Expertini Research Research

Browse Research Papers

190+ open-access research outputs.

✕ Clear
🔍 abhinav joshi
Showing 190 results for "abhinav joshi"
AI & Data Science Preprint PDF DOI

Learning to Think from Multiple Thinkers

Nirmit Joshi, Roey Magen, Nathan Srebro, Nikolaos Tsilivis, Gal Vardi · 2026

We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step solutions to math prob…

Read Paper →
AI & Data Science Preprint PDF DOI

Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations

Bhaskar Singh, Shobhit Banga, Pranav Sharma · 2026

Full-duplex spoken dialogue systems can model natural conversational behaviours such as interruptions, overlaps, and backchannels, yet such systems remain largely unexplored for Indian languages. We p…

Read Paper →
Computer Science Preprint PDF DOI

Analysis of AWW (Anganwadi Workers) Training Content, ILA (Incremental Learning Approach) Modules Following CDT (Component Display Theory)

Arka Majhi, Satish B. Agnihotri · 2026

POSHAN Abhiyan envisages capacity building of AWWs or frontline health workers through 21 training modules of ILA (Incremental Learning Approach), modularising the net learning content into smaller le…

Read Paper →
Physics Preprint PDF DOI

Quasinormal modes of the generalized JMN naked singularity using exact WKB analysis

Aryansh Saxena, Suresh C. Jaryal, K. K. Sharma · 2026

In this paper, we study the quasinormal modes of the generalized Joshi-Malafarina-Narayan (JMN) naked singularity spacetime using the exact Wentzel-Kramers-Brillouin (WKB) method. Working in the compl…

Read Paper →
Physics Preprint PDF DOI

GRMHD accretion beyond the black hole paradigm: Light from within the shadow

Saurabh, Maciek Wielgus, Parth Bambhaniya, Elisabete M. de Gouveia Dal Pino, Andrei P. Lobanov, Pankaj S. Joshi · 2026

We present the first three-dimensional general relativistic magnetohydrodynamic simulation of sustained accretion onto a horizonless singularity in which matter reaches the central object rather than …

Read Paper →
AI & Data Science Preprint PDF DOI

Towards Design Compositing

Abhinav Mahajan, Abhikhya Tripathy, Sudeeksha Reddy Pala, Vaibhav Methi, K J Joseph, Balaji Vasan Srinivasan · 2026

Graphic design creation involves harmoniously assembling multimodal components such as images, text, logos, and other visual assets collected from diverse sources, into a visually-appealing and cohesi…

Read Paper →
AI & Data Science Preprint PDF DOI

Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-End

Steve Hanneke, Idan Mehalel, Shay Moran · 2026

Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (COLT 2025) introduced a PAC-learning framework for…

Read Paper →
AI & Data Science Preprint PDF DOI

Environmental Footprint of GenAI Research: Insights from the Moshi Foundation Model

Marta Lopez-Rauhut, Loic Landrieu, Mathieu Aubry, Anne-Laure Ligozat · 2026

New multi-modal large language models (MLLMs) are continuously being trained and deployed, following rapid development cycles. This generative AI frenzy is driving steady increases in energy consumpti…

Read Paper →
Mathematics Preprint PDF DOI

Computing with reaction networks at input-independent speed: exponential and logarithmic functions

David F. Anderson, Badal Joshi, Tung D. Nguyen · 2026

The concept of input-independent computational time for chemistry-based analog computers was introduced in Anderson-Joshi (2025), where it was shown that arithmetic operations can be computed in a fix…

Read Paper →
Engineering Preprint PDF DOI

RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild

Wenjing Margaret Mao, Jefferson Ng, Luyang Hu, Daniel Gehrig, Antonio Loquercio · 2026

Scaling up robot learning will likely require human data containing rich and long-horizon interactions in the wild. Existing approaches for collecting such data trade off portability, robustness to oc…

