222 citations · 328 across the 139 of their papers we have counts for
41 papers · 1 filter
AlignMerge - Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
Aniruddha Roy, Jyoti Patel, Aman Chadha +2
Merging large language models (LLMs) is a practical way to compose capabilities from multiple fine-tuned checkpoints without retraining. Yet standard schemes (linear weight soups,…
JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
Georgios Ioannides, Christos Constantinou, Aman Chadha +4
We introduce a two-stage self-supervised framework that combines the Joint-Embedding Predictive Architecture (JEPA) with a Density Adaptive Attention Mechanism (DAAM) for learning…
Embodied Referring Expression Comprehension in Human-Robot Interaction
Md Mofijul Islam, Alexi Gladstone, Sujan Sarker +5
As robots enter human workspaces, there is a crucial need for them to comprehend embodied human instructions, enabling intuitive and fluent human-robot interaction (HRI). However,…
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…
DAWZY: A New Addition to AI powered "Human in the Loop" Music Co-creation
Aaron C Elkins, Sanchit Singh, Adrian Kieback +3
Digital Audio Workstations (DAWs) offer fine control, but mapping high-level intent (e.g., "warm the vocals") to low-level edits breaks creative flow. Existing artificial intellige…
Rice-VL: Evaluating Vision-Language Models for Cultural Understanding Across ASEAN Countries
Tushar Pranav, Eshan Pandey, Austria Lyka Diane Bala +3
Vision-Language Models (VLMs) excel in multimodal tasks but often exhibit Western-centric biases, limiting their effectiveness in culturally diverse regions like Southeast Asia (SE…
Catch Me If You Can: How Smaller Reasoning Models Pretend to Reason with Mathematical Fidelity
Subramanyam Sahoo, Vinija Jain, Saanidhya Vats +4
Current evaluation of mathematical reasoning in language models relies primarily on answer accuracy, potentially masking fundamental failures in logical computation. We introduce a…
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…
Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria
Kartik Garg, Shourya Mishra, Kartikeya Sinha +8
Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving diff…
Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models
Huan Song, Deeksha Razdan, Yiyue Qian +6
Small Language Models (SLMs) offer compelling advantages in deployment cost and latency, but their accuracy often lags behind larger models, particularly for complex domain-specifi…
DeHate: A Stable Diffusion-based Multimodal Approach to Mitigate Hate Speech in Images
Dwip Dalal, Gautam Vashishtha, Anku Rani +11
The rise in harmful online content not only distorts public discourse but also poses significant challenges to maintaining a healthy digital environment. In response to this, we in…
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…
A Comprehensive Dataset for Human vs. AI Generated Text Detection
Rajarshi Roy, Gurpreet Singh, Ashhar Aziz +17
The rapid advancement of large language models (LLMs) has led to increasingly human-like AI-generated text, raising concerns about content authenticity, misinformation, and trustwo…
FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs
Md Mubtasim Ahasan, Rafat Hasan Khan, Tasnim Mohiuddin +6
Speech tokenization enables discrete representation and facilitates speech language modeling. However, existing neural codecs capture low-level acoustic features, overlooking the s…
SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction
Saumya Chaturvedi, Aman Chadha, Laurent Bindschaedler
Converting natural language queries into SQL queries is a crucial challenge in both industry and academia, aiming to increase access to databases and large-scale applications. This…
AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models
Snehasis Mukhopadhyay, Aryan Kasat, Shivam Dubey +5
Large Language Models (LLMs) can inadvertently reflect societal biases present in their training data, leading to harmful or prejudiced outputs. In the Indian context, our empirica…
PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
Leon Garza, Anantaa Kotal, Aritran Piplai +3
Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-…
I Think, Therefore I Am Under-Qualified? A Benchmark for Evaluating Linguistic Shibboleth Detection in LLM Hiring Evaluations
Julia Kharchenko, Tanya Roosta, Aman Chadha +1
This paper introduces a comprehensive benchmark for evaluating how Large Language Models (LLMs) respond to linguistic shibboleths: subtle linguistic markers that can inadvertently…
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…
TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
Amitava Das, Vinija Jain, Aman Chadha
Large Language Models (LLMs) fine-tuned to align with human values often exhibit alignment drift, producing unsafe or policy-violating completions when exposed to adversarial promp…
Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact
Rizwan Qureshi, Ranjan Sapkota, Abbas Shah +16
Can machines truly think, reason and act in domains like humans? This enduring question continues to shape the pursuit of Artificial General Intelligence (AGI). Despite the growing…
MOD-X: A Modular Open Decentralized eXchange Framework proposal for Heterogeneous Interoperable Artificial Intelligence Agents
Georgios Ioannides, Christos Constantinou, Vinija Jain +2
As Artificial Intelligence systems evolve from monolithic models to ecosystems of specialized agents, the need for standardized communication protocols becomes increasingly critica…
Energy-Based Transformers are Scalable Learners and Thinkers
Alexi Gladstone, Ganesh Nanduru, Md Mofijul Islam +7
Inference-time computation techniques, analogous to human System 2 Thinking, have recently become popular for improving model performances. However, most existing approaches suffer…
Investigating Hallucination in Conversations for Low Resource Languages
Amit Das, Md. Najib Hasan, Souvika Sarkar +7
Large Language Models (LLMs) have demonstrated remarkable proficiency in generating text that closely resemble human writing. However, they often generate factually incorrect state…