6 papers
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
Ganesh Senrayan, Moyuru Yamada, Ishan Jindal +1
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, e…
A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs
Kiran Purohit, Anurag Reddy Parvathgari, Sourangshu Bhattacharya
Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes require heavy computational resources…
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
Kiran Purohit, Ramasuri Narayanam, Soumyabrata Pal
Speculative decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose outputs that a stronger target model verifies. However, its to…
Sample Efficient Demonstration Selection for In-Context Learning
Kiran Purohit, V Venktesh, Sourangshu Bhattacharya +1
The in-context learning paradigm with LLMs has been instrumental in advancing a wide range of natural language processing tasks. The selection of few-shot examples (exemplars / dem…
EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning
Kiran Purohit, Venktesh V, Raghuram Devalla +3
Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-c…
A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning
Kiran Purohit, Soumi Das, Sourangshu Bhattacharya +1
Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the inp…