arXiv subjects

Md Ashiqur Rahman

Publications and source records attributed to Md Ashiqur Rahman.

At least 19 recordsLinked to original sources

arXiv2026

SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation

Vision-Language-Action (VLA) models are a class of generalist robot policies that map camera images and language instructions directly to robot actions. While promising, these models remain slow at test time, particularly for long-horizon tasks that require many queries to the policy. Recent efforts reduce VLA latency by distilling smaller models, overlapping asynchronous action chunks, or pairing the VLA with a fast low-level policy, but still run a learned policy for the entire task. In contrast to VLA, classical motion planners quickly find collision-free motions, but require an explicit goal and have no semantic understanding of the task. In this work, we present SkipVLA, a hybrid policy that combines a pretrained VLA with a classical motion planner, using the planner for free-space motion and querying the VLA only for contact-rich skills such as grasping and placing. SkipVLA reuses the frozen vision-language backbone of the VLA to predict a target pose for each planned motion, and learns this predictor without additional demonstrations introduced into the system by using what was already learnt by the large VLA. We evaluate SkipVLA with three VLAs on 13 LIBERO tasks in simulation and three pick-and-place tasks on a physical 6-DoF YAM arm, demonstrating up to 2.5x faster task completion and significantly lower energy consumption while achieving the same task success rate.

cs.RO↗

arXiv2026

Neural Operator: Is data all you need to model the world? An insight into the paradigm of data-driven scientific ML

Numerical approximations of partial differential equations (PDEs) are routinely employed to formulate the solution of physics, engineering, and mathematical problems involving functions of several variables, such as the propagation of heat or sound, fluid flow, elasticity, electrostatics, electrodynamics, and more. While this has led to solving many complex phenomena, there are some limitations. Conventional approaches such as Finite Element Methods (FEMs) and Finite Difference Methods (FDMs) require considerable time and are computationally expensive. In contrast, data-driven machine learning-based methods, such as neural networks, provide a faster, fairly accurate alternative, and, in particular, focus on neural operators, which have certain advantages such as discretization invariance and resolution invariance. This article aims to provide a comprehensive insight into how data-driven approaches can complement conventional techniques to solve engineering and physics problems, while also noting some of the open problems of machine learning-based approaches. We will note how these new computational approaches can bring immense advantages in tackling many problems in fundamental and applied physics.

cs.AI↗

arXiv2026

Tunable Soft Equivariance with Guarantees

Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely satisfied in real-world data, which can limit a model's performance. Controlling the degree of equivariance is therefore desirable. We propose a general framework for constructing soft equivariant models by projecting the model weights into a designed subspace. The method applies to any pre-trained architecture and provides theoretical bounds on the induced equivariance error. Empirically, we demonstrate the effectiveness of our method on multiple pre-trained backbones, including ViT and ResNet, across image classification, semantic segmentation, and human-trajectory prediction tasks. Notably, our approach improves the performance while simultaneously reducing equivariance error on the competitive ImageNet benchmark.

cs.CV↗

arXiv2025

A Two-Stage Stochastic Optimization Framework for Environmentally Sensitive Oil Spill Response Resource Allocation in the Arctic

The risk of oil spills in the Alaskan Arctic has become an urgent environmental and logistical concern as maritime traffic increases under climate driven sea ice retreat. Traditional deterministic response planning models fail to represent key uncertainties, including variable spill magnitudes, changing environmental sensitivity, and infrastructure limitations. This study develops a two-stage stochastic mixed integer linear programming framework that jointly optimizes the location of oil spill response stations and the allocation of heterogeneous resources across multiple probabilistic spill scenarios. The model integrates a weighted objective that combines spill volume, environmental sensitivity index (ESI), response time, and costs for station setup, deployment, and inter station transfer. Separate importance weights for coverage and cost, together with internal ecological weights, allow decision makers to balance ecological protection and operational efficiency. Data was compiled from Alaska Department of Environmental Conservation spill records and National Oceanic and Atmospheric Administration ESI layers and are converted into model ready scenarios through harmonization and sampling. The model is solved with the Gurobi optimizer, and sensitivity analysis is performed over 324 combinations of importance and ecological weights. Results show about a 35.45% percent improvement in response effectiveness over deterministic methods, as confirmed by the value of the stochastic solution, and reveal clear tradeoffs between cost and ecological coverage. The framework provides a data driven decision support tool for Arctic emergency planners that simultaneously accounts for uncertainty, environmental sensitivity, and realistic logistical constraints.

math.OC↗

arXiv2025

Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

Scale variation is a fundamental challenge in computer vision. Objects of the same class can have different sizes, and their perceived size is further affected by the distance from the camera. These variations are local to the objects, i.e., different object sizes may change differently within the same image. To effectively handle scale variations, we present a deep equilibrium canonicalizer (DEC) to improve the local scale equivariance of a model. DEC can be easily incorporated into existing network architectures and can be adapted to a pre-trained model. Notably, we show that on the competitive ImageNet benchmark, DEC improves both model performance and local scale consistency across four popular pre-trained deep-nets, e.g., ViT, DeiT, Swin, and BEiT. Our code is available at https://github.com/ashiq24/local-scale-equivariance.

cs.CV↗

arXiv2025

CLIPSym: Delving into Symmetry Detection with CLIP

Symmetry is one of the most fundamental geometric cues in computer vision, and detecting it has been an ongoing challenge. With the recent advances in vision-language models,~i.e., CLIP, we investigate whether a pre-trained CLIP model can aid symmetry detection by leveraging the additional symmetry cues found in the natural image descriptions. We propose CLIPSym, which leverages CLIP's image and language encoders and a rotation-equivariant decoder based on a hybrid of Transformer and $G$-Convolution to detect rotation and reflection symmetries. To fully utilize CLIP's language encoder, we have developed a novel prompting technique called Semantic-Aware Prompt Grouping (SAPG), which aggregates a diverse set of frequent object-based prompts to better integrate the semantic cues for symmetry detection. Empirically, we show that CLIPSym outperforms the current state-of-the-art on three standard symmetry detection datasets (DENDI, SDRW, and LDRS). Finally, we conduct detailed ablations verifying the benefits of CLIP's pre-training, the proposed equivariant decoder, and the SAPG technique. The code is available at https://github.com/timyoung2333/CLIPSym.

cs.CV↗

arXiv2025

Group Downsampling with Equivariant Anti-aliasing

Downsampling layers are crucial building blocks in CNN architectures, which help to increase the receptive field for learning high-level features and reduce the amount of memory/computation in the model. In this work, we study the generalization of the uniform downsampling layer for group equivariant architectures, e.g., G-CNNs. That is, we aim to downsample signals (feature maps) on general finite groups with anti-aliasing. This involves the following: (a) Given a finite group and a downsampling rate, we present an algorithm to form a suitable choice of subgroup. (b) Given a group and a subgroup, we study the notion of bandlimited-ness and propose how to perform anti-aliasing. Notably, our method generalizes the notion of downsampling based on classical sampling theory. When the signal is on a cyclic group, i.e., periodic, our method recovers the standard downsampling of an ideal low-pass filter followed by a subsampling operation. Finally, we conducted experiments on image classification tasks demonstrating that the proposed downsampling operation improves accuracy, better preserves equivariance, and reduces model size when incorporated into G-equivariant networks

cs.LG↗

arXiv2025

HessianForge: Scalable LiDAR reconstruction with Physics-Informed Neural Representation and Smoothness Energy Constraints

Accurate and efficient 3D mapping of large-scale outdoor environments from LiDAR measurements is a fundamental challenge in robotics, particularly towards ensuring smooth and artifact-free surface reconstructions. Although the state-of-the-art methods focus on memory-efficient neural representations for high-fidelity surface generation, they often fail to produce artifact-free manifolds, with artifacts arising due to noisy and sparse inputs. To address this issue, we frame surface mapping as a physics-informed energy optimization problem, enforcing surface smoothness by optimizing an energy functional that penalizes sharp surface ridges. Specifically, we propose a deep learning based approach that learns the signed distance field (SDF) of the surface manifold from raw LiDAR point clouds using a physics-informed loss function that optimizes the $L_2$-Hessian energy of the surface. Our learning framework includes a hierarchical octree based input feature encoding and a multi-scale neural network to iteratively refine the signed distance field at different scales of resolution. Lastly, we introduce a test-time refinement strategy to correct topological inconsistencies and edge distortions that can arise in the generated mesh. We propose a \texttt{CUDA}-accelerated least-squares optimization that locally adjusts vertex positions to enforce feature-preserving smoothing. We evaluate our approach on large-scale outdoor datasets and demonstrate that our approach outperforms current state-of-the-art methods in terms of improved accuracy and smoothness. Our code is available at \href{https://github.com/HrishikeshVish/HessianForge/}{https://github.com/HrishikeshVish/HessianForge/}

cs.GR↗

arXiv2024

Molecular Dynamics Study of Liquid Condensation on Nano-structured Sinusoidal Hybrid Wetting Surfaces

Although real surfaces exhibit intricate topologies at the nanoscale, rough surface consideration is often overlooked in nanoscale heat transfer studies. Superimposed sinusoidal functions effectively model the complexity of these surfaces. This study investigates the impact of sinusoidal roughness on liquid argon condensation over a functional gradient wetting (FGW) surface with 84% hydrophilic content using molecular dynamics simulations. Argon atoms are confined between two platinum substrates: a flat lower substrate heated to 130K and a rough upper substrate at 90K. Key metrics of the nanoscale condensation process, such as nucleation, surface heat flux, and total energy per atom, are analyzed. Rough surfaces significantly enhance nucleation, nearly doubling cluster counts compared to smooth surfaces and achieving a more extended atomic density profile with a peak of approximately and improved heat flux. Stronger atom-surface interactions also lead to more efficient energy dissipation. These findings underscore the importance of surface roughness in optimizing condensation and heat transfer, offering a more accurate representation of surface textures and a basis for designing surfaces that achieve superior heat transfer performance.

cond-mat.mtrl-sci↗

arXiv2024

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs

Existing neural operator architectures face challenges when solving multiphysics problems with coupled partial differential equations (PDEs) due to complex geometries, interactions between physical variables, and the limited amounts of high-resolution training data. To address these issues, we propose Codomain Attention Neural Operator (CoDA-NO), which tokenizes functions along the codomain or channel space, enabling self-supervised learning or pretraining of multiple PDE systems. Specifically, we extend positional encoding, self-attention, and normalization layers to function spaces. CoDA-NO can learn representations of different PDE systems with a single model. We evaluate CoDA-NO's potential as a backbone for learning multiphysics PDEs over multiple systems by considering few-shot learning settings. On complex downstream tasks with limited data, such as fluid flow simulations, fluid-structure interactions, and Rayleigh-Bénard convection, we found CoDA-NO to outperform existing methods by over 36%.

cs.LG↗

arXiv2024

MosquitoFusion: A Multiclass Dataset for Real-Time Detection of Mosquitoes, Swarms, and Breeding Sites Using Deep Learning

In this paper, we present an integrated approach to real-time mosquito detection using our multiclass dataset (MosquitoFusion) containing 1204 diverse images and leverage cutting-edge technologies, specifically computer vision, to automate the identification of Mosquitoes, Swarms, and Breeding Sites. The pre-trained YOLOv8 model, trained on this dataset, achieved a mean Average Precision (mAP@50) of 57.1%, with precision at 73.4% and recall at 50.5%. The integration of Geographic Information Systems (GIS) further enriches the depth of our analysis, providing valuable insights into spatial patterns. The dataset and code are available at https://github.com/faiyazabdullah/MosquitoFusion.

cs.CV↗

arXiv2023

Truly Scale-Equivariant Deep Nets with Fourier Layers

In computer vision, models must be able to adapt to changes in image resolution to effectively carry out tasks such as image segmentation; This is known as scale-equivariance. Recent works have made progress in developing scale-equivariant convolutional neural networks, e.g., through weight-sharing and kernel resizing. However, these networks are not truly scale-equivariant in practice. Specifically, they do not consider anti-aliasing as they formulate the down-scaling operation in the continuous domain. To address this shortcoming, we directly formulate down-scaling in the discrete domain with consideration of anti-aliasing. We then propose a novel architecture based on Fourier layers to achieve truly scale-equivariant deep nets, i.e., absolute zero equivariance-error. Following prior works, we test this model on MNIST-scale and STL-10 datasets. Our proposed model achieves competitive classification performance while maintaining zero equivariance-error.

cs.LG↗

arXiv2023

U-NO: U-shaped Neural Operators

Neural operators generalize classical neural networks to maps between infinite-dimensional spaces, e.g., function spaces. Prior works on neural operators proposed a series of novel methods to learn such maps and demonstrated unprecedented success in learning solution operators of partial differential equations. Due to their close proximity to fully connected architectures, these models mainly suffer from high memory usage and are generally limited to shallow deep learning models. In this paper, we propose U-shaped Neural Operator (U-NO), a U-shaped memory enhanced architecture that allows for deeper neural operators. U-NOs exploit the problem structures in function predictions and demonstrate fast training, data efficiency, and robustness with respect to hyperparameters choices. We study the performance of U-NO on PDE benchmarks, namely, Darcy's flow law and the Navier-Stokes equations. We show that U-NO results in an average of 26% and 44% prediction improvement on Darcy's flow and turbulent Navier-Stokes equations, respectively, over the state of the art. On Navier-Stokes 3D spatiotemporal operator learning task, we show U-NO provides 37% improvement over the state of art methods.

cs.LG↗

arXiv2023

AdaFNIO: Adaptive Fourier Neural Interpolation Operator for video frame interpolation

We present, AdaFNIO - Adaptive Fourier Neural Interpolation Operator, a neural operator-based architecture to perform video frame interpolation. Current deep learning based methods rely on local convolutions for feature learning and suffer from not being scale-invariant, thus requiring training data to be augmented through random flipping and re-scaling. On the other hand, AdaFNIO, learns the features in the frames, independent of input resolution, through token mixing and global convolution in the Fourier space or the spectral domain by using Fast Fourier Transform (FFT). We show that AdaFNIO can produce visually smooth and accurate results. To evaluate the visual quality of our interpolated frames, we calculate the structural similarity index (SSIM) and Peak Signal to Noise Ratio (PSNR) between the generated frame and the ground truth frame. We provide the quantitative performance of our model on Vimeo-90K dataset, DAVIS, UCF101 and DISFA+ dataset.

cs.CV↗

arXiv2022

PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators

We address the problem of generating 3D human motions in dyadic activities. In contrast to the concurrent works, which mainly focus on generating the motion of a single actor from the textual description, we generate the motion of one of the actors from the motion of the other participating actor in the action. This is a particularly challenging, under-explored problem, that requires learning intricate relationships between the motion of two actors participating in an action and also identifying the action from the motion of one actor. To address these, we propose partner conditioned motion operator (PaCMO), a neural operator-based generative model which learns the distribution of human motion conditioned by the partner's motion in function spaces through adversarial training. Our model can handle long unlabeled action sequences at arbitrary time resolution. We also introduce the "Functional Frechet Inception Distance" ($F^2ID$) metric for capturing similarity between real and generated data for function spaces. We test PaCMO on NTU RGB+D and DuetDance datasets and our model produces realistic results evidenced by the $F^2ID$ score and the conducted user study.

cs.CV↗

arXiv2022

Generative Adversarial Neural Operators

We propose the generative adversarial neural operator (GANO), a generative model paradigm for learning probabilities on infinite-dimensional function spaces. The natural sciences and engineering are known to have many types of data that are sampled from infinite-dimensional function spaces, where classical finite-dimensional deep generative adversarial networks (GANs) may not be directly applicable. GANO generalizes the GAN framework and allows for the sampling of functions by learning push-forward operator maps in infinite-dimensional spaces. GANO consists of two main components, a generator neural operator and a discriminator neural functional. The inputs to the generator are samples of functions from a user-specified probability measure, e.g., Gaussian random field (GRF), and the generator outputs are synthetic data functions. The input to the discriminator is either a real or synthetic data function. In this work, we instantiate GANO using the Wasserstein criterion and show how the Wasserstein loss can be computed in infinite-dimensional spaces. We empirically study GANO in controlled cases where both input and output functions are samples from GRFs and compare its performance to the finite-dimensional counterpart GAN. We empirically study the efficacy of GANO on real-world function data of volcanic activities and show its superior performance over GAN.

cs.LG↗

arXiv2022

Applying Data Augmentation to Handwritten Arabic Numeral Recognition Using Deep Learning Neural Networks

Handwritten character recognition has been the center of research and a benchmark problem in the sector of pattern recognition and artificial intelligence, and it continues to be a challenging research topic. Due to its enormous application many works have been done in this field focusing on different languages. Arabic, being a diversified language has a huge scope of research with potential challenges. A convolutional neural network model for recognizing handwritten numerals in Arabic language is proposed in this paper, where the dataset is subject to various augmentation in order to add robustness needed for deep learning approach. The proposed method is empowered by the presence of dropout regularization to do away with the problem of data overfitting. Moreover, suitable change is introduced in activation function to overcome the problem of vanishing gradient. With these modifications, the proposed system achieves an accuracy of 99.4\% which performs better than every previous work on the dataset.

cs.CV↗

arXiv2021

BLEnD: Improving NDN Performance Over Wireless Links Using Interest Bundling

Named Data Networking (NDN) employs small-sized Interest packets to retrieve large-sized Data packets. Given the half-duplex nature of wireless links, Interest packets frequently contend for the channel with Data packets, leading to throughput degradation. In this work, we present a novel idea called BLEnD, an Interest-bundling technique that encodes multiple Interests into one at the sender and decodes at the receiver. The major design challenges are to reduce the number of Interest transmissions without impacting the one-Interest one-Data principle embedded everywhere in NDN architecture and implementation, and support flow/congestion control mechanisms that usually use Interest packets as signals. BLEnD achieves these by bundling/unbundling Interests at the link adaptation layer, keeping all NDN components unaware and unaffected. Over a one-hop WiFi link, BLEnD improves application throughput by 30%. It may also be used over multiple hops and be improved in a number of ways.

cs.NI↗