Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2609.14178v1 Announce Type: new Abstract: The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen p...
arXiv:2609.14687v1 Announce Type: new Abstract: Data-to-text driver coaching is often presented as a generic pipeline from telematics events to advice. This paper argues that its content requires loc...
arXiv:2609.13791v1 Announce Type: new Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom...
arXiv:2609.13941v1 Announce Type: new Abstract: We present BLInD (Blind Learned Intent Distribution), a compact network that maps recent vehicle-state history (e.g. speed, curvature, indicator, and v...
arXiv:2606.29997v2 Announce Type: replace Abstract: Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limi...
arXiv:2512.20257v2 Announce Type: replace Abstract: With the rise of easily accessible generative tools for creating and manipulating multimedia content, the threat of realistic synthetic alterations...
arXiv:2605.16742v3 Announce Type: replace Abstract: Cortical surface registration is often driven by local geometric descriptors (e.g., sulcal depth and curvature). While this approach achieves geome...
UniCAR‑RL is an annotation‑free reinforcement learning framework designed to improve multimodal large language models’ visual mathematics reasoning. It decouples perception and reasoning by using three branches: Caption‑RL for perception optimization, Reasoning‑RL for logical reasoning with a gold image description, and QA‑RL for end‑to‑end question answering. Experiments show significant gains in mathematical and visual reasoning across various model architectures and scales using only raw short‑answer data.
arXiv:2609.15855v1 Announce Type: cross Abstract: % !TEX root = ../main.tex People increasingly use large language models (LLMs) for mental health support, yet their safety in evolving, high-risk con...
arXiv:2606.19100v4 Announce Type: replace Abstract: Large Vision and Language Models (LVLMs) have advanced rapidly, yet European Portuguese (pt-PT) remains systematically underserved by existing open...
The paper argues that as Large Language Models transition from chatbots to agentic systems, the current post-hoc interpretability paradigm is insufficient for safe deployment because it cannot audit or intervene before an output is produced. It proposes a shift to generative interpretability, where a model’s inference process inherently exposes semantically meaningful checkpoints that are human-understandable and can be causally intervened upon. The authors illustrate the advantages of this approach and introduce Neuro‑Symbolic Models as a concrete implementation.
arXiv:2609.15106v1 Announce Type: new Abstract: Large language models can hallucinate even when the knowledge required for a correct answer is already available. We study this failure through a laten...
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
arXiv:2609.15883v1 Announce Type: cross Abstract: Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies...
arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising $97\%$ cost reductions over traditional surveys. Yet aggregat...
arXiv:2609.13547v1 Announce Type: new Abstract: We study switching regret in adversarial multi-armed bandits, where the learner competes with an arm sequence that changes at most $S$ times. When $S$...
Multimodal large language models (MLLMs) have made strong progress on visual question answering and image captioning, yet they still produce fluent claims about objects, attributes, or relations that...
Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This...
Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that provide natural language access to scientific kno...
Rapid advancements in vision-language models have propelled Referring Remote Sensing Image Segmentation (RRSIS) to the forefront of Earth observation. However, practical deployments suffer severe perf...