5 papers
MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
Ashok Urlana, L. D. M. S. Sai Teja, Vivek Hruday Kavuri +1
We present our submission to Task 3 of the Gen 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training objectives, richer concept r…
Think: Grounded Metacognitive Reasoning in Large Language Models
Abraham Paul Elenjical, Vivek Hruday Kavuri, Vasudeva Varma
Large Language Models (LLMs) demonstrate strong reasoning performance, yet their ability to reliably monitor, diagnose, and correct their own errors remains limited. We introduce a…
NEAT: Concept driven Neuron Attribution in LLMs
Vivek Hruday Kavuri, Gargi Shroff, Rahul Mishra
Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies h…
Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
Vivek Hruday Kavuri, Vysishtya Karanam, Venkata Jahnavi Venkamsetty +3
Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text…
KTCR: Improving Implicit Hate Detection with Knowledge Transfer driven Concept Refinement
Samarth Garg, Vivek Hruday Kavuri, Gargi Shroff +1
The constant shifts in social and political contexts, driven by emerging social movements and political events, lead to new forms of hate content and previously unrecognized hate p…