arXiv subjects

Mukesh Singhal

Publications and source records attributed to Mukesh Singhal.

11 recordsLinked to original sources

arXiv2026

CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation

Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions. Together, these elements demand a level of fine-grained control beyond current text-to-video models. Existing work addresses each axis in isolation: multi-subject personalization, temporal control, multi-shot synthesis, or camera control; no prior framework jointly integrates all four. We present CineOrchestra, a unified video diffusion model that controls subjects, events, cameras, and shot transitions simultaneously. Our key insight is that these heterogeneous cinematic elements share a fundamental structure: each is an entity acting over a specific temporal interval, which can therefore all be expressed through one shared structure of entity-centric conditioning primitives, augmented with reference images for visual entities. This formulation reduces the architectural challenge to a single positional encoding problem, which we solve with two parameter-free coordinated rotary embeddings: (a) an interval-sampled temporal RoPE that yields consistent attention behavior across events of dramatically varying duration, and (b) a 2D entity-temporal cross-attention RoPE that disambiguates per-entity conditions and routes each to its corresponding spatiotemporal region. On two new benchmarks, CineOrchestra outperforms six per-axis specialists on dense caption following and shot-transition timing, with consistent gains in a pairwise user study and component ablations. Project page: https://snap-research.github.io/CineOrchestra

cs.CV↗

arXiv2026

A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models

We survey continuous-time generative modeling methods based on transporting a simple reference distribution to a data distribution via stochastic or deterministic dynamics. We present a unified framework in which diffusion models, score-based generative models, and flow matching are instances of learning a time-dependent vector field that induces a family of marginals $(\rho_t)_{t \in [0,1]}$ governed by continuity and Fokker-Planck equations. Such a unified theory is timely because these methods are converging methodologically, yet fragmented notation and competing derivations continue to obscure their shared structure and the practical tradeoffs governing sampling, stability, and computation. Within this framework, we (i) derive reverse-time sampling for diffusion and score-based models as controlled stochastic dynamics, (ii) show that the probability flow ODE yields identical marginals and connects diffusion to likelihood-based normalizing flows, and (iii) interpret flow matching as direct regression of the velocity field under a chosen interpolation, clarifying when it coincides with or differs from score-based training. We compare objectives, sampling schemes, and discretization errors under unified notation, discuss connections to Schrodinger bridges and entropic optimal transport, and summarize theoretical guarantees and open problems on approximation, stability, and scalability.

cs.LG↗

arXiv2025

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer

cs.CV↗

arXiv2025

Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization

Stochastic gradient descent and other first-order variants, such as Adam and AdaGrad, are commonly used in the field of deep learning due to their computational efficiency and low-storage memory requirements. However, these methods do not exploit curvature information. Consequently, iterates can converge to saddle points or poor local minima. On the other hand, Quasi-Newton methods compute Hessian approximations which exploit this information with a comparable computational budget. Quasi-Newton methods re-use previously computed iterates and gradients to compute a low-rank structured update. The most widely used quasi-Newton update is the L-BFGS, which guarantees a positive semi-definite Hessian approximation, making it suitable in a line search setting. However, the loss functions in DNNs are non-convex, where the Hessian is potentially non-positive definite. In this paper, we propose using a limited-memory symmetric rank-one quasi-Newton approach which allows for indefinite Hessian approximations, enabling directions of negative curvature to be exploited. Furthermore, we use a modified adaptive regularized cubics approach, which generates a sequence of cubic subproblems that have closed-form solutions with suitable regularization choices. We investigate the performance of our proposed method on autoencoders and feed-forward neural network models and compare our approach to state-of-the-art first-order adaptive stochastic methods as well as other quasi-Newton methods.x

math.OC↗

arXiv2024

A Committee Based Optimal Asynchronous Byzantine Agreement Protocol W.P. 1

Multi-valued Byzantine agreement (MVBA) protocols are essential for atomic broadcast and fault-tolerant state machine replication in asynchronous networks. Despite advances, challenges persist in optimizing these protocols for communication and computation efficiency. This paper presents a committee-based MVBA protocol (cMVBA), a novel approach that achieves agreement without extra communication rounds by analyzing message patterns in asynchronous networks with probability 1.

cs.DC↗

arXiv2024

Slim-ABC: An Optimized Atomic Broadcast Protocol

The Byzantine Agreement (BA) problem is a fundamental challenge in distributed systems, focusing on achieving reaching an agreement among parties, some of which may behave maliciously. With the rise of cryptocurrencies, there has been significant interest in developing atomic broadcast protocols, which facilitate agreement on a subset of parties' requests. However, these protocols often come with high communication complexity ($O(ln^2 + \lambda n^3 \log n)$, where $l$ is the bit length of the input, $n$ is the number of parties, and $\lambda$ represents the security parameter bit length). This can lead to inefficiency, especially when the requests across parties exhibit little variation, resulting in unnecessary resource consumption. In this paper, we introduce Slim-ABC, a novel atomic broadcast protocol that eliminates the $O(ln^2 + \lambda n^3 \log n)$ term associated with traditional atomic broadcast protocols. While Slim-ABC reduces the number of accepted requests, it significantly mitigates resource wastage, making it more efficient. The protocol leverages the asynchronous common subset and provable-broadcast mechanisms to achieve a communication complexity of $O(ln^2 + \lambda n^2)$. Despite the trade-off in accepted requests, Slim-ABC maintains robust security by allowing only a fraction ($f+1$) of parties to broadcast requests. We present an extensive efficiency analysis of Slim-ABC, evaluating its performance across key metrics such as message complexity, communication complexity, and time complexity. Additionally, we provide a rigorous security analysis, demonstrating that Slim-ABC satisfies the \textit{agreement}, \textit{validity}, and \textit{totality} properties of the asynchronous common subset protocol.

