Searcharxiv⌕ Search

arXiv subjects

M. Salman Asif

Publications and source records attributed to M. Salman Asif.

At least 19 recordsLinked to original sources
arXiv2026

Provable and Robust Wavefront Sensing via Self-Reference Interferometry

Wavefront sensing involves estimating the phase and intensity of light, enabling a wide range of imaging applications, from adaptive optics and astronomy to biomedical imaging. Since conventional image sensors can only measure the spatial intensity distribution, phase retrieval arises as the central problem in wavefront sensing. Conventional interferometric approaches like phase-shifting interferometry (PSI) can recover phase information, but they rely on a stable reference beam that is difficult to realize in practical settings. To overcome this limitation, we propose a novel self-reference framework that relies on interference between shifted copies of the incoming wave; this results in pairwise phase differences between shifted pixels. We formulate an analytical solution for the complete phase retrieval based on the propagation of these differences across a connected graph. Furthermore, we provide a theoretical analysis of optimal measurement patterns, proving that co-prime shifts guarantee a connected graph and bound worst-case error accumulation, yielding a provably robust method. Extensive simulations demonstrate that complete phase profiles can be recovered from as few as eight shifted measurements, outperforming several existing approaches. Finally, we validate our framework using a hardware prototype, demonstrating real experiments for optical phase profile recovery, auto-refocusing, and imaging through scattering media.

eess.IV↗
arXiv2026

Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit scalability. We propose an inference-time steering framework that leverages gradient feedback from frozen pretrained foundation models to guide the generation process without modifying the underlying generator. Our key observation is that vision-language foundation models encode rich semantic representations that can be repurposed as off-the-shelf supervisory signals during generation. By injecting such feedback through clean latent estimates at each sampling step, our method formulates safety steering as an energy-based sampling problem. This design enables modular, training-free safety control that is compatible with both diffusion and flow-matching models and can generalize across diverse visual concepts. Experiments demonstrate state-of-the-art robustness against NSFW red-teaming benchmarks and effective multi-target steering, while preserving high generation quality on benign non-targeted prompts. Our framework provides a principled approach for utilizing foundation models as semantic energy estimators, enabling reliable and scalable safety control for text-to-image generation.

cs.CV↗
arXiv2026

SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires large paired datasets and substantial computational resources. Since many pretrained MLLMs (e.g., vision-language or audio-language) are publicly available, we ask whether we can merge them into a single MLLM that can handle multiple modalities? Merging MLLMs with different input modalities remains challenging, partly because of differences in the learned representations and interference between their parameter spaces. To address these challenges, we propose Singular Subspace Alignment and Merging (SSAM), a training-free model merging framework that unifies independently trained specialist MLLMs into a single model capable of handling any combination of input modalities. SSAM maintains modality-specific parameter updates separately and identifies a shared low-rank subspace for language-related parameter updates, aligns them within this subspace, and merges them to preserve complementary knowledge while minimizing parameter interference. Without using any multimodal training data, SSAM achieves state-of-the-art performance across four datasets, surpassing prior training-free merging methods and even jointly trained multimodal models. These results demonstrate that aligning models in parameter space provides a scalable and resource-efficient alternative to conventional joint multimodal training.

cs.LG↗
arXiv2026

Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks

Multi-task and multi-domain learning methods seek to learn multiple tasks/domains, jointly or one after another, using a single unified network. The primary challenge and opportunity lie in leveraging shared information across these tasks and domains to enhance the efficiency of the unified network. The efficiency can be in terms of accuracy, storage cost, computation, or sample complexity. In this paper, we introduce a factorized tensor network (FTN) designed to achieve accuracy comparable to that of independent single-task or single-domain networks, while introducing a minimal number of additional parameters. The FTN approach entails incorporating task- or domain-specific low-rank tensor factors into a shared frozen network derived from a source model. This strategy allows for adaptation to numerous target domains and tasks without encountering catastrophic forgetting. Furthermore, FTN requires a significantly smaller number of task-specific parameters compared to existing methods. We performed experiments on widely used multi-domain and multi-task datasets. We show the experiments on convolutional-based architecture with different backbones and on transformer-based architecture. Our findings indicate that FTN attains similar accuracy as single-task or single-domain methods while using only a fraction of additional parameters per task. The code is available at https://doi.org/10.24433/CO.7519211.v2.

