Research
Research
Research
Research
182,110+ open-access research outputs.
Large Language Models (LLMs) have transformed software development and AI applications. While LLMs are designed for text processing, LLM agents extend this capability by enabling autonomous actions, t…
Games offer a compelling paradigm for developing general reasoning capabilities in language models, as they naturally demand strategic planning, probabilistic inference, and adaptive decision-making. …
Peer review is central to scientific publishing, yet reviewers frequently include claims that are subjective, rhetorical, or misaligned with the submitted work. Assessing whether review statements are…
Constitution-conditioned post-training can be analysed as a structured perturbation of a model's learned representational geometry. We introduce ATLAS, a geometry-first program that traces constitutio…
Continuous Integration and Continuous Deployment (CI/CD) have become fundamental to modern software development, with GitHub Actions (GHA) emerging as a dominant automation platform. In this study, we…
The footprints of residential segregation have long been documented, yet the role of urban form as both medium and manifestation of segregation remains under-specified. We investigate whether the conf…
This work addresses the challenge of disseminating reusable artificial intelligence (AI) models accompanied by AI documentation (a.k.a., AI model cards). The work is motivated by the large number of t…
High and persistent child malnutrition levels with tardy reduction, seen in successive health surveys, continue to be a matter of concern in India, drawing attention to the need to revamp the four-dec…
Multi-agent systems built on large language models (LLMs) are difficult to reason about. Coordination errors such as deadlocks or type-mismatched messages are often hard to detect through testing. We …
How much data is enough to make a scientific discovery? As biomedical datasets scale to millions of samples and AI models grow in capacity, progress increasingly depends on predicting when additional …
Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical de…
Bangladesh exhibits marked year-to-year variability in dengue, partly driven by meteorological fluctuations that shape \textit{Aedes} breeding-site persistence, mosquito development, and transmission.…
Two-particle two-hole (2p2h) excitations driven by meson-exchange currents (MEC) are among the leading nuclear uncertainties in long-baseline neutrino oscillation experiments. Three models currently i…
Medical imaging AI development is fundamentally dependent on annotated datasets, yet no existing standard provides machine-enforceable validation across dataset structure, annotation provenance, quali…
Ransomware continues to evolve as one of the most disruptive cyber threats, with recent variants increasingly leveraging automated and AI-assisted techniques to evade traditional signature-based defen…
The transition from neural machine translation to agentic workflows has revolutionized Automated Program Repair (APR). However, existing agents, despite their advanced reasoning capabilities, frequent…
A Single-Photon Detector (SPD) can detect extremely low intensity of electromagnetic wave - down to a single photon. Driven by the rapid developments in quantum information science and an increasing d…
These notes give a concise introduction to General Relativity at the advanced undergraduate level, starting from the weak field limit and gravitational waves, then introducing curved manifolds and Rie…
Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to ext…
Automatic evaluation metrics are central to the development of machine translation systems, yet their robustness under domain shift remains unclear. Most metrics are developed on the Workshop on Machi…
Free open-access publishing with Google Scholar indexing.
Submission Guide →