21 citations · 34 across the 35 of their papers we have counts for
16 papers · 1 filter
Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair
Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu
Ablate a component of a language model, and other components often appear to adjust and compensate. This phenomenon, termed self-repair, has been observed repeatedly, but its mecha…
SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs
Pratinav Seth, Saisab Sadhu, Anshul Kaushal +1
Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and evaluation protocols, making…
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
Pratinav Seth, Hem Gosalia, Aditya Kasliwal +1
Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such an…
Distilling Tabular Foundation Models for Structured Health Data
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi +2
Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We study whether their…
Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
Aditya Tanna, Yash Desai, Pratinav Seth +3
Tabular foundation models (TFMs) now match or beat tuned gradient-boosted trees on a growing fraction of tabular tasks, but no single TFM wins on every dataset. Ensembling is the g…
Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
Aditya Tanna, Nassim Bouarour, Mohamed Bouadi +2
A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the TFM offline into an XGBoost or…
Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
Aditya Tanna, Mitul Solanki, Mohamed Bouadi +3
Credit default prediction is a tabular learning problem with severe class imbalance, heterogeneous features, and tight latency budgets. Tabular Foundation Models (TFMs) approach th…
Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands
Pratinav Seth, Vinay Kumar Sankarapu
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted betwee…
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent wo…
Exploring Fine-Tuning for Tabular Foundation Models
Aditya Tanna, Pratinav Seth, Mohamed Bouadi +1
Tabular Foundation Models (TFMs) have recently shown strong in-context learning capabilities on structured data, achieving zero-shot performance comparable to traditional machine l…
TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
Aditya Tanna, Pratinav Seth, Mohamed Bouadi +2
Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption re…
Orion-Bix: Bi-Axial Attention for Tabular In-Context Learning
Mohamed Bouadi, Pratinav Seth, Aditya Tanna +1
Tabular data drive most real-world machine learning applications, yet building general-purpose models for them remains difficult. Mixed numeric and categorical fields, weak feature…
Interpretability as Alignment: Making Internal Understanding a Design Principle
Aadit Sengupta, Pratinav Seth, Vinay Kumar Sankarapu
Frontier AI systems require governance mechanisms that can verify internal alignment, not just behavioral compliance. Private governance mechanisms audits, certification, insurance…
xai_evals : A Framework for Evaluating Post-Hoc Local Explanation Methods
Pratinav Seth, Yashwardhan Rathore, Neeraj Kumar Singh +2
The growing complexity of machine learning and deep learning models has led to an increased reliance on opaque "black box" systems, making it difficult to understand the rationale…
DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
Vinay Kumar Sankarapu, Chintan Chitroda, Yashwardhan Rathore +2
The rapid growth of AI has led to more complex deep learning models, often operating as opaque "black boxes" with limited transparency in their decision-making. This lack of interp…
Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data
Kumud Lakara, Akshat Bhandari, Pratinav Seth +1
Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption doesn'…