cs.LG↗
arXiv2025

Discovering Sparse Recovery Algorithms Using Neural Architecture Search

The design of novel algorithms for solving inverse problems in signal processing is an incredibly difficult, heuristic-driven, and time-consuming task. In this short paper, we the idea of automated algorithm discovery in the signal processing context through meta-learning tools such as Neural Architecture Search (NAS). Specifically, we examine the Iterative Shrinkage Thresholding Algorithm (ISTA) and its accelerated Fast ISTA (FISTA) variant as candidates for algorithm rediscovery. We develop a meta-learning framework which is capable of rediscovering (several key elements of) the two aforementioned algorithms when given a search space of over 50,000 variables. We then show how our framework can apply to various data distributions and algorithms besides ISTA/FISTA.

cs.LG↗
arXiv2025

Robust Multimodal Learning via Cross-Modal Proxy Tokens

Multimodal models often experience a significant performance drop when one or more modalities are missing during inference. To address this challenge, we propose a simple yet effective approach that enhances robustness to missing modalities while maintaining strong performance when all modalities are available. Our method introduces cross-modal proxy tokens (CMPTs), which approximate the class token of a missing modality by attending only to the tokens of the available modality without requiring explicit modality generation or auxiliary networks. To efficiently learn these approximations with minimal computational overhead, we employ low-rank adapters in frozen unimodal encoders and jointly optimize an alignment loss with a task-specific loss. Extensive experiments on five multimodal datasets show that our method outperforms state-of-the-art baselines across various missing rates while achieving competitive results in complete-modality settings. Overall, our method offers a flexible and efficient solution for robust multimodal learning. The code for this paper is available at: https://github.com/CSIPlab/Cross-Modal-Proxy-Tokens.

cs.CV↗
arXiv2025

Cross-Modal Safety Alignment: Is textual unlearning all you need?

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). While further SFT and RLHF-based safety training can be conducted in multi-modal settings, collecting multi-modal training datasets poses a significant challenge. Inspired by the structural design of recent multi-modal models, where, regardless of the combination of input modalities, all inputs are ultimately fused into the language space, we aim to explore whether unlearning solely in the textual domain can be effective for cross-modality safety alignment. Our evaluation across six datasets empirically demonstrates the transferability -- textual unlearning in VLMs significantly reduces the Attack Success Rate (ASR) to less than 8\% and in some cases, even as low as nearly 2\% for both text-based and vision-text-based attacks, alongside preserving the utility. Moreover, our experiments show that unlearning with a multi-modal dataset offers no potential benefits but incurs significantly increased computational demands, possibly up to 6 times higher.

cs.CL↗
arXiv2025

EigenScore: OOD Detection using Covariance in Diffusion Models

Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progress, recent work has explored their potential for OOD detection. We propose EigenScore, a new OOD detection method that leverages the eigenvalue spectrum of the posterior covariance induced by a diffusion model. We argue that posterior covariance provides a consistent signal of distribution shift, leading to larger trace and leading eigenvalues on OOD inputs, yielding a clear spectral signature. We further provide analysis explicitly linking posterior covariance to distribution mismatch, establishing it as a reliable signal for OOD detection. To ensure tractability, we adopt a Jacobian-free subspace iteration method to estimate the leading eigenvalues using only forward evaluations of the denoiser. Empirically, EigenScore achieves SOTA performance, with up to 5% AUROC improvement over the best baseline. Notably, it remains robust in near-OOD settings such as CIFAR-10 vs CIFAR-100, where existing diffusion-based methods often fail.

cs.CV↗
arXiv2025

Gaussian is All You Need: A Unified Framework for Solving Inverse Problems via Diffusion Posterior Sampling

Diffusion models can generate a variety of high-quality images by modeling complex data distributions. Trained diffusion models can also be very effective image priors for solving inverse problems. Most of the existing diffusion-based methods integrate data consistency steps by approximating the likelihood function within the diffusion reverse sampling process. In this paper, we show that the existing approximations are either insufficient or computationally inefficient. To address these issues, we propose a unified likelihood approximation method that incorporates a covariance correction term to enhance the performance and avoids propagating gradients through the diffusion model. The correction term, when integrated into the reverse diffusion sampling process, achieves better convergence towards the true data posterior for selected distributions and improves performance on real-world natural image datasets. Furthermore, we present an efficient way to factorize and invert the covariance matrix of the likelihood function for several inverse problems. Our comprehensive experiments demonstrate the effectiveness of our method over several existing approaches. Code available at https://github.com/CSIPlab/CoDPS.

