Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2604.25866v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, where reliable emotion detection is essential. H...
arXiv:2605.00326v2 Announce Type: replace Abstract: Safety pipelines often block content by thresholding a model's first-token unsafe score. We show that a single prompt's score is not a reliable pro...
arXiv:2605.25421v2 Announce Type: replace Abstract: Communication protocol design is a central challenge in large language model-based multi-agent systems. Existing single-channel approaches face an...
arXiv:2509.21143v3 Announce Type: replace-cross Abstract: Multimodal models have demonstrated strong capabilities in web, desktop, and mobile GUI environments, but their performance in automotive coc...
arXiv:2606.11648v2 Announce Type: replace-cross Abstract: Backdoor attacks pose a serious threat to the safety and reliability of Large Language Models (LLMs), as they cause models to behave normally...
arXiv:2610.33044v1 Announce Type: new Abstract: Embodied vision-language models must answer questions from partial, evolving observations. Their success depends on both the reasoning capability selec...
arXiv:2610.33737v1 Announce Type: new Abstract: Daylight compliance assessment in residential buildings requires time-consuming raytracing simulations and specialist model preparation, limiting its i...
arXiv:2610.34303v1 Announce Type: new Abstract: Recent advances in image editing have enabled fine-grained and highly controllable visual modifications. However, achieving similar levels of controlla...
arXiv:2610.34952v1 Announce Type: new Abstract: Dynamic Gaussian reconstruction requires compact scene features to support coordinated changes in geometry and appearance. A factorized grid provides e...
arXiv:2610.35448v1 Announce Type: cross Abstract: End-to-end driving models perform well on standard benchmarks but collide frequently in safety-critical scenarios. We present a failure-mode analysis...
arXiv:2502.04192v5 Announce Type: replace Abstract: Multiple works have emerged to push the boundaries of multi-modal large language models (MLLMs) towards pixel-level understanding. The current tren...
arXiv:2509.01107v2 Announce Type: replace Abstract: Layout-to-image (L2I) generation has exhibited promising results in natural domains, but suffers from limited generative fidelity and weak alignmen...
arXiv:2512.01675v3 Announce Type: replace Abstract: Text-to-image flow matching transformers degrade sharply in long-tail settings: tail-class outputs collapse in fidelity and diversity, limiting the...
arXiv:2603.16063v2 Announce Type: replace Abstract: Vision Transformers (ViTs) based vision foundation models (VFMs) have achieved remarkable performance across diverse vision tasks, but suffer from...
arXiv:2606.13315v2 Announce Type: replace Abstract: MRI self-supervised learning (SSL) has largely emphasized segmentation and dense prediction, while controlled studies of how alternative pretrainin...
arXiv:2608.10181v2 Announce Type: replace Abstract: Computer vision saliency models predict where people will look, one map per image, and a predicted-attention industry sells those maps in place of...
arXiv:2610.14403v2 Announce Type: replace Abstract: Learning reusable skills can improve visual reasoning agents, yet applying a skill still requires the agent to implement or invoke a procedure and...
arXiv:2606.06498v2 Announce Type: replace-cross Abstract: Traditional statistical graphics are precise but often lack the visual appeal, memorability, and engagement of pictorial charts. We present a...
arXiv:2610.35428v1 Announce Type: new Abstract: Structured sparse learning is a leading paradigm for high-dimensional data modeling, as it enables rigorous integration of domain-validated structural...
arXiv:2610.33985v1 Announce Type: cross Abstract: Gradient equilibrium (GEQ) is a recent framework in online learning that requires the time-averaged gradients along the learner's trajectory to vanis...