Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602.01161v2 Announce Type: replace Abstract: The global deployment of large language models (LLMs) has raised concerns about cultural misalignment, yet the linguistic properties of fine-tuning...
arXiv:2603.00842v2 Announce Type: replace Abstract: Biomedical multimodal assistants have the potential to unify radiology, pathology, and clinical-text reasoning, yet a critical deployment gap remai...
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR arch...
arXiv:2605.10893v3 Announce Type: replace Abstract: Large vision-language models (LVLMs) suffer from visual ungroundedness: they can produce a fluent, confident, and even correct response driven enti...
arXiv:2605.25920v2 Announce Type: replace Abstract: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constra...
arXiv:2608.18082v2 Announce Type: replace Abstract: Although context windows have expanded significantly in recent years, hallucinations in long-context summarization remain a challenge. Long novels...
arXiv:2609.22706v1 Announce Type: new Abstract: Identity association in multi-object tracking (MOT) is vulnerable to partial occlusion, truncated detections, and fluctuating confidence scores. Existi...
arXiv:2609.22762v1 Announce Type: new Abstract: Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expe...
arXiv:2609.23012v1 Announce Type: new Abstract: Generative vision-language models (VLMs) offer a counting paradigm in which one model produces both a count and a natural-language account of the scene...
arXiv:2609.23061v1 Announce Type: new Abstract: Small-object detection in UAV imagery is challenged by weak visual evidence, ambiguous boundaries, dense object distributions, and complex backgrounds....
arXiv:2609.23161v1 Announce Type: new Abstract: A conventional camera uses millions of pixels to measure radiance from all directions within its field of view. We present an omnidirectional irradianc...
arXiv:2609.23248v1 Announce Type: new Abstract: A fundamental challenge in deploying vision models is domain shift, which arises when training and test data follow different distributions, leading to...
arXiv:2609.23427v1 Announce Type: new Abstract: Vision foundation models targeting Earth observation (EO) tasks are commonly evaluated on clean downstream benchmarks, but operational EO products can...
arXiv:2609.23442v1 Announce Type: new Abstract: Diffusion models generate high-quality images, yet often violate the physical laws governing mirror reflections. Reflections often suffer from geometri...
arXiv:2609.23796v1 Announce Type: new Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...
arXiv:2609.23881v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) are a promising paradigm for learning task-agnostic latent world models without visual reconstruction....
arXiv:2609.24215v1 Announce Type: new Abstract: Although text-to-image models can accurately depict subjects and scenes, creators still struggle to specify the fine-grained emotions an image should c...
arXiv:2609.24228v1 Announce Type: new Abstract: Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only...
arXiv:2609.24537v1 Announce Type: new Abstract: Video recording on smart glasses exposes more than faces. Continuous capture reveals full-body biometric signatures, including gait, posture, and silho...
arXiv:2609.24539v1 Announce Type: new Abstract: Multi-modal object Re-Identification (ReID) benefits from complementary information across heterogeneous imaging modalities. To further enrich semantic...