eess.IV↗
arXiv2025

VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions

Human pose and shape (HPS) estimation methods have been extensively studied, with many demonstrating high zero-shot performance on in-the-wild images and videos. However, these methods often struggle in challenging scenarios involving complex human poses or significant occlusions. Although some studies address 3D human pose estimation under occlusion, they typically evaluate performance on datasets that lack realistic or substantial occlusions, e.g., most existing datasets introduce occlusions with random patches over the human or clipart-style overlays, which may not reflect real-world challenges. To bridge this gap in realistic occlusion datasets, we introduce a novel benchmark dataset, VOccl3D, a Video-based human Occlusion dataset with 3D body pose and shape annotations. Inspired by works such as AGORA and BEDLAM, we constructed this dataset using advanced computer graphics rendering techniques, incorporating diverse real-world occlusion scenarios, clothing textures, and human motions. Additionally, we fine-tuned recent HPS methods, CLIFF and BEDLAM-CLIFF, on our dataset, demonstrating significant qualitative and quantitative improvements across multiple public datasets, as well as on the test split of our dataset, while comparing its performance with other state-of-the-art methods. Furthermore, we leveraged our dataset to enhance human detection performance under occlusion by fine-tuning an existing object detector, YOLO11, thus leading to a robust end-to-end HPS estimation system under occlusions. Overall, this dataset serves as a valuable resource for future research aimed at benchmarking methods designed to handle occlusions, offering a more realistic alternative to existing occlusion datasets. See the Project page for code and dataset:https://yashgarg98.github.io/VOccl3D-dataset/

cs.CV↗
arXiv2025

Targeted Unlearning with Single Layer Unlearning Gradient

Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and unrelated tasks. We propose Single Layer Unlearning Gradient (SLUG) as an efficient method to unlearn targeted information by updating a single critical layer using a one-time gradient computation. SLUG uses layer importance and gradient alignment metrics to identify the optimal layer for targeted information removal while preserving the model utility. We demonstrate the effectiveness of SLUG for CLIP, Stable Diffusion, and vision-language models (VLMs) in removing concrete (e.g., identities and objects) and abstract concepts (e.g., artistic styles). On the UnlearnCanvas benchmark, SLUG achieves comparable unlearning performance to existing methods while requiring significantly less computational resources. Our proposed approach offers a practical solution for targeted unlearning that is computationally efficient and precise. Our code is available at https://github.com/CSIPlab/SLUG.

cs.LG↗
arXiv2025

Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models

Diffusion models are widely used as priors in imaging inverse problems. However, their performance often degrades under distribution shifts between the training and test-time images. Existing methods for identifying and quantifying distribution shifts typically require access to clean test images, which are almost never available while solving inverse problems (at test time). We propose a fully unsupervised metric for estimating distribution shifts using only indirect (corrupted) measurements and score functions from diffusion models trained on different datasets. We theoretically show that this metric estimates the KL divergence between the training and test image distributions. Empirically, we show that our score-based metric, using only corrupted measurements, closely approximates the KL divergence computed from clean images. Motivated by this result, we show that aligning the out-of-distribution score with the in-distribution score -- using only corrupted measurements -- reduces the KL divergence and leads to improved reconstruction quality across multiple inverse problems.

cs.CV↗
arXiv2025

RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds

Despite the substantial advancements demonstrated by learning-based neural models in the LiDAR Point Cloud Compression (LPCC) task, realizing real-time compression - an indispensable criterion for numerous industrial applications - remains a formidable challenge. This paper proposes RENO, the first real-time neural codec for 3D LiDAR point clouds, achieving superior performance with a lightweight model. RENO skips the octree construction and directly builds upon the multiscale sparse tensor representation. Instead of the multi-stage inferring, RENO devises sparse occupancy codes, which exploit cross-scale correlation and derive voxels' occupancy in a one-shot manner, greatly saving processing time. Experimental results demonstrate that the proposed RENO achieves real-time coding speed, 10 fps at 14-bit depth on a desktop platform (e.g., one RTX 3090 GPU) for both encoding and decoding processes, while providing 12.25% and 48.34% bit-rate savings compared to G-PCCv23 and Draco, respectively, at a similar quality. RENO model size is merely 1MB, making it attractive for practical applications. The source code is available at https://github.com/NJUVISION/RENO.

