Selected computer vision, artificial intelligence, and applied research briefings with direct links to the original work.
arXiv:2609.05484v1 Announce Type: new Abstract: Deep learning registration methods routinely stack two kinds of enhancement on a base network: architectural additions such as affine pre-alignment stages, and training-objective additions such as regularization losses. Papers tend to adopt both at once, so it is unclear…
Read at sourcearXiv:2609.05503v1 Announce Type: new Abstract: Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse at scale, motivating a rapidly growing body of research on adversarial attacks and defenses. This survey provides, to…
Read at sourcearXiv:2609.05516v1 Announce Type: new Abstract: Unified perception enables autonomous driving systems to perform object detection, drivable-area segmentation, and lane segmentation within a single network, improving efficiency and reducing deployment complexity. Jointly optimizing multiple perception tasks remains cha…
Read at sourcearXiv:2609.05517v1 Announce Type: new Abstract: Human observers prioritize visual information according to task goals. Most computational models of naturalistic viewing are gaze-trained for free viewing, leaving open whether goal-directed attention can emerge in systems without gaze supervision. We tested two off-the…
Read at sourcearXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, motivating multimodal retrieval-augmented generation (RAG) to ground responses in external text and images. However, existi…
Read at sourcearXiv:2609.05520v1 Announce Type: new Abstract: In this paper, we tackle automatic anomaly detection in multi-illumination and multi-focus display images. The minute defects on the display surface are hard to spot out in RGB images and by a model trained with only normal data. To address this, we propose a novel contr…
Read at sourcearXiv:2609.05522v1 Announce Type: new Abstract: Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints. We address this using two complementary denoising diffusion probabilistic models (DDPMs) for unconditio…
Read at sourcearXiv:2609.05523v1 Announce Type: new Abstract: This paper presents a one-stage learning framework that maps monocular roadside-camera images directly to vehicle states in a ground-fixed coordinate frame. Unlike conventional approaches that first detect vehicles in the image plane and subsequently apply geometric post…
Read at sourcearXiv:2609.05525v1 Announce Type: new Abstract: Large vision-language models (VLMs) are increasingly deployed in safety-critical settings, yet existing visual jailbreak research has focused almost exclusively on autoregressive architectures, leaving an important emerging family unstudied: multimodal discrete diffusion…
Read at sourcearXiv:2609.05532v1 Announce Type: new Abstract: Background: Diagnosing head and neck cancer using PET/CT is clinically challenging and time-consuming due to the anatomical complexity of the region, motivating computer-aided diagnosis (CAD). Generalist Large Multimodal Models (LMMs) remain limited in medical contexts b…
Read at sourcearXiv:2609.05533v1 Announce Type: new Abstract: Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in observations from minutes earlier. Existing memory mechanisms: retrieval banks, learned compressors, recurrent states must decide what to keep from the…
Read at sourcearXiv:2609.05535v1 Announce Type: new Abstract: Verdict-only evaluation does not reveal whether a vision-language model (VLM) used the visual evidence that should support its decision. We study this problem in web-agent guardrails, where a VLM judges whether on-screen text conflicts with a user instruction. We introdu…
Read at sourcearXiv:2609.05537v1 Announce Type: new Abstract: Tracking social media posts can help spot early signs of depression. Recent studies show that combining text and images works better for detecting depression than using text alone. However, many social media posts do not have images, which makes it hard to use multimodal…
Read at sourcearXiv:2609.05539v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have recently made strong progress in vision-language reasoning, yet their performance often degrades as generations grow longer. A key factor is that they frequently lose track of earlier visual evidence and intermediate constrai…
Read at sourcearXiv:2609.05540v1 Announce Type: new Abstract: Many medical conditions require diagnosis through detailed, multi-context clinical assessment rather than from visual appearance alone. Despite this, vision-language models (VLMs) are increasingly queried to interpret images in ways that touch on medical or diagnostic ju…
Read at sourcearXiv:2609.05541v1 Announce Type: new Abstract: Implicit Neural Representations (INR) provide a compact and content-adaptive paradigm for video compression, typically representing a video through shared network parameters and frame-indexed embeddings. Compared to conventional or autoencoder-based codecs, these approac…
Read at sourcearXiv:2609.05543v1 Announce Type: new Abstract: Automated assessment of depression from facial dynamics holds promise for scalable mental health monitoring, yet cross-corpus generalization of learned biomarkers remains an open challenge. We present a systematic bidirectional transfer study pairing the EmpkinS-EKSpress…
Read at sourcearXiv:2609.05550v1 Announce Type: new Abstract: Near-infrared (NIR) video is a promising modality for contactless sleep monitoring, but recent video-based sleep staging methods often use it as a route to reconstructed respiratory/cardiac proxies or cross-modal physiological representations. We study video-only sleep s…
Read at source