…AI-generated summary Token serves as the fundamental unit of computation in modern autoregressive models , and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches lack…
…modern diffusion backbones can serve as generalist segmentation learners rather than pure generators, narrowing the gap between visual generation and visual understanding . View arXiv page View PDF Add to collection Community Diffusion…
…Recent studies show that even modern commercial models with advanced guardrails remain vulnerable to such attacks despite advances in safety alignment and external guardrails. In this work, we address this challenge by…
…View arXiv page View PDF Add to collection Community StateKV is an inference-time method that enables linear-time video prefill for video vision-language models by using a fixed-capacity recurrent…
…SAE-space clustering with moderate batch mixing for batch diversity control, a difficulty proxy for easy-to-hard curriculum ordering, and a quality probe for data filtering. SAERL improves average accuracy by…
…By evaluating our method across several modern image-classification models , we provide empirical evidence supporting the hypothesis that decision regions in deep neural networks are not only path connected , but also simply…
…Yet modern regressors are still trained on the full feature set. We ask whether the Markov boundary is genuinely useful for prediction on SCM3K, a 3,450-task synthetic SCM benchmark with…
…AI-generated summary Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized codecs such as JPEG and…
…Error analysis shows that moderation relations and concept hierarchies remain the most challenging cases, highlighting the difficulty of extracting higher-order empirical claims and implicit abstraction structure from scientific abstracts. View arXiv…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens . While text-based output interfaces enable scalable pretraining and strong zero…