arXiv subjects

Sandeep Mishra

Publications and source records attributed to Sandeep Mishra.

At least 19 recordsLinked to original sources

arXiv2026

A Unified Quantum Interferometric Framework for Interaction-Free Measurement and Delayed-Choice Experiments

A theoretical unified interferometric framework is developed for interaction-free measurement (IFM) and delayed-choice (DC) experiments. The proposed model leads to a quantum circuit based architecture in which an ancillary qubit coherently controls the interaction between a photon and a bomb, allowing the system to evolve in a superposition of interaction and non-interaction regimes. The ancillary control qubit serves as a quantum switch that continuously interpolates between IFM and DC behavior, revealing a common operational origin for both phenomena. We demonstrate that both the phenomena can be realized within this framework through controlled quantum-gate operations. The analysis shows that the framework enables a continuous transition between the particle-like and wave-like behavior in DC setup. The framework is shown to be consistent with standard quantum mechanics, preserving unitary evolution, quantum superposition and the measurement postulate.

quant-ph↗

arXiv2026

On the generic structures of the protocols for quantum auction and quantum summation and their relation

Secure multi-party computation (SMC) addresses the problem of jointly computing global functions of private inputs while revealing minimal information about individual data. Two prominent examples of SMC tasks are sealed-bid auction and secure multi-party summation. Existing schemes for quantum auction and quantum summation have largely been developed independently, motivated by distinct applications and employing different computational primitives. In this work, structural symmetries in existing protocols for quantum auction and quantum summation are identified. In particular, it is established that the core auction primitives including revenue estimation, maximum bid identification, and winner determination can be reduced to repeated invocations of a summation oracle acting on suitably defined indicator functions. Conversely, summation protocols can be naturally embedded as auxiliary subroutines within auction frameworks, establishing summation as a unifying primitive underlying a broad class of auction mechanisms. Further, computational, communication and memory costs of these reductions are analyzed and compared with some of the representative existing protocols. The analysis has revealed that the process of implementing summation tasks through currently known auction protocols leads to additional overhead associated with bid-space exploration and winner determination. The proposed framework is protocol-agnostic and applicable across diverse computational models, including gate-based and photonic implementations. Finally, a proof-of-concept experimental realization (numerical validation) of a two-bidder sealed-bid auction using IBM (optical quantum) hardware is demonstrated to establish that the claimed equivalence is not merely formal but experimentally verifiable with the available hardware.

quant-ph↗

arXiv2026

Finite key analysis of experimentally realized practical COW-QKD protocol

An experimental implementation of the Coherent One-Way Quantum Key Distribution (COW-QKD) protocol is reported under realistic conditions, and a clean and easy-to-use framework for performing finite key analysis of the COW-QKD protocol is provided by extending a set of existing results. The framework provided here is used to perform finite key rate analysis of the COW-QKD protocol with respect to the actual parameters used in the experimental realization reported here. The system is kept running for several hours with different experimental parameters and stable secure key rates between 1.2 to 1.6 kbps are observed. In addition, QBER, phase error rate and secure key rate are obtained under finite key analysis, and it is shown that COW-QKD is secure for medium-range transmissions (up-to ~ 156 (171) km of optical fiber with 0.2 dB loss per km if detector efficiency is 0.1 (0.2) and other parameters are same as those used in this experiment).

quant-ph↗

arXiv2026

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs

Real-time multimodal auto-completion is essential for digital assistants, chatbots, design tools, and healthcare consultations, where user inputs rely on shared visual context. We introduce Multimodal Auto-Completion (MAC), a task that predicts upcoming characters in live chats using partially typed text and visual cues. Unlike traditional text-only auto-completion (TAC), MAC grounds predictions in multimodal context to better capture user intent. To enable this task, we adapt MMDialog and ImageChat to create benchmark datasets. We evaluate leading vision-language models (VLMs) against strong textual baselines, highlighting trade-offs in accuracy and efficiency. We present Router-Suggest, a router framework that dynamically selects between textual models and VLMs based on dialog context, along with a lightweight variant for resource-constrained environments. Router-Suggest achieves a 2.3x to 10x speedup over the best-performing VLM. A user study shows that VLMs significantly excel over textual models on user satisfaction, notably saving user typing effort and improving the quality of completions in multi-turn conversations. These findings underscore the need for multimodal context in auto-completions, leading to smarter, user-aware assistants.

