Research
Research
Research
Research
138+ open-access research outputs.
Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long…
There is an increasing interest in telling serious stories with data. Designers organize information, construct narratives, and present findings to inform audiences. However, many of these practices e…
In-Context Learning (ICL) is a significant paradigm for Large Multimodal Models (LMMs), using a few in-context demonstrations (ICDs) for new task adaptation. However, its performance is sensitive to d…
We prove that a complete Riemannian manifold with a positive uniform lower bound on injectivity radius and a positive uniform lower bound on Ricci curvature admits an $L^\infty$-close (bi-Lipschitz) s…
This study investigates one of the central problems of dynamic fracture mechanics, namely the dependence of the instantaneous stress intensity factor (SIF) on the crack propagation velocity. For this …
Vision-Language Models (VLMs) remain limited in spatial reasoning tasks that require multi-view understanding and embodied perspective shifts. Recent approaches such as MindJourney attempt to mitigate…
Multimodal large language models (MLLMs) that think with images can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-…
We present ShoppingComp, a challenging real-world benchmark for comprehensively evaluating LLM-powered shopping agents on three core capabilities: precise product retrieval, expert-level report genera…
The Coupling from the Past (CFTP) paradigm is a canonical method for perfect sampling. For uniform sampling of proper $q$-colorings in graphs with maximum degree $\Delta$, the bounding chains of Huber…
This dataset provides responses to a standardized, bilingual (English-Hindi) Prakriti Assessment Questionnaire designed to evaluate the physical, physiological, and psychological characteristics of in…
We propose LLM-Interleaved (LLM-I), a flexible and dynamic framework that reframes interleaved image-text generation as a tool-use problem. LLM-I is designed to overcome the "one-tool" bottleneck of c…
The advent of Deep Research agents has substantially reduced the time required for conducting extensive research tasks. However, these tasks inherently demand rigorous standards of factual accuracy an…
We introduce the cave polynomial of a polymatroid and show that it yields a valuative function on polymatroids. The support of this polynomial after homogenization is again a polymatroid. The cave pol…
Gait is becoming popular as a method of person re-identification because of its ability to identify people at a distance. However, most current works in gait recognition do not address the practical p…
We introduce the Mirya-m1 Cosmic Ray Detector, the largest and only cosmic ray detector in Turkiye designed for space weather research. Mirya-m1, modeled and built after the Muon Impact Tracer and Obs…
We investigate some classes of infinite series involving central binomial coefficients, particularly focusing on those arising from ratios such as $\binom{2n}{n}\binom{4n}{2n}^{-1}$,$\binom{4n}{2n}\bi…
Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting t…
Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing models may fail to pro…
Gait recognition is an important biometric technique over large distances. State-of-the-art gait recognition systems perform very well in controlled environments at close range. Recently, there has be…
We consider the procedure proposed by Bhandari et al. (2009) in the context of two-treatment clinical trials, with the objective of minimizing the applications of the less effective drug to the least …
Free open-access publishing with Google Scholar indexing.
Submission Guide →