cs.CV↗
arXiv2025

Transform-Dependent Adversarial Attacks

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial perturbations--their dependence on image transforms--and introduce transform-dependent adversarial attacks. Unlike traditional attacks, our perturbations exhibit metamorphic properties, enabling diverse adversarial effects as a function of transformation parameters. We demonstrate that this transform-dependent vulnerability exists across different architectures (e.g., CNN and transformer), vision tasks (e.g., image classification and object detection), and a wide range of image transforms. Additionally, we show that transform-dependent perturbations can serve as a defense mechanism, preventing sensitive information disclosure when image enhancement transforms pose a risk of revealing private content. Through analysis in blackbox and defended model settings, we show that transform-dependent perturbations achieve high targeted attack success rates, outperforming state-of-the-art transfer attacks by 17-31% in blackbox scenarios. Our work introduces novel, controllable paradigm for adversarial attack deployment, revealing a previously overlooked vulnerability in deep networks.

cs.CV↗
arXiv2024

STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimation

The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate prediction of human poses under conditions of severe occlusion. Traditional image-based estimators struggle with heavy occlusions due to a lack of temporal context, resulting in inconsistent predictions. While video-based models benefit from processing temporal data, they encounter limitations when faced with prolonged occlusions that extend over multiple frames. This challenge arises because these models struggle to generalize beyond their training datasets, and the variety of occlusions is hard to capture in the training data. Addressing these challenges, we propose STRIDE (Single-video based TempoRally contInuous Occlusion-Robust 3D Pose Estimation), a novel Test-Time Training (TTT) approach to fit a human motion prior for each video. This approach specifically handles occlusions that were not encountered during the model's training. By employing STRIDE, we can refine a sequence of noisy initial pose estimates into accurate, temporally coherent poses during test time, effectively overcoming the limitations of prior methods. Our framework demonstrates flexibility by being model-agnostic, allowing us to use any off-the-shelf 3D pose estimation method for improving robustness and temporal consistency. We validate STRIDE's efficacy through comprehensive experiments on challenging datasets like Occluded Human3.6M, Human3.6M, and OCMotion, where it not only outperforms existing single-image and video-based pose estimation models but also showcases superior handling of substantial occlusions, achieving fast, robust, accurate, and temporally consistent 3D pose estimates. Code is made publicly available at https://github.com/take2rohit/stride

cs.CV↗
arXiv2024

MMP: Towards Robust Multi-Modal Learning with Masked Modality Projection

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing methods that can handle missing modalities involve custom training or adaptation steps for each input modality combination. These approaches are either tied to specific modalities or become computationally expensive as the number of input modalities increases. In this paper, we propose Masked Modality Projection (MMP), a method designed to train a single model that is robust to any missing modality scenario. We achieve this by randomly masking a subset of modalities during training and learning to project available input modalities to estimate the tokens for the masked modalities. This approach enables the model to effectively learn to leverage the information from the available modalities to compensate for the missing ones, enhancing missing modality robustness. We conduct a series of experiments with various baseline models and datasets to assess the effectiveness of this strategy. Experiments demonstrate that our approach improves robustness to different missing modality scenarios, outperforming existing methods designed for missing modalities or specific modality combinations.

cs.LG↗
arXiv2024

Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation

Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correlated modalities. However, we observe that the performance of several existing multimodal networks significantly deteriorates if one or multiple modalities are absent at test time. To enable robustness to missing modalities, we propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks. In particular, we exploit modulation of intermediate features to compensate for the missing modalities. We demonstrate that such adaptation can partially bridge performance drop due to missing modalities and outperform independent, dedicated networks trained for the available modality combinations in some cases. The proposed adaptation requires extremely small number of parameters (e.g., fewer than 1% of the total parameters) and applicable to a wide range of modality combinations and tasks. We conduct a series of experiments to highlight the missing modality robustness of our proposed method on five different multimodal tasks across seven datasets. Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities.

cs.CV↗
arXiv2024

Event Transformer

The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or spikes for deep neural networks (DNNs). However, these approaches often sacrifice temporal granularity or require specialized devices for processing. This work introduces a novel token-based event representation, where each event is considered a fundamental processing unit termed an event-token. This approach preserves the sequence's intricate spatiotemporal attributes at the event level. Moreover, we propose a Three-way Attention mechanism in the Event Transformer Block (ETB) to collaboratively construct temporal and spatial correlations between events. We compare our proposed token-based event representation extensively with other prevalent methods for object classification and optical flow estimation. The experimental results showcase its competitive performance while demanding minimal computational resources on standard devices. Our code is publicly accessible at \url{https://github.com/NJUVISION/EventTransformer}.

cs.CV↗