Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608.30951v1 Announce Type: new Abstract: The rapid development of generative portrait models has raised growing concerns about privacy leakage and identity misuse. In particular, audio-driven...
arXiv:2608.30964v1 Announce Type: new Abstract: Pretrained vision embeddings are increasingly used as general-purpose representations for modelling how people appraise urban scenes, and are validated...
arXiv:2608.31025v1 Announce Type: new Abstract: Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remain...
arXiv:2608.28714v1 Announce Type: cross Abstract: Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged me...
arXiv:2608.28773v1 Announce Type: cross Abstract: Perceptual losses are widely used in medical image synthesis because they encourage agreement in high-level structure beyond voxel-wise intensity sim...
arXiv:2409.11018v3 Announce Type: replace Abstract: The LiDAR 3D object detector that balances accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many ex...
arXiv:2502.12527v2 Announce Type: replace Abstract: Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the...
arXiv:2505.16990v3 Announce Type: replace Abstract: In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discr...
arXiv:2510.23515v3 Announce Type: replace Abstract: This paper proposes FreeFuse, a training-free framework for multi-subject text-to-image generation through automatic fusion of multiple subject LoR...
arXiv:2510.25901v2 Announce Type: replace Abstract: The vulnerability of cyclists, exacerbated by the rising popularity of faster e-bikes, motivates adapting automotive perception technologies for bi...
arXiv:2603.06399v2 Announce Type: replace Abstract: Facial attribute classification relies on large-scale annotated datasets in which many traits, such as age and expression, are inherently ambiguous...
arXiv:2605.13155v2 Announce Type: replace Abstract: Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward...
arXiv:2607.10851v2 Announce Type: replace Abstract: Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classif...
arXiv:2607.14088v2 Announce Type: replace Abstract: Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure...
arXiv:2608.01988v2 Announce Type: replace Abstract: Rapid advances in image generation models call for interpretable AI-generated image detection methods that not only determine authenticity but also...
arXiv:2608.08693v2 Announce Type: replace Abstract: Quantitative T2* maps have strong potential for biomarker discovery but are limited by long scan times, rendering them impractical in clinical sett...
arXiv:2410.19245v3 Announce Type: replace-cross Abstract: With the rapid advancement of Large Language Models (LLMs), LLM-based approaches have demonstrated strong problem-solving capabilities across...
arXiv:2605.09362v2 Announce Type: replace-cross Abstract: We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wiref...
PermitGPT is a generative‑AI framework that transforms unstructured construction permit descriptions into structured outputs for safety hazard identification, permit requirement specification, and community impact assessment. It aligns data from the NYC Department of Buildings, OSHA, and NYC 311 to create 90,000 prompt‑response pairs, fine‑tunes three open‑weight language models, and evaluates them on 2,833 test cases, reporting complementary performance across inference speed, lexical overlap, and semantic alignment. The study presents an initial AI‑assisted approach to construction governance and outlines future evaluation and validation directions.
The paper introduces the Frequency Selective Neural Network (FSNN), a new foundation architecture for time‑series learning that embeds advanced signal‑processing mathematics into its neural topology. By using a fully differentiable Wiener‑like filter bank optimized with complex‑domain backpropagation, FSNN autonomously discovers and isolates the precise physical modes of a given task, thereby avoiding the spectral entanglement that plagues CNNs, RNNs, and Transformers. Extensive evaluations show that FSNN achieves state‑of‑the‑art predictive performance, attaining 77.0 % average accuracy on the 10 multivariate UEA datasets and leading all major metrics on the imbalanced PTB‑XL ECG benchmark, while converging directly on physically meaningful frequency bands such as the cardiac QRS complex.