Publications (23)
Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep +40
Rotate to Attend: Convolutional Triplet Attention Module
Diganta Misra, Trikay Nalamada, Ajay Uppili Arasanipalai +1
Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics
Victor May, Aaditya Salgarkar, Yishan Wang +2
(Almost) Free Modality Stitching of Foundation Models
Jaisidh Singh, Diganta Misra, Boris Knyazev +1
GRASP: Deterministic argument ranking in interaction graphs
Diganta Misra, Antonio Orvieto, Rediet Abebe +1
Image Processing on IOPA Radiographs: A comprehensive case study on Apical Periodontitis
Diganta Misra, Vanshika Arora
Uncovering the Hidden Cost of Model Compression
Diganta Misra, Muawiz Chaudhary, Agam Goyal +2
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Explaining Grokking in Transformers through the Lens of Inductive Bias
Jaisidh Singh, Diganta Misra, Antonio Orvieto
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models
Nizar Islah, Justine Gehring, Diganta Misra +4
On the low-shot transferability of [V]-Mamba
Diganta Misra, Jay Gala, Antonio Orvieto
GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version Incompatibilities
Diganta Misra, Nizar Islah, Victor May +9
GenOL: Generating Diverse Examples for Name-only Online Learning
Minhyuk Seo, Seongwon Cho, Minjae Lee +4
Using Shapley interactions to understand how models use structure
Divyansh Singhvi, Diganta Misra, Andrej Erkelens +3
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Hao Chen, Yujin Han, Diganta Misra +6
Mish: A Self Regularized Non-Monotonic Activation Function
Diganta Misra
Advanced Image Processing for Astronomical Images
Diganta Misra, Sparsha Mishra, Bhargav Appasani
Challenging Common Assumptions about Catastrophic Forgetting
Timothée Lesort, Oleksiy Ostapenko, Diganta Misra +4
FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
Victor May, Diganta Misra, Yanqi Luo +3
APP: Anytime Progressive Pruning
Diganta Misra, Bharat Runwal, Tianlong Chen +2
Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee +46
MMTEB: Massive Multilingual Text Embedding Benchmark
Kenneth Enevoldsen, Isaac Chung, Imene Kerboua +83