cs.CL↗

arXiv2025

Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps

Photographs of people taken by professional photographers typically present the person in beautiful lighting, with an interesting pose, and flattering quality. This is unlike common photos people take of themselves in uncontrolled conditions. In this paper, we explore how to canonicalize a person's 'in-the-wild' photograph into a controllable, high-fidelity avatar -- reposed in a simple environment with standardized minimal clothing. A key challenge is preserving the person's unique whole-body identity, facial features, and body shape while stripping away the complex occlusions of their original garments. While a large paired dataset of the same person in varied clothing and poses would simplify this, such data does not exist. To that end, we propose two key insights: 1) Our method transforms the input photo into a canonical full-body UV space, which we couple with a novel reposing methodology to model occlusions and synthesize novel views. Operating in UV space allows us to decouple pose from appearance and leverage massive unpaired datasets. 2) We personalize the output photo via multi-image finetuning to ensure robust identity preservation under extreme pose changes. Our approach yields high-quality, reposed portraits that achieve strong quantitative performance on real-world imagery, providing an ideal, clean biometric canvas that significantly improves the fidelity of downstream applications like Virtual Try-On (VTO).

cs.CV↗

arXiv2025

VIDMP3: Video Editing by Representing Motion with Pose and Position Priors

Motion-preserved video editing is crucial for creators, particularly in scenarios that demand flexibility in both the structure and semantics of swapped objects. Despite its potential, this area remains underexplored. Existing diffusion-based editing methods excel in structure-preserving tasks, using dense guidance signals to ensure content integrity. While some recent methods attempt to address structure-variable editing, they often suffer from issues such as temporal inconsistency, subject identity drift, and the need for human intervention. To address these challenges, we introduce VidMP3, a novel approach that leverages pose and position priors to learn a generalized motion representation from source videos. Our method enables the generation of new videos that maintain the original motion while allowing for structural and semantic flexibility. Both qualitative and quantitative evaluations demonstrate the superiority of our approach over existing methods. The code will be made publicly available at https://github.com/sandeep-sm/VidMP3.

cs.CV↗

arXiv2025

Frequency drift corrected ultra-stable laser through phase-coherent fiber producing a quantum channel

Phase coherent fibers (PCF) are essential to distribute nearly monochromatic photons, ultra-stable in their frequency and phases, which have demanding requirements for state-of-the-art networked experiments, quantum as well as very high-speed communications. We report the development of a novel system that produces PCF links, also actively corrects the unavoidable slow frequency drift of the source laser. The PCF follows white phase noise limited $\sigma_o \times \tau^{-1}$ stability behavior having $\sigma_o$ values $1.9(2) \times 10^{-16}$ and $2.6(1) \times 10^{-16}$ for a 3.3 km field-deployed and 71 km spool fibers, respectively, with up to 47.5 dB suppression of the phase noise compared to a normal fiber. Additionally, the system is featured to correct the source laser's 33.8 mHz/s frequency drift to as low as $\simeq 0.05$ mHz/s. Therefore, this all-in-one solution producing a quantum link can potentially enhance the effectiveness of the twin field quantum key distribution (TF-QKD) by nearly a 73-fold reduction of the QBER that arises from using unstabilized fiber links, as well as relaxes the laser frequency drift correction constraints by severalfold.

quant-ph↗

arXiv2025

Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems

Ghosting, the ability to predict a user's intended text input for inline query auto-completion, is an invaluable feature for modern search engines and chat interfaces, greatly enhancing user experience. By suggesting completions to incomplete queries (or prefixes), ghosting aids users with slow typing speeds, disabilities, or limited language proficiency. Ghosting is a challenging problem and has become more important with the ubiquitousness of chat-based systems like ChatGPT, Copilot, etc. Despite the increasing prominence of chat-based systems utilizing ghosting, this challenging problem of Chat-Ghosting has received little attention from the NLP/ML research community. There is a lack of standardized benchmarks and relative performance analysis of deep learning and non-deep learning methods. We address this through an open and thorough study of this problem using four publicly available dialog datasets: two human-human (DailyDialog and DSTC7-Ubuntu) and two human-bot (Open Assistant and ShareGPT). We experiment with various existing query auto-completion methods (using tries), n-gram methods and deep learning methods, with and without dialog context. We also propose a novel entropy-based dynamic early stopping strategy. Our analysis finds that statistical n-gram models and tries outperform deep learning based models in terms of both model performance and inference efficiency for seen prefixes. For unseen queries, neural models like T5 and Phi-2 lead to better results. Adding conversational context leads to significant improvements in ghosting quality, especially for Open-Assistant and ShareGPT. We make code and data publicly available