Read Paper →
AI & Data Science Preprint PDF DOI

A Taxonomy of Programming Languages for Code Generation

Nishat Raihan, Christian Newman, Marcos Zampieri · 2026

The world's 7,000+ languages vary widely in the availability of resources for NLP, motivating efforts to systematically categorize them by their degree of resourcefulness (Joshi et al., 2020). A simil…

Read Paper →
Physics Preprint PDF DOI

Causal Structure of Spacetime Singularities and Their Observable Signatures

Bina Patel, Jahnvi Mistry, Ayush Bidlan, Parth Bambhaniya · 2026

We analyze the causal structure of horizonless compact objects via the light-cone geometry and conformal compactification of the Joshi-Malafarina-Narayan (JMN-1) and Janis-Newman-Winicour (JNW) spacet…

Read Paper →
Physics Preprint PDF DOI

Generalized JMN Naked Singularity Models

Jay Verma Trivedi, Pankaj S. Joshi · 2026

We construct a generalized class of Joshi-Malafarina-Narayan (JMN) naked singularity spacetimes that arise as equilibrium end states of gravitational collapse with non-vanishing tangential pressure. T…

Read Paper →
Mathematics Preprint PDF DOI

The log homotopy exact sequence

Mattia Talpo · 2026

We show exactness of the homotopy sequence for the logarithmic fundamental group in the case of log smooth, finitely presented, proper and saturated morphisms of fs log schemes over a field. This gene…

Read Paper →
Physics Preprint PDF DOI

Degeneracy in Accretion Disk Spectra from Naked Singularities and Kerr Black Holes: Application to the AGN MCG-06-30-15

Vishva Patel, Sayantan Bhattacharya, Sudip Bhattacharyya, Pankaj S. Joshi · 2026

Theoretical studies suggest that gravitational collapse can form either a black hole or a visible (naked) singularity. Identifying observational signatures that distinguish these two types of collapse…

Read Paper →
Engineering Preprint PDF DOI

Privacy-Preserving End-to-End Full-Duplex Speech Dialogue Models

Nikita Kuzmin, Tao Zhong, Jiajun Deng, Yingke Zhu, Tristan Tsoi, Tianxiang Cao, Simon Lui, Kong Aik Lee, Eng Siong Chng · 2026

End-to-end full-duplex speech models feed user audio through an always-on LLM backbone, yet the speaker privacy implications of their hidden representations remain unexamined. Following the VoicePriva…

Read Paper →
Mathematics Preprint PDF DOI

Anabelian perspectives in Galois-Teichm\"uller theory

Benjamin Collas · 2026

By exploiting the arithmetic homotopy of the moduli spaces of curves, Galois-Teichm\"uller theory stands at the interface of braid-mapping class groups and of anabelian geometry. Starting from the cla…

Read Paper →
Mathematics Preprint PDF DOI

The Golden Sieve

Benoit Cloitre · 2026

We revisit the golden sieve, a self-referential deletion process on increasing sequences of positive integers introduced by the author in 2002. Applied to the natural numbers, the sieve produces the W…

Read Paper →
Computer Science Preprint PDF DOI

Artificial intelligence is creating a new global linguistic hierarchy

Giulia Occhini, Kumiko Tanaka-Ishii, Anna Barford, Refael Tikochinski, Songbo Hu, Roi Reichart, Yijie Zhou, Hannah Claus, Ulla Petti, Ivan Vulic, Ramit Debnath, Anna Korhonen · 2026

Artificial intelligence (AI) has the potential to transform healthcare, education, governance and socioeconomic equity, but its benefits remain concentrated in a small number of languages (Bender, 201…

Read Paper →
Computer Science Preprint PDF DOI

Mikasa: A Character-Driven Emotional AI Companion Inspired by Japanese Oshi Culture

Miki Ueno · 2026

Recent progress in large language models and multimodal interaction has made it possible to develop AI companions that can have fluent and emotionally expressive conversations. However, many of these …

Read Paper →
Page 1 of 10 Next →