activity
20242026
collaborators

5 papers

cs.AI2026

GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

Pavan C Shekar, Abhishek H S, Aswanth Krishnan

Large language model reasoning leaves no trace once it is done. The steps of a chain of thought disappear when the context window closes, a pruned search branch is just gone, and m…

cs.AI2026

ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models

Abhishek HS, Pavan C Shekar, Arpit Jain +1

Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1. We pres…

cs.AI2026

Adaptive Minds: Empowering Agents with LoRA-as-Tools

Pavan C Shekar, Aswanth Krishnan

We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hypothesize that, when adapters are…

cs.CV2025

HyperFake: Hyperspectral Reconstruction and Attention-Guided Analysis for Advanced Deepfake Detection

Pavan C Shekar, Pawan Soni, Vivek Kanhangad

Deepfakes pose a significant threat to digital media security, with current detection methods struggling to generalize across different manipulation techniques and datasets. While…

cs.CV2024

Automated Bleeding Detection and Classification in Wireless Capsule Endoscopy with YOLOv8-X

Pavan C Shekar, Vivek Kanhangad, Shishir Maheshwari +1

Gastrointestinal (GI) bleeding, a critical indicator of digestive system disorders, re quires efficient and accurate detection methods. This paper presents our solution to the Auto…