Quality follows upgrading
Tag: cs.CV
arXiv:2604.06333v1 Announce Type: new Abstract: Drifting models generate high-quality samples in a single forward pass by transporting generated samples toward the data distribution using a …
arXiv:2604.06631v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training while preserving data privacy, but its practical deployment is hampered by system and …
arXiv:2604.06349v1 Announce Type: new Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains …
arXiv:2604.06422v1 Announce Type: new Abstract: Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere …
arXiv:2604.05378v1 Announce Type: new Abstract: Recent progress in vision-language-action (VLA) models has enabled language-conditioned driving agents to execute natural-language navigation commands in closed-loop simulation, yet …
arXiv:2604.05497v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive (AR) LLMs. Recently, this paradigm has been extended …
arXiv:2604.05414v1 Announce Type: new Abstract: Recent work has shown that removing orthogonalization during training and applying it only at inference improves rotation estimation in deep …
arXiv:2604.05445v1 Announce Type: new Abstract: Vision-language reward modeling faces a dilemma: generative approaches are interpretable but slow, while discriminative ones are efficient but act as …
arXiv:2604.05070v1 Announce Type: new Abstract: Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level …
arXiv:2604.03928v1 Announce Type: new Abstract: Effective ride-hailing dispatch requires anticipating demand patterns that vary substantially across time-of-day, day-of-week, season, and special events. We propose a …
arXiv:2604.02338v1 Announce Type: new Abstract: MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable …
arXiv:2604.02371v1 Announce Type: cross Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored …