CORTEXA
← Browse
arxivcs.CVcs.AIcs.LG2026-06-30

A Mechanism-Driven Theory of Phase Transitions in Active Learning

Julia Machnio, Mads Nielsen, Mostafa Mehdipour Ghazi

Active learning (AL) performance is known to be budget-dependent, yet regimes are typically defined by heuristic label counts that fail to generalize across datasets or architectures. We characterize AL dynamics by reframing budget regimes as shifts in the dominant generalization mechanism. By reinterpreting PAC-style risk components as dynamic interacting terms, we prove that dominance shifts are structurally unavoidable, creating a moving bottleneck for generalization. We operationalize this using measurable proxies and a segmented regression procedure to identify a tripartite taxonomy: data-driven, transition, and model-driven phases. Our framework explains the long-standing observation that representativeness, coverage, and uncertainty strategies excel at different stages. Experiments across natural and medical imaging show that AL efficiency depends on the alignment between the strategy's inductive bias and the active bottleneck. Moreover, self-supervised representation shift transitions earlier along the labeling trajectory, highlighting the role of representation quality in shaping AL dynamics. Overall, this work provides a unified framework for the next generation of transition-aware AL algorithms.

View free PDFSource page

Related papers

arxivcs.CVcs.AIcs.LG2026-06-26

Improving Adversarial Robustness via Activation Amplification and Attenuation

Taïga Gonçalves, Yongsong Huang, Tomo Miyazaki, Shinichiro Omachi

The existence of adversarial attacks is often attributed to the presence of non-robust features in neural networks. While prior defenses reduce their impact via pruning, masking, or feature recalibration, we instead propose to jointly learn to amplify and attenuate these signals…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-06-28

Can Machines Really See Objects in Images? A Study Based on Syntactic Distance and Visual Self-Referential Instances

Xingyu Peng, Junran Wu, Yue Hou, Zhongliang Qiao, Jiaheng Liu, Shangzhe Li, et al.

Can a vision model truly see an object, or does it only fit surface-level visual cues? Following Wittgenstein's view that the limits of language are the limits of the world, we view a model's recognition ability as bounded by the descriptive system it has learned. In current visi…

View free PDFSource page
arxivcs.LGcs.AIcs.CLcs.CV2026-07-05

DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics

Silin Gao, Hao Zhao, Zeming Chen, Sepideh Mamooler, Antara Raaghavi Bhattacharya, Qiyu Wu, et al.

Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences. Such inputs require models to predict or simulate multiple levels of dynamic constituents, such as actions taken in the visual sequence, and the associated…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-06-29

Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection

Mohammad Mahdi Abootorabi, Sina Namazi, Armin Saadat, Lyuyang Wang, Obed Dzikunu, Paul F. R. Wilson, et al.

Micro-ultrasound ($μ$US) is a new, emerging, and promising imaging modality for prostate cancer (PCa) detection, but accurate identification of suspicious tissue remains highly dependent on clinical experience, leading to substantial inter-observer variability. Machine-learning a…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-07

Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation

Yu Cheng, Siyue Yao, Zhongang Qi, Shanyan Guan, Wei Li, Fajie Yuan

Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all denoising s…

View free PDFSource page
arxiveess.IVcs.AIcs.CVcs.LG2026-06-26

MLVC: Multi-platform Learned Video Codec for Real-World Deployment

Tanel Pärnamaa, Martin Lumiste, Ardi Loot, Evgenii Indenbom, Andrei Znobishchev, Ando Saabas

Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce deterministic results across diverse hardware pl…

View free PDFSource page