4 papers
Mechanistic Analysis of Alignment Algorithms in Language Models
Aarush Sinha, Ishan Garg, Veeraraju Elluru +2
Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations. We present a systematic mechanisti…
Mechanistically Interpreting Compression in Vision-Language Models
Veeraraju Elluru, Arth Singh, Roberto Aguero +3
Compressed vision-language models (VLMs) are widely used to reduce memory and compute costs, making them a suitable choice for real-world deployment. However, compressing these mod…
Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
Sai Siddhartha Chary Aylapuram, Veeraraju Elluru, Shivang Agarwal
Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous drivin…
Zero-resource Speech Translation and Recognition with LLMs
Karel Mundnich, Xing Niu, Prashant Mathur +10
Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose…