computer vision

HeadGuard: Selective Head Protection for Low-Bit VLM KV-Cache Quantization

Evaluated through simulated quantization, HeadGuard offers a composable way to improve low-bit VLM accuracy without replacing the underlying quantizer.

FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding

ForUM is presented, a training-free test-time fusion of frozen MLLMs guided by two fixed geometric rules: agreement-based selection keeps the region supported by the most distinct models, and medoid localization returns an actual member box instead of a coordinate average, so one loose prediction cannot shift the answe...

An Analysis of Object Detection in Bad Weather Conditions using Deep Learning Models

Object detection, a task, in the field of computer vision faces obstacles when dealing with weather conditions such as fog, rain, snow, and low light situations. This paper provides an overview of advancements in the realm of object detection under challenging weather conditions. It delves into groundbreaking research...

Exploring the Landscape of Cloud Robotics: A Comprehensive Review

Cloud robotics is an innovative field that leverages cloud technologies-including cloud computing (CC), cloud storage, deep learning, big data, and the Internet of Things to augment the capabilities of robotics. This integration facilitates the execution of robotic functions through a converged infrastructure and share...

Active learning for interactive prompt clarification in safety-critical programmable logic controller code generation

A Memory-Efficient Tool for Bengali Parts of Speech Tagging

Are Predictive Models Epistemically Superior to Causal Ones?

This thesis investigates the complex and often contentious question of whether predictive models are epistemically superior to causal models. It challenges the simplistic dichotomy that often frames this debate, arguing that the epistemic superiority of a model is not an intrinsic property but is contingent upon the sp...

Are Predictive Models Epistemically Superior to Causal Ones?

This thesis investigates the complex and often contentious question of whether predictive models are epistemically superior to causal models. It challenges the simplistic dichotomy that often frames this debate, arguing that the epistemic superiority of a model is not an intrinsic property but is contingent upon the sp...

How Should We Understand Truth in Fluctuational Epistemology?

This paper develops a novel account of truth grounded in fluctuational epistemology, a framework that situates knowledge within the ontological instability of reality. Traditional theories—correspondence, coherence, pragmatic, and deflationary—assume varying degrees of stability in the relation between propositions and...

How Should We Understand Truth in Fluctuational Epistemology?

This paper develops a novel account of truth grounded in fluctuational epistemology, a framework that situates knowledge within the ontological instability of reality. Traditional theories—correspondence, coherence, pragmatic, and deflationary—assume varying degrees of stability in the relation between propositions and...

Is the Algorithm an Epistemic Agent? A Critical Analysis of Computational Epistemology and the Emergence of Algorithmic Agency

The question of whether algorithms can be considered epistemic agents represents one of the most profound challenges at the intersection of philosophy of mind, epistemology, and artificial intelligence. This paper develops a novel theoretical framework for understanding algorithmic epistemic agency through the introduc...

Is the Algorithm an Epistemic Agent? A Critical Analysis of Computational Epistemology and the Emergence of Algorithmic Agency

The question of whether algorithms can be considered epistemic agents represents one of the most profound challenges at the intersection of philosophy of mind, epistemology, and artificial intelligence. This paper develops a novel theoretical framework for understanding algorithmic epistemic agency through the introduc...