Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.32374v1 Announce Type: new Abstract: Alzheimer's disease (AD) is a progressive neurological disorder associated with memory loss, cognitive decline, and behavioral disturbances. Early and...
arXiv:2610.32407v1 Announce Type: new Abstract: Text-to-image (T2I) diffusion models have advanced notably, but still fail to satisfy prompt conditions, resulting in attribute mismatches and missing...
arXiv:2610.32491v1 Announce Type: new Abstract: Computed tomography (CT) and magnetic resonance (MR) imaging provide complementary information for the brain, but acquiring both modalities is not alwa...
arXiv:2610.32500v1 Announce Type: new Abstract: While wide-angle lenses provide an expanded field of view (FoV), they exhibit severe nonlinear distortion near image boundaries, unnaturally stretching...
arXiv:2610.32709v1 Announce Type: new Abstract: Text-enhanced visible-infrared person re-identification (VI-ReID) exploits textual descriptions to compensate for appearance cues that are weak or unav...
arXiv:2610.32784v1 Announce Type: new Abstract: The rapid growth of video data has created an urgent need for efficient video understanding systems that can handle long and continuous visual inputs,...
arXiv:2610.32894v1 Announce Type: new Abstract: Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paired Earth Observation imagery. We pr...
arXiv:2610.32977v1 Announce Type: new Abstract: Actions that condition world models are highly heterogeneous, and thus existing action-conditioned world models are typically built for individual acti...
arXiv:2610.32473v1 Announce Type: cross Abstract: Dominant color extraction is a fundamental task in computer vision, with applications in design, image retrieval, and content recommendation. However...
arXiv:2511.15188v3 Announce Type: replace Abstract: Accurate brain-age estimation from structural MRI provides a valuable biomarker for studying healthy aging and neurodegenerative disease. We propos...
arXiv:2602.03380v3 Announce Type: replace Abstract: While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are...
arXiv:2607.24009v2 Announce Type: replace Abstract: Tensor methods are said to preserve structure that matrix methods destroy, but what is lost, and why, is unclear. Relative to a multilinear referen...
arXiv:2608.05663v3 Announce Type: replace Abstract: Real-time long-form avatar audio-video generation requires causal, continuous synthesis while maintaining audiovisual synchronization and visual co...
The paper introduces an improved post‑hoc out‑of‑distribution detection method called SCALE with an Absolute Fix that uses absolute‑valued activations to avoid cancellation of negative values. It further adds Anti‑coherence regularization, which penalizes scaling factors based on sign‑mismatched contributions to the maximum logit, thereby reducing unreliable evidence for the predicted class. The resulting approach achieves AUROC and FPR@95 performance that ties or surpasses training‑data‑dependent activation‑shaping methods on CIFAR‑10 and ImageNet under the OpenOOD v1.5 protocol.
The paper introduces CoRPS-Dial, a dual-agent framework that synthesizes pre‑consultation medical dialogues by combining a persona‑driven patient agent with a process‑guided doctor agent. It incorporates post‑hoc quality control to ensure role consistency, workflow completeness, and textual consistency. Experiments on coronary heart disease data show that CoRPS‑Dial produces dialogues that better match real conversations in information coverage, clinical compliance, and naturalness, and that the synthetic data improves downstream medical dialogue tasks.
DeepSafe‑SciHazard introduces a real‑world‑grounded benchmark for measuring scientific safety risks, comprising 2,400 hazardous and 600 oversafety questions across 12 disciplines. It defines a decomposed harm scoring system, DeHarm‑Score, that evaluates query severity, refusal behavior, and response‑level risk, further breaking down harm into executability and net‑new risk. An expert‑validation study shows DeHarm‑Score aligns 90.17% better with expert judgments than the best baseline, and the benchmark reveals that deep research agents score 32.3% higher on mean DeHarm‑Score than standard LLMs, highlighting a critical blind spot in current safety defenses.
PAIR‑SAFE is a paired‑agent framework that pairs a Responder agent with a Judge agent grounded in the clinically validated Motivational Interviewing Treatment Integrity (MITI‑4) to audit and refine AI‑mediated mental health support in real time. The Judge evaluates each response and issues “allow” or “revise” decisions, guiding the Responder toward more clinically aligned interactions. Experiments with a support‑seeker simulator show that Judge‑supervised interactions significantly improve MITI dimensions such as Partnership, Seek Collaboration, and overall relational quality, with findings corroborated by expert evaluation.
The paper uncovers a systematic mismatch in modern text embeddings: while sentiment can be extracted with high accuracy from frozen encoders, the embeddings’ cosine similarity metric barely reflects polarity differences. Across eleven models from 2021–2026, a linear probe achieves up to 91.3% accuracy, yet cosine similarity margins are only 0.003–0.064, leading to poor retrieval performance (e.g., Qwen3-Embedding-4B’s 64.3 MAP). Introducing a lightweight supervised‑contrastive head (Sentiment‑Injected Sentence Embeddings) dramatically improves probe accuracy, retrieval MAP, and polarity margins, but at the cost of downstream semantic similarity. "whyItMatters":"The findings reveal that widely used retrieval and clustering systems may ignore valuable sentiment information encoded in embeddings, impacting their effectiveness."
The paper proposes a method for estimating and correcting camera movement in 3D modeling by combining a modified ASIFT feature extractor with a two‑camera rotation correction model and a stereo camera translation estimation model. This integrated approach reduces computational overhead, increases the number of reliable matching points, and improves camera rotation and translation accuracy. Experiments demonstrate a 99.9% match to the actual camera path, outperforming existing state‑of‑the‑art methods and enabling more precise 3D reconstructions.
DetailAnywhere introduces a new fashion detail generation task that focuses on generating photorealistic close‑up views of specific garment regions, such as collars or cuffs, based on a focus marker in a reference image. The authors release FDBench, a benchmark of over 40,000 human‑verified detail pairs across 41 categories, and propose Cross‑Modal Feature Alignment Distillation (CFAD) to align multimodal diffusion branches using a DINOv3 teacher. A consistency reward model further improves alignment, and experiments show DetailAnywhere surpasses existing open‑source methods in both quantitative metrics and human evaluation.