Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.20278v1 Announce Type: new Abstract: Facial image watermarking can support traceability and certification in biometric pipelines, but provenance or manipulation detection alone does not gu...
arXiv:2610.20494v1 Announce Type: new Abstract: Pretrained representations are increasingly used to share and reuse information from medical images without exposing the original scans, but it is uncl...
arXiv:2610.20608v1 Announce Type: new Abstract: Representation-alignment methods effectively accelerate the diffusion transformer training. REPA, for example, uses a pretrained vision encoder to supe...
arXiv:2610.20543v1 Announce Type: new Abstract: Multimodal sentiment models are usually evaluated on complete utterances, yet streams often lose a contiguous span of text, audio, or video. We study l...
arXiv:2610.20561v1 Announce Type: new Abstract: Reliable brain-mask transfer into native fluid-attenuated inversion recovery (FLAIR) space can fail when T1-to-FLAIR rigid registration is unstable. We...
arXiv:2610.19825v1 Announce Type: cross Abstract: Integrating world models into Vision-Language-Action models (VLAs) has emerged as a promising direction, enabling policies to anticipate future dynam...
arXiv:2610.19274v1 Announce Type: cross Abstract: Atmospheric turbulence creates complex spatial and temporal distortions that significantly reduce image quality. This work compares two deep learning...
arXiv:2509.09658v3 Announce Type: replace Abstract: Hallucinations in multimodal large language models (MLLMs), where a model generates content inconsistent with the input image, pose significant ris...
arXiv:2602.05359v3 Announce Type: replace Abstract: The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often...
arXiv:2605.20337v2 Announce Type: replace Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks in...
arXiv:2606.16203v4 Announce Type: replace Abstract: Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI). Yet, early identification remains challenging due to the co...
arXiv:2605.09129v2 Announce Type: replace Abstract: Circuit study aims to explain how language models (LMs) implement a task by localizing and interpreting a circuit: a computational subgraph respons...
arXiv:2605.15959v2 Announce Type: replace Abstract: Physics-informed neural networks (PINNs) are powerful surrogates for differential equations but are notoriously difficult to train due to spectral...
arXiv:2609.32807v2 Announce Type: replace Abstract: Clinical LLM evaluation often emphasizes answer accuracy; however, accuracy alone does not test counterfactual consistency or demographic robustnes...
arXiv:2606.22278v2 Announce Type: replace-cross Abstract: Ensuring safety of learning-enabled robotic manipulation across diverse embodiments and tasks still requires significant manual engineering....
arXiv:2610.16015v1 Announce Type: new Abstract: The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models...
arXiv:2310.14040v2 Announce Type: replace-cross Abstract: Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. H...
arXiv:2610.14136v2 Announce Type: new Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
arXiv:2610.14186v1 Announce Type: new Abstract: Could model-free reinforcement learning algorithms actually be learning a model of the environment? In this work, we apply counterfactual interventions...
arXiv:2506.23101v2 Announce Type: replace-cross Abstract: Ensuring the trustworthiness of Multimodal Large Language Models (MLLMs) requires rigorous evaluation of gender bias, particularly in sociall...