cs.DC↗

arXiv2024

VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise

Deep Neural Networks (DNN) have become a promising paradigm when developing Artificial Intelligence (AI) and Machine Learning (ML) applications. However, DNN applications are vulnerable to fake data that are crafted with adversarial attack algorithms. Under adversarial attacks, the prediction accuracy of DNN applications suffers, making them unreliable. In order to defend against adversarial attacks, we introduce a novel noise-reduction procedure, Vector Quantization U-Net (VQUNet), to reduce adversarial noise and reconstruct data with high fidelity. VQUNet features a discrete latent representation learning through a multi-scale hierarchical structure for both noise reduction and data reconstruction. The empirical experiments show that the proposed VQUNet provides better robustness to the target DNN models, and it outperforms other state-of-the-art noise-reduction-based defense methods under various adversarial attacks for both Fashion-MNIST and CIFAR10 datasets. When there is no adversarial attack, the defense method has less than 1% accuracy degradation for both datasets.

cs.CV↗

arXiv2021

Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques that are only applicable to specific machine learning models. Additionally, the existing data poisoning attacks in the literature are limited to either binary classifiers or to gradient-based algorithms. To address these limitations, this paper first proposes a novel model-free label-flipping attack based on the multi-modality of the data, in which the adversary targets the clusters of classes while constrained by a label-flipping budget. The complexity of our proposed attack algorithm is linear in time over the size of the dataset. Also, the proposed attack can increase the error up to two times for the same attack budget. Second, a novel defense technique based on the Synthetic Reduced Nearest Neighbor (SRNN) model is proposed. The defense technique can detect and exclude flipped samples on the fly during the training procedure. Through extensive experimental analysis, we demonstrate that (i) the proposed attack technique can deteriorate the accuracy of several models drastically, and (ii) under the proposed attack, the proposed defense technique significantly outperforms other conventional machine learning models in recovering the accuracy of the targeted model.

cs.LG↗

arXiv2018

Joint Failure Recovery, Fault Prevention, and Energy-efficient Resource Management for Real-time SFC in Fog-supported SDN

In this paper, we focus on the problems of traffic engineering, failure recovery, fault prevention, and Service Function Chain (SFC) with reliability and energy consumption constraints in Software Defined Networks (SDN). These types of deployments use Fog computing as an emerging paradigm to manage the distributed small-size traffic flows passing through the SDN-enabled switches (possibly Fog Nodes). The main aim of this integration is to support service delivery in real-time, failure recovery, and fault-awareness in an SFC context. Firstly, we present an architecture for Failure Recovery and Fault Prevention called FRFP; this is a multi-tier structure in which the real-time traffic flows pass through SDN-enabled switches to jointly decrease the network side-effects of flow rerouting and energy consumption of the Fog Nodes. We then mathematically formulate an optimization problem called the Optimal Fog-Supported Energy-Aware SFC rerouting algorithm (OFES) and propose a near-optimal heuristic called Heuristic OFES (HFES) to solve the corresponding problem in polynomial time. In this way, the energy consumption and the reliability of the selected paths are optimized, while the Quality of Service constraints are met and the network congestion is minimized. In a reliability context, the focus of this work is on fault prevention; however, since we use a reallocation technique, the proposed scheme can be used as a failure recovery scheme. We compare the performance of HFES and OFES in terms of power consumption, average path length, fault probability, network side-effects, link utilization, and Fog Node utilization. Additionally, we analyze the computational complexity of HFES. We use a real-world network topology to evaluate our algorithm. The simulation results show that the heuristic algorithm is applicable to large-scale networks.

cs.DC↗

arXiv2018

Learning from Richer Human Guidance: Augmenting Comparison-Based Learning with Feature Queries

We focus on learning the desired objective function for a robot. Although trajectory demonstrations can be very informative of the desired objective, they can also be difficult for users to provide. Answers to comparison queries, asking which of two trajectories is preferable, are much easier for users, and have emerged as an effective alternative. Unfortunately, comparisons are far less informative. We propose that there is much richer information that users can easily provide and that robots ought to leverage. We focus on augmenting comparisons with feature queries, and introduce a unified formalism for treating all answers as observations about the true desired reward. We derive an active query selection algorithm, and test these queries in simulation and on real users. We find that richer, feature-augmented queries can extract more information faster, leading to robots that better match user preferences in their behavior.

cs.AI↗

arXiv2016

GraphPrints: Towards a Graph Analytic Method for Network Anomaly Detection

This paper introduces a novel graph-analytic approach for detecting anomalies in network flow data called GraphPrints. Building on foundational network-mining techniques, our method represents time slices of traffic as a graph, then counts graphlets -- small induced subgraphs that describe local topology. By performing outlier detection on the sequence of graphlet counts, anomalous intervals of traffic are identified, and furthermore, individual IPs experiencing abnormal behavior are singled-out. Initial testing of GraphPrints is performed on real network data with an implanted anomaly. Evaluation shows false positive rates bounded by 2.84% at the time-interval level, and 0.05% at the IP-level with 100% true positive rates at both.

cs.CR↗