Scholar
Vedant Palit
Google Scholar ID: aUL2jngAAAAJ
Indian Institute of Technology, Kharagpur
Natural Language Processing
Mechanistic Interpretability
Deep Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
74
H-index
5
i10-index
2
Publications
7
Co-authors
10
list available
Publications
8 items
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
2026
Cited
0
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
2026
Cited
0
Simulating Eutopia: Revisiting Long-term Fairness with Outcomes, Performativity, and Dynamics
arXiv.org · 2026
Cited
0
CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
2026
Cited
0
Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks
2025
Cited
0
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
2025
Cited
0
Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case
2025
Cited
0
What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Noise-free Text-Image Corruption and Evaluation
arXiv.org · 2024
Cited
0
Co-authors
10 total
William Rudman
Postdoctoral Fellow, UT-Austin
Carsten Eickhoff
Professor, University of Tübingen
Ritambhara Singh
Associate Professor, Brown University
Michal Golovanevsky
Brown University
Aryaman Arora
Stanford University
Rohan Pandey
OpenAI
Paul Liang
Assistant Professor, Media Lab and EECS, MIT
Manas Gaur
University of Maryland Baltimore County
