Author

Vinay Kumar Sankarapu

h-index 5 View on Semantic Scholar

We have 7 of 28 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy. Such monitoring is meaningful only if a detector's verdict depends on the s...

Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu et al. · 2 citations

#machine learning Preprint Oct 2026

AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents

Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing tooling typically addresses these stages in isolation. We present AgentTune, a source-available Python library that provides a unified framework for developing and opti...

R E Zera Marveen Lyngkhoi, Abhivansh Gupta, Vidushee Vats et al. · 0 citations

#machine learning Preprint Oct 2026

When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior

Relational foundation models are increasingly pretrained on synthetic databases, yet downstream benchmarks reveal little about why one synthetic corpus produces a better model than another. In particular, strong performance may arise from realistic row-level statistics without the model ever learning to use relational...

Shivam Dubey, Mohamed Bouadi, Nassim Bouarour et al. · 0 citations

#machine learning Preprint Oct 2026

From Behavior to Provenance: Attributing Tabular Foundation Models to Synthetic Pretraining Data

Training-data attribution aims to identify which training examples shape model behavior, yet validating such claims is difficult because causal training influence is rarely observable. We argue that controlled synthetic pretraining makes attribution experimentally testable. Using O'PRIOR, a provenance-rich synthetic ta...

Mohamed Bouadi, Nassim Bouarour, Shivam Dubey et al. · 0 citations

#machine learning Preprint Oct 2026

Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair

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 mechanism remains unclear. The most systematic study to date concluded that self-repair is noisy and unlikely to have a single explanation. We ar...

Areeb Ahmad, Pratinav Seth, Vinay Kumar Sankarapu · 0 citations

#machine learning Preprint Aug 2026

SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs

Methods for addressing safety drift in fine-tuned Large Language Models (LLMs) are scattered across incompatible implementations, lifecycle stages, and evaluation protocols, making them difficult to adopt and compare. We introduce SafeTune, a source-available library that unifies four intervention paradigms: post-hoc w...

Pratinav Seth, Saisab Sadhu, Anshul Kaushal et al. · 0 citations

Preprint Jul 2026

Faithfulness to Refusal: A Causal Audit of Neuron Selectors

Two paired audits built on one-shot neuron-row zeroing show that rank-stability proxies miss the kinds of selector failures a direct causal audit can surface, and audit selectors at the language-modeling level.

Ananth Eswar, Pratinav Seth, Utsav Avaiya et al. · 1 citation