the resulting fast tree-field integrators (FTFIs) are presented, including (a) …

Exploring Safety-Utility Trade-Offs in Personalized Language Models

Anvesh Rao Vijjini, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi

As large language models (LLMs) become increasingly integrated into daily applications, it is essential to ensure they operate fairly across diverse user demographics. In this work, we show that LLMs suffer from personalization bias, where their performance is impacted when they are …