222 citations · 400 across the 85 of their papers we have counts for
17 papers · 1 filter
Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it…
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
Yash Aggarwal, Atmika Gorti, Vinija Jain +3
Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "…
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
Anay Chauhan, Gurucharan Marthi Krishna Kumar, Arion Das +4
Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeated High Bandwidth Memory (HBM)…
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Suryash Yagnik, Shubham Gaur, Saksham Thakur +3
Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of CounterFact, 0.6% of ZSRE, and le…
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
Harsh Kumar, Rahul Maity, Tanmay Joshi +4
Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. W…
When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Mathematical reasoning models are widely deployed in education, automated tutoring, and decision support systems despite exhibiting fundamental computational instabilities. We demo…
I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
Subramanyam Sahoo, Vinija Jain, Divya Chaudhary +1
Instruction tuned reasoning models are increasingly deployed with safety classifiers trained on frozen embeddings, assuming representation stability across model updates. We system…
SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
Arion Das, Partha Pratim Saha, Amit Dhanda +3
Direct Preference Optimization (DPO) is a principled, scalable alternative to RLHF for aligning large language models from pairwise preferences, but its internal geometric footprin…
ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
Kapil Wanaskar, Gaytri Jena, Vinija Jain +2
Alignment in large language models (LLMs) is still largely static: after training, the policy is frozen. DPO, GRPO methods typically imprint one behavior into the weights, leaving…
D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
Samarth Raina, Saksham Aggarwal, Aman Chadha +3
Preference-based post-training shapes language-model behavior, but safer outputs do not reveal how that change is represented internally or how firmly it persists under direct inte…
Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma
Subramanyam Sahoo, Aman Chadha, Vinija Jain +1
Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fair…
A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies
Sathwik Narkedimilli, N V Saran Kumar, Aswath Babu H +5
Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adver…
AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
Amitava Das, Abhilekh Borah, Vinija Jain +1
Low-rank adaptation (LoRA) has become a standard tool for efficiently fine-tuning large language models (LLMs). Yet, even minor LoRA updates can induce alignment drift, weakening s…
DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization
Amitava Das, Suranjana Trivedy, Danush Khanna +8
The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Prefer…
A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models
Pranab Sahoo, Prabhash Meharia, Akash Ghosh +3
The rapid advancement of foundation models (FMs) across language, image, audio, and video domains has shown remarkable capabilities in diverse tasks. However, the proliferation of…
Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications
Charith Chandra Sai Balne, Sreyoshi Bhaduri, Tamoghna Roy +2
The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of p…
Few-shot Multimodal Multitask Multilingual Learning
Aman Chadha, Vinija Jain
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building u…