12 papers
RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents
Mayur Akewar, Ravi Ranjan
Agent checkpoint systems decide what state is recovery-relevant, how to snapshot it, and whether rollback is admissible. None decides which of the safe boundaries they expose are w…
DePICT: Decision-Preserving Interface for Constrained Downstream Tasks
Utkarsh Grover, Ravi Ranjan, Agoritsa Polyzou +5
A constrained optimization problem may involve a parameter in its objective and active constraints, yet the final decision may remain insensitive to small changes in that parameter…
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machin…
SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
Mayur Akewar, Ravi Ranjan
Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitment: an agent acts before re…
Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models
Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1
Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret. Existing explainable AI (XAI)…
PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs
Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1
Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while maintaining diagnostic correc…
VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
Ravi Ranjan, Agoritsa Polyzou
Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe…
G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs
Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1
Large language models (LLMs) are trained on massive web-scale corpora, raising growing concerns about privacy and copyright. Membership inference attacks (MIAs) aim to determine wh…
CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs
Ravi Ranjan, Utkarsh Grover, Mayur Akewar +2
Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods…
Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
Utkarsh Grover, Ravi Ranjan, Mingyang Mao +9
Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size,…
RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1
Transformer based diffusion and vision-language models have achieved remarkable success; yet, efficiently removing undesirable or sensitive information without retraining remains a…
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
Ravi Ranjan, Utkarsh Grover, Agorista Polyzou
Biases in large language models (LLMs) often manifest as systematic distortions in associations between demographic attributes and professional or social roles, reinforcing harmful…