10 papers
Chain-of-Thought Shows the Path to a Tree: Realizing Branching Complexity
Debanjan Dutta, Anish Chakrabarty, Swagatam Das
Chain of Thought (CoT) lifts the expressive ceiling of bounded-depth Transformers, with characterizations tying the number of CoT steps to circuit complexity classes. What remains…
ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models
Sharanya Dasgupta, Arkaprabha Basu, Sujoy Nath +1
Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations…
HalluShift++: Bridging Language and Vision through Internal Representation Shifts for Hierarchical Hallucinations in MLLMs
Sujoy Nath, Arkaprabha Basu, Sharanya Dasgupta +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding tasks. While these models often produce linguistically coherent…
Relation-Aware Slicing in Cross-Domain Alignment
Dhruv Sarkar, Aprameyo Chakrabartty, Anish Chakrabarty +1
The Sliced Gromov-Wasserstein (SGW) distance, aiming to relieve the computational cost of solving a non-convex quadratic program that is the Gromov-Wasserstein distance, utilizes p…
On the Existence of Universal Simulators of Attention
Debanjan Dutta, Anish Chakrabarty, Faizanuddin Ansari +1
Previous work on the learnability of transformers \textemdash\ focused primarily on examining their ability to approximate specific algorithmic patterns through training \textemdas…
HalluShift: Measuring Distribution Shifts towards Hallucination Detection in LLMs
Sharanya Dasgupta, Sujoy Nath, Arkaprabha Basu +2
Large Language Models (LLMs) have recently garnered widespread attention due to their adeptness at generating innovative responses to the given prompts across a multitude of domain…
On Robust Cross Domain Alignment
Anish Chakrabarty, Arkaprabha Basu, Swagatam Das
The Gromov-Wasserstein (GW) distance is an effective measure of alignment between distributions supported on distinct ambient spaces. Calculating essentially the mutual departure f…
Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures
Arkaprabha Basu, Kushal Bose, Sankha Subhra Mullick +2
Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) co…
Concurrent Density Estimation with Wasserstein Autoencoders: Some Statistical Insights
Anish Chakrabarty, Arkaprabha Basu, Swagatam Das
Variational Autoencoders (VAEs) have been a pioneering force in the realm of deep generative models. Amongst its legions of progenies, Wasserstein Autoencoders (WAEs) stand out in…
HyPE-GT: where Graph Transformers meet Hyperbolic Positional Encodings
Kushal Bose, Swagatam Das
Graph Transformers (GTs) facilitate the comprehension of complex relationships on graph-structured data by leveraging self-attention of the possible pairs of nodes. The structural…