arXiv subjects

Sakshi Agarwal

Publications and source records attributed to Sakshi Agarwal.

5 recordsLinked to original sources

arXiv2026

On-the-Fly Machine-Learned Force Fields for High-Fidelity Polymer Glass Transition Simulations

Predicting polymer glass transition temperatures (Tg) with first-principles fidelity has long remained out of reach, as cooling multi-thousand-atom systems over a broad temperature range at acceptable rates exceeds the computational limits of ab initio molecular dynamics (AIMD). Here we employ a hybrid scheme that merges AIMD with accelerated on-the-fly (OTF) machine-learned force-field (MLFF) construction, enabling Tg prediction at quantum-mechanical accuracy with near-classical computational cost. The OTF protocol to construct MLFFs adaptively triggers first-principles calculations only when newly encountered configurations lie outside the current model's domain of confidence, allowing robust, parameter-free MLFFs to be built from merely 1000 AIMD-sampled configurations per polymer. These MLFFs are then utilized to perform long-time cooling simulations on amorphous supercells containing several thousand atoms. Applied across twelve polymers spanning aromatic, aliphatic, heteroatomic, and branched chemistries, the method yields predictions in excellent accord with experiment while reducing computational cost by approximately six orders of magnitude relative to AIMD. This work establishes a new paradigm for predictive polymer modeling, demonstrating that OTF-MLFFs provide a generalizable, accurate, and scalable route to simulating the thermophysical behavior of complex disordered materials at near quantum-mechanical fidelity.

cond-mat.mtrl-sci↗

arXiv2026

VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference

Diffusion probabilistic models learn to remove noise added during training, generating novel data (e.g., images) from Gaussian noise through sequential denoising. However, conditioning the generative process on corrupted or masked images is challenging. While various methods have been proposed for inpainting masked images with diffusion priors, they often fail to produce samples from the true conditional distribution, especially for large masked regions. Many baselines also cannot be applied to latent diffusion models which generate high-quality images with much lower computational cost. We propose a hierarchical variational inference algorithm that optimizes a non-Gaussian Markov approximation of the true diffusion posterior. Our VIPaint method outperforms existing approaches to inpainting, producing diverse high-quality imputations even for state-of-the-art text-conditioned latent diffusion models, and is also effective for other inverse problems like deblurring and superresolution.

cs.CV↗

arXiv2026

Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models

Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs) offer rich scene understanding, they struggle with reliable spatial grounding - often producing hallucinated or geometrically invalid bounding boxes when asked to localize objects. We propose VANGUARD (Video Anomaly Understanding through Reasoning and Grounding), a framework that unifies anomaly classification, spatial grounding, and chain-of-thought reasoning within a single VLM. VANGUARD introduces a three-stage curriculum that progressively layers training objectives: (1) classifier warmup on frozen backbone features, (2) LoRA-adapted spatial grounding, and (3) chain-of-thought generation. To overcome the sparse annotation typical of VAD benchmarks, we employ a teacher-student annotation pipeline in which a VLM (Qwen3-VL-4B) generates structured per-subclip reasoning trajectories based on manual annotations available from the UCA Dataset. Further, GroundingDINO provides bounding box supervision. On UCF-Crime, VANGUARD achieves 94% ROC-AUC with 84% F1 while simultaneously producing interpretable chain-of-thought explanations and spatial grounding of anomalous objects - capabilities absent from prior VAD methods. Ablations confirm that staged training outperforms monolithic optimization, and that structured reasoning acts as an implicit regularizer yielding more balanced predictions than classification-only fine-tuning. Zero-shot transfer to XD-Violence and ShanghaiTech demonstrates cross-domain generalization without target-domain adaptation.

cs.CV↗

arXiv2025

polyRETRO: a Language Model Approach to predict Polymerization Class and Monomer(s) for a Target Polymer

While machine learning has transformed polymer design by enabling rapid property prediction and candidate generation, translating these designs into experimentally realizable materials remains a critical challenge. Traditionally, the synthesis of target polymers has relied heavily on expert intuition and prior experience. The lack of automated retrosynthetic tools to assist chemists, limit the rapid practical impact of data-driven polymer discovery. To expedite lab-scale validation and beyond, we present a retrosynthetic framework that leverages large language models (LLMs) to guide polymer synthesis. Our approach, which we call polyRETRO, involves two key steps: 1) predicting the most likely polymerization reaction class of a target polymer and 2) identifying the underlying chemical transformation templates and the corresponding monomers, using primarily natural-language based constructs. This LLM-driven framework enables direct retrosynthetic analysis given just the target polymer SMILES string. polyRETRO constitutes a initial step towards a scalable, interpretable, and generalizable approach to bridge the gap between computational design and experimental synthesis.

cond-mat.soft↗

arXiv2019

Limits of Deepfake Detection: A Robust Estimation Viewpoint

Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated. A robust statistics view of GANs is considered to bound the error probability for various GAN implementations in terms of their performance. The bounds are further simplified using a Euclidean approximation for the low error regime. Lastly, relationships between error probability and epidemic thresholds for spreading processes in networks are established.

cs.LG↗