Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benefit from both temporal breast tissue changes across longitudinal examinations and complementary anatomical information from craniocaudal (CC) and mediolateral oblique (M...
Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin et al.· 0 citations
Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-token prediction Transformer with the deep clustering algorithm DCSS to learn meaningful representations with well-separated clusters. In a controlled Minecr...
Tobias Schneider, Danial Fahrner, Soren Antebi et al.· 0 citations
SLDBench v2 is introduced with two extensions, and active scaling law discovery is introduced: an agent chooses which experiments to run, pays each one's recorded cost, and revises its law as outcomes arrive, and is scored on the same hidden extrapolation targets as in the passive setting.
Ling-Bei Meng, Rui Huang, Zhi-Rong Shen et al.· 0 citations
Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive, multimodal policy parameterizations via deterministic probability transport. Compared to diffusion-based policies that rely on stochastic denoising chains, FM uses sa...
Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Deep-search agents are commonly trained by distilling tool-use trajectories from stronger teacher models. However, structurally complex questions may remain relatively easy for teachers familiar with key entities in the underlying entity graph, resulting in lower search demand and weaker supervision. We refer to this t...
Yifei Liu, Zhixiang Liang, Wentao Tan et al.· 0 citations
We study sampling from $\pi(x)\propto\mathrm{e}^{-V(x)}$ on $\mathbb{R}^d$, where $V$ is $\alpha$-strongly convex and $\beta$-smooth with condition number $\kappa=\beta/\alpha$. For this problem, the proximal sampler preserves the target exactly and recovers overdamped Langevin dynamics in the small-step limit, but its...
In-silico optimization of nucleic acids relies on predictive oracles that imperfectly capture biological function, so sequences optimized against one model may exploit model-specific artifacts and fail to generalize to independent models. Recent studies have shown that not all designers generalize equally well to indep...
Text-to-image models have made remarkable progress in visual fidelity and instruction following, yet complex compositional generation remains challenging. Existing agentic approaches address this limitation through iterative generation and editing, adapting their actions based on interaction history. However, they typi...
Zixu Wang, Xiaoran Zhao, Yahui Liu et al.· 0 citations
Embedded platforms increasingly host safety-related streaming functions next to less critical ones. Whether a safety architecture pattern, such as a doer/checker pair, protects a function depends on the cores that run its components. Their schedule must meet the throughput requirement, and mixing safety integrity level...
Spatial transcriptomics jointly captures molecular state, tissue morphology, and spatial organization, yet spatial-domain methods are typically compared only at late training checkpoints, obscuring differences in convergence efficiency. We introduce MP-MNCA, a morphology-prior masked neighbor cross-attention framework...
This work proposes EventLens, a vision-centric reinforcement learning framework that learns video understanding through event-structure recovery, and introduces multi-teacher on-policy distillation (MT-OPD) to consolidate specialized policies into a unified model.
Guo-Wen Zhang, Bo-Shen Xu, Zihao Yue et al.· 0 citations
A fruitful approach towards understanding generalization in machine learning involves characterizing how models separate generalizable structure from idiosyncratic or even corrupted features of training data. Fisher information has emerged as a diagnostic tool for this separation, leveraging loss geometry to distinguis...
Daniel T. Bernstein, Chase Goddard, L. di Carlo et al.· 0 citations
