arXiv:2604.13217v1 Announce Type: new Abstract: Reliable evaluation of blastocyst quality is critical for the success of in vitro fertilization (IVF) treatments. Current embryo grading practices primarily rely on visual assessment of morphological features, which introduces subjectivity, inter-embryologist variability, and challenges in standardizing quality assurance. In this study, we propose a multitask embedding-based approach for the automated analysis and prediction of key blastocyst components, including the trophectoderm (TE), inner cell mass (ICM), and blastocyst expansion (EXP). The method leverages […]

Ver mais

arXiv:2603.22824v1 Announce Type: cross Abstract: Implicit bias induced by gradient-based algorithms is essential to the generalization of overparameterized models, yet its mechanisms can be subtle. This work leverages the Normalized Steepest Descent} (NSD) framework to investigate how optimization geometry shapes solutions on multiclass separable data. We introduce NucGD, a geometry-aware optimizer designed to enforce low rank structures through nuclear norm constraints. Beyond the algorithm itself, we connect NucGD with emerging low-rank projection methods, providing a unified perspective. To […]

Ver mais

arXiv:2602.23411v1 Announce Type: new Abstract: The structural phase transitions and computational complexity of random 3-SAT instances are traditionally described using thermodynamic analogies from statistical physics, such as Replica Symmetry Breaking and energy landscapes. While providing profound macroscopic insights, these theories lack a discrete microscopic structure. In this paper, we propose a complementary, strictly discrete geometric model that maps these phenomena directly to the combinatorial topology of an $N$-dimensional Boolean hypercube. By defining the problem space purely through valid […]

Ver mais

In healthcare, predictive models increasingly inform patient-level decisions, yet little attention is paid to the variability in individual risk estimates and its impact on treatment decisions. For overparameterized models, now standard in machine learning, a substantial source of variability often goes undetected. Even when the data and model architecture are held fixed, randomness introduced by optimization and initialization can lead to materially different risk estimates for the same patient. This problem is largely obscured by standard evaluation practices, […]