cs.CL↗

arXiv2024

Quantum Teleportation using Quantum Candies

Quantum Candies or Qandies provide us with a lucid way of understanding the concepts of quantum information and quantum science in the language of candies. The critical idea of qandies is intuitively depicting quantum science to the general public, making sense as most of the research in this domain is funded by the taxpayers. The qandies model is already used to explain the essential concepts of quantum science and quantum cryptography. However, teleportation and related concepts are yet to be explained. Motivated by this fact, we investigate and extend the idea of Jacobs and Lin-Mor-Shapira to explain teleportation using qandies. Here, we explicitly design the teleportation protocol and perform a circuit model using qandy gates. The protocol is successful when the correlated qandies are appropriately pre-shared and use of some local operations at both ends. The model we develop can be a valuable tool for science and engineering educators who want to help the general public to gain more insights into quantum science and technology.

physics.pop-ph↗

arXiv2024

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals

3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method generates 3D animals that are not possible to create using previous text-to-3D generative methods. Additionally, our method is capable of preserving anatomic consistency in the generated animals, an area where prior text-to-3D approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly found animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Turntable results and code are released at https://youdream3d.github.io/

cs.CV↗

arXiv2024

C3DAG: Controlled 3D Animal Generation using 3D pose guidance

Recent advancements in text-to-3D generation have demonstrated the ability to generate high quality 3D assets. However while generating animals these methods underperform, often portraying inaccurate anatomy and geometry. Towards ameliorating this defect, we present C3DAG, a novel pose-Controlled text-to-3D Animal Generation framework which generates a high quality 3D animal consistent with a given pose. We also introduce an automatic 3D shape creator tool, that allows dynamic pose generation and modification via a web-based tool, and that generates a 3D balloon animal using simple geometries. A NeRF is then initialized using this 3D shape using depth-controlled SDS. In the next stage, the pre-trained NeRF is fine-tuned using quadruped-pose-controlled SDS. The pipeline that we have developed not only produces geometrically and anatomically consistent results, but also renders highly controlled 3D animals, unlike prior methods which do not allow fine-grained pose control.

cs.CV↗

arXiv2024

NTIRE 2024 Quality Assessment of AI-Generated Content Challenge

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.

cs.CV↗

arXiv2024

Subjective and Objective Analysis of Indian Social Media Video Quality

We conducted a large-scale subjective study of the perceptual quality of User-Generated Mobile Video Content on a set of mobile-originated videos obtained from the Indian social media platform ShareChat. The content viewed by volunteer human subjects under controlled laboratory conditions has the benefit of culturally diversifying the existing corpus of User-Generated Content (UGC) video quality datasets. There is a great need for large and diverse UGC-VQA datasets, given the explosive global growth of the visual internet and social media platforms. This is particularly true in regard to videos obtained by smartphones, especially in rapidly emerging economies like India. ShareChat provides a safe and cultural community oriented space for users to generate and share content in their preferred Indian languages and dialects. Our subjective quality study, which is based on this data, offers a boost of cultural, visual, and language diversification to the video quality research community. We expect that this new data resource will also allow for the development of systems that can predict the perceived visual quality of Indian social media videos, to control scaling and compression protocols for streaming, provide better user recommendations, and guide content analysis and processing. We demonstrate the value of the new data resource by conducting a study of leading blind video quality models on it, including a new model, called MoEVA, which deploys a mixture of experts to predict video quality. Both the new LIVE-ShareChat dataset and sample source code for MoEVA are being made freely available to the research community at https://github.com/sandeep-sm/LIVE-SC

eess.IV↗

arXiv2023

Experimental implementation of distributed phase reference quantum key distribution protocols

Quantum cryptography is now considered as a promising technology due to its promise of unconditional security. In recent years, rigorous work is being done for the experimental realization of quantum key distribution (QKD) protocols to realize secure networks. Among various QKD protocols, coherent one way and differential phase shift QKD protocols have undergone rapid experimental developments due to the ease of experimental implementations with the present available technology. In this work, we have experimentally realized optical fiber based coherent one way and differential phase shift QKD protocols at telecom wavelength. Both protocols belong to a class of protocols named as distributed phase reference protocol in which weak coherent pulses are used to encode the information. Further, we have analyzed the key rates with respect to different parameters such distance, disclose rate, compression ratio and detector dead time.

