arXiv:2605.07915v1 Announce Type: new
Abstract: Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing tokenizers are primarily designed to improve reconstruc…
arXiv:2605.07919v1 Announce Type: new
Abstract: Medical vision–language models (VLMs) are usually evaluated on intact image–question pairs, but trustworthy clinical use requires a stronger property: a model must recognise when the evidential basis f…
arXiv:2605.07517v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat natu…
arXiv:2605.08084v1 Announce Type: new
Abstract: The pursuit of autonomous driving has produced one of the richest sensor data collections in all of robotics. However, its scale and diversity remain largely untapped. Each dataset adopts different 2D an…
arXiv:2604.19697v2 Announce Type: replace
Abstract: Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuab…
arXiv:2604.16579v2 Announce Type: replace-cross
Abstract: Automated multimodal depression estimation in unconstrained environments is inherently challenged by naturalistic noise and complex behavioral variability. Prevailing deterministic methods, how…
arXiv:2605.00814v2 Announce Type: replace
Abstract: While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a “Visual Signal Dilution” phenomenon, where the accumulation of textual hi…
arXiv:2604.26509v3 Announce Type: replace
Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for simulation-based training and real-world deployment. While 3D generative modeling has …
arXiv:2605.02357v2 Announce Type: replace
Abstract: In 3D point cloud understanding, the core challenge lies in accurately capturing discriminative features within complex neighborhoods, which directly affects the execution precision of downstream tas…
arXiv:2605.02881v2 Announce Type: replace
Abstract: Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today’s systems fall short on the criteria that matter for real-world deployment. Frontier models are…