arXiv:2603.12517v1 Announce Type: new Abstract: Timestep sampling $p(t)$ is a central design choice in Flow Matching models, yet common practice increasingly favors static middle-biased distributions (e.g., Logit-Normal). We show that this choice induces a speed–quality trade-off: middle-biased sampling accelerates early…
arXiv:2509.21619v2 Announce Type: replace Abstract: Training large models ranging from millions to billions of parameters is highly resource-intensive, requiring significant time, compute, and memory. It is observed that most of the learning (higher change in weights) takes place in the…
arXiv:2603.12520v1 Announce Type: new Abstract: Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is…
arXiv:2511.13421v2 Announce Type: replace Abstract: While data scaling laws of large language models (LLMs) have been widely examined in the one-pass regime with massive corpora, their form under limited data and repeated epochs remains largely unexplored. This paper presents a…
arXiv:2603.12529v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve impressive performance on complex reasoning tasks via Chain-of-Thought (CoT) reasoning, which enables them to generate intermediate thinking tokens before arriving at the final answer. However, LRMs often suffer from significant…
arXiv:2602.02592v2 Announce Type: replace Abstract: This paper proposes a unified family of learnable Koopman operator parameterizations that integrate linear dynamical systems theory with modern deep learning forecasting architectures. We introduce four learnable Koopman variants-scalar-gated, per-mode gated, MLP-shaped spectral mapping, and…
arXiv:2603.12530v1 Announce Type: new Abstract: Recent work shows that when contexts are drawn i.i.d., linear contextual bandits can be reduced to single-context linear bandits. This “contexts are cheap” perspective is highly advantageous, as it allows for sharper finite-time analyses and…
The technology could enable fast, point-of-care diagnoses for pneumonia and other lung conditions.
arXiv:2603.05773v2 Announce Type: replace-cross Abstract: Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the textbf{underline{D}}isentangled textbf{underline{S}}afety textbf{underline{H}}ypothesis textbf{(DSH)}, positing that…
arXiv:2505.07920v2 Announce Type: replace-cross Abstract: Peer review is a critical component of scientific progress in the fields like AI, but the rapid increase in submission volume has strained the reviewing system, which inevitably leads to reviewer shortages and declines review…