quant-ph↗

arXiv2023

A Comprehensive Review of Quantum Random Number Generators: Concepts, Classification and the Origin of Randomness

Random numbers are central to cryptography and various other tasks. The intrinsic probabilistic nature of quantum mechanics has allowed us to construct a large number of quantum random number generators (QRNGs) that are distinct from the traditional true number generators. This article provides a review of the existing QRNGs with a focus on their various possible features (e.g., device independence, semi-device independence) that are not achievable in the classical world. It also discusses the origin, applicability, and other facets of randomness. Specifically, the origin of randomness is explored from the perspective of a set of hierarchical axioms for quantum mechanics, implying that succeeding axioms can be regarded as a superstructure constructed on top of a structure built by the preceding axioms. The axioms considered are: (Q1) incompatibility and uncertainty; (Q2) contextuality; (Q3) entanglement; (Q4) nonlocality and (Q5) indistinguishability of identical particles. Relevant toy generalized probability theories (GPTs) are introduced, and it is shown that the origin of random numbers in different types of QRNGs known today are associated with different layers of nonclassical theories and all of them do not require all the features of quantum mechanics. Further, classification of the available QRNGs has been done and the technological challenges associated with each class are critically analyzed. Commercially available QRNGs are also compared.

quant-ph↗

arXiv2023

Partial Loopholes Free Device Independent Quantum Random Number Generator Using IBM's Quantum Computers

Random numbers form an intrinsic part of modern day computing with applications in a wide variety of fields. But due to their limitations, the use of pseudo random number generators (PRNGs) is certainly not desirable for sensitive applications. Quantum systems due to their intrinsic randomness form a suitable candidate for generation of true random numbers that can also be certified. In this work, the violation of CHSH inequality has been used to propose a scheme by which one can generate device independent quantum random numbers by use of IBM quantum computers that are available on the cloud. The generated random numbers have been tested for their source of origin through experiments based on the testing of CHSH inequality through available IBM quantum computers. The performance of each quantum computer against the CHSH test has been plotted and characterized. Further, efforts have been made to close as many loopholes as possible to produce device independent quantum random number generators. This study will provide new directions for the development of self-testing and semi-self-testing random number generators using quantum computers.

quant-ph↗

arXiv2023

Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild

Automatic Perceptual Image Quality Assessment is a challenging problem that impacts billions of internet, and social media users daily. To advance research in this field, we propose a Mixture of Experts approach to train two separate encoders to learn high-level content and low-level image quality features in an unsupervised setting. The unique novelty of our approach is its ability to generate low-level representations of image quality that are complementary to high-level features representing image content. We refer to the framework used to train the two encoders as Re-IQA. For Image Quality Assessment in the Wild, we deploy the complementary low and high-level image representations obtained from the Re-IQA framework to train a linear regression model, which is used to map the image representations to the ground truth quality scores, refer Figure 1. Our method achieves state-of-the-art performance on multiple large-scale image quality assessment databases containing both real and synthetic distortions, demonstrating how deep neural networks can be trained in an unsupervised setting to produce perceptually relevant representations. We conclude from our experiments that the low and high-level features obtained are indeed complementary and positively impact the performance of the linear regressor. A public release of all the codes associated with this work will be made available on GitHub.

cs.CV↗

arXiv2022

Open quantum system dynamics of $X$-states: Entanglement sudden death and sudden birth

The origin of disentanglement for two specific sub-classes of $X$-states namely maximally nonlocal mixed states (MNMSs) and maximally entangled mixed states (MEMSs) is investigated analytically for a physical system consisting of two spatially separated qubits interacting with a common vacuum bath. The phenomena of entanglement sudden death (ESD) and the entanglement sudden birth (ESB) are observed, but the characteristics of ESD and ESB are found to be different for the case of two photon coherence and single photon coherence states. The role played by initial coherence for the underlying entanglement dynamics is investigated. Further, the entanglement dynamics of MNMSs and MEMSs under different environmental noises namely phase damping, amplitude damping and RTN noise with respect to the decay and revival of entanglement is analyzed. It's observed that the single photon coherence states are more robust against the sudden death of entanglement indicating the usability of such states in the development of technologies for the practical implementation of quantum information processing tasks.

quant-ph↗