Hate speech detection on social media faces challenges in both accuracy and explainability, especially for underexplored Indic languages. We propose a novel exp...
While Unified Multimodal Models (UMMs) have achieved remarkable success in cross-modal comprehension, a significant gap persists in their ability to leverage su...
The hallmark of human intelligence is the ability to master new skills through Constructive Episodic Simulation-retrieving past experiences to synthesize soluti...
Multimodal medical large language models have shown impressive progress in chest X-ray interpretation but continue to face challenges in spatial reasoning and a...
Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typicall...
We present a theoretical analysis of decentralization of autoregressive generation. We define the Decentralized Discrete Flow Matching objective, by expressing ...
Foundation models (FMs) are recognized as a transformative breakthrough that has started to reshape the future of artificial intelligence (AI) across both acade...
Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial c...
Precise and scalable instance segmentation of cell nuclei is essential for computational pathology, yet gigapixel Whole-Slide Images pose major computational ch...
Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent...
Surface electromyography (sEMG) provides a direct neural interface for decoding muscle activity and offers a promising foundation for keyboard-free text input i...
In todays digital landscape, end-user feedback plays a crucial role in the evolution of software applications, particularly in addressing issues that hinder use...
