19 citations · 36 across the 42 of their papers we have counts for
10 papers · 1 filter
Merge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion
Aditya Pola, Vineeth N. Balasubramanian
Model merging consolidates fine-tuned experts into one multi-task model without retraining. All existing data-free methods approach this problem entirely in weight space. Restricte…
Annotation-Free Class-Incremental Learning
Hari Chandana Kuchibhotla, K S Ananth, Vineeth N Balasubramanian
Despite significant progress in continual learning ranging from architectural novelty to clever strategies for mitigating catastrophic forgetting most existing methods rest on a st…
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz +2
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable,…
Interpretable Model Drift Detection
Pranoy Panda, Kancheti Sai Srinivas, Vineeth N Balasubramanian +1
Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowled…
FW-Shapley: Real-time Estimation of Weighted Shapley Values
Pranoy Panda, Siddharth Tandon, Vineeth N Balasubramanian
Fair credit assignment is essential in various machine learning (ML) applications, and Shapley values have emerged as a valuable tool for this purpose. However, in critical ML appl…
Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
Susmit Agrawal, Deepika Vemuri, Sri Siddarth Chakaravarthy P +1
Concept-based methods have emerged as a promising direction to develop interpretable neural networks in standard supervised settings. However, most works that study them in increme…
Teaching Transformers Causal Reasoning through Axiomatic Training
Aniket Vashishtha, Abhinav Kumar, Atharva Pandey +4
For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since active interventions are costly, we study to what extent a system can learn c…
Rethinking Robustness of Model Attributions
Sandesh Kamath, Sankalp Mittal, Amit Deshpande +1
For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is import…
Mitigating the Effect of Incidental Correlations on Part-based Learning
Gaurav Bhatt, Deepayan Das, Leonid Sigal +1
Intelligent systems possess a crucial characteristic of breaking complicated problems into smaller reusable components or parts and adjusting to new tasks using these part represen…
Universalization of any adversarial attack using very few test examples
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam +1
Deep learning models are known to be vulnerable not only to input-dependent adversarial attacks but also to input-agnostic or universal adversarial attacks. Dezfooli et al. \cite{D…