Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.27760v1 Announce Type: new Abstract: We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual in...
arXiv:2608.28382v1 Announce Type: new Abstract: Users often ask large language models (LLMs) to report how confident they are, but it is unclear whether such linguistic confidence tracks the model's...
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common...
arXiv:2608.28394v1 Announce Type: cross Abstract: Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneit...
arXiv:2608.28518v1 Announce Type: cross Abstract: We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that...
arXiv:2606.21359v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to communicate and explain scientific concepts, yet their tendency to hallucinate poses signific...
arXiv:2606.17092v2 Announce Type: replace-cross Abstract: Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex convers...
arXiv:2608.27997v1 Announce Type: new Abstract: Air-ground cross-view referring person detection is a necessary component in the language-to-perception-to-control chain of collective embodied intelli...
arXiv:2608.27971v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) multimodal perception integrates visible (RGB), infrared (IR), synthetic aperture radar (SAR), and depth sensors for scen...
arXiv:2608.28219v1 Announce Type: new Abstract: Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving vid...
arXiv:2608.28386v1 Announce Type: new Abstract: Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic o...
arXiv:2608.28455v1 Announce Type: new Abstract: Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated lab...
arXiv:2604.06079v2 Announce Type: replace Abstract: Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals...
arXiv:2604.14129v2 Announce Type: replace Abstract: While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal ha...
arXiv:2607.22494v2 Announce Type: replace-cross Abstract: Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk facto...
arXiv:2606.26403v2 Announce Type: replace Abstract: Foundation-model research increasingly needs data about people: user state, personal histories, relationships, contact-like fields, documents, and...
arXiv:2510.25384v2 Announce Type: replace Abstract: Large Language Models (LLMs) are promising tools for synthetic data generation in mental health. However, privacy policies and restrictions forced...
The paper investigates when conditional flow matching (CFM) can replace pointwise negative log-likelihood (NLL) calculations. It shows that for linear Gaussian paths, the endpoint NLL can be exactly decomposed into entropy, a weighted CFM objective, and residual terms, meaning CFM-only estimates are exact only when these residuals cancel. The study finds that ordinary CFM is generally not a pointwise NLL estimator, and even weighted variants may not fully eliminate bias, especially in training or on‑policy settings, with experiments confirming these theoretical insights.
The paper investigates how scaling video diffusion models affects performance on autonomous driving data, training models ranging from 1 M to 9 B parameters on up to 5,500 hours of driving footage. Validation loss follows predictable power‑law trends with both model size and training exposure, showing that longer training yields faster loss reduction than increasing model size, though larger models still achieve lower asymptotic loss. Guided by these findings, the authors train a 9 B‑parameter model that becomes the largest video diffusion model trained from scratch on driving data and sets a new open‑source state‑of‑the‑art on the nuScenes benchmark.
The paper investigates audio‑visual conflict as a test of compositional generalization for audio‑visual large language models (AV‑LLMs). It shows that models such as VideoLLaMA 2‑7B‑AV and InternVideo2 exhibit a failure mode called prior dominance, where late‑layer commitment to an internally preferred answer pattern overrides conflicting audio‑visual inputs, leading to significant accuracy drops. Mechanistic analysis reveals that this commitment is concentrated around layer 25.5 and that stronger temporal alignment shifts answer bias but does not resolve the conflict.