Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2605.31328v2 Announce Type: replace Abstract: Emergent misalignment (EM) is the surprising tendency of language models to become broadly misaligned after fine-tuning on narrowly misaligned exam...
arXiv:2606.01914v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly...
arXiv:2606.05985v2 Announce Type: replace Abstract: Multicultural multi-agent systems are increasingly deployed in globally diverse settings, where different agents are grounded in different cultural...
arXiv:2606.30085v2 Announce Type: replace Abstract: Large-language models have proven to be remarkable if inconsistent parrots of public attitudes and opinions. The extent to which LLMs are able to p...
arXiv:2608.28945v1 Announce Type: new Abstract: Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such...
arXiv:2505.15741v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Evolutionary Computation (EC) are increasingly being combined to support automated optimization, algorithm d...
arXiv:2510.26861v4 Announce Type: replace-cross Abstract: Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practi...
arXiv:2601.20107v3 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index st...
arXiv:2608.28787v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) have primarily been developed for self-supervised representation learning. Denoising JEPA (D-JEPA) rec...
arXiv:2608.28933v1 Announce Type: new Abstract: Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias...
arXiv:2608.29038v1 Announce Type: new Abstract: Noise poses a widespread challenge in signal processing, particularly when it comes to denoising images. Although convolutional neural networks (CNNs)...
arXiv:2608.29126v1 Announce Type: new Abstract: Referring single-object tracking enables language-grounded target initialization and subsequent tracking by jointly leveraging semantic cues and visual...
arXiv:2608.29186v1 Announce Type: new Abstract: Federated Video Domain Adaptation (FVDA) enables collaborative learning across distributed and non-IID video datasets while preserving privacy, but is...
arXiv:2608.29220v1 Announce Type: new Abstract: Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while el...
arXiv:2608.29456v1 Announce Type: new Abstract: As artificial intelligence is increasingly integrated into chest X-ray (CXR) interpretation, triage, and clinical decision support, understanding its v...
arXiv:2608.29540v1 Announce Type: new Abstract: This paper introduces NepScript Genesis, a Neural Architecture Search (NAS) framework for automated Generative Adversarial Network (GAN) discovery, app...
arXiv:2608.29917v1 Announce Type: new Abstract: Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes...
arXiv:2608.29970v1 Announce Type: new Abstract: Artistic Text Recognition (ATR) remains challenging because word images often combine decorative fonts, curved layouts, object-like characters, clutter...
arXiv:2608.30247v1 Announce Type: new Abstract: Recent unified open-vocabulary detection (OVD) supports heterogeneous prompts, including text queries, visual exemplars, and their combinations, but of...
arXiv:2608.30758v1 Announce Type: new Abstract: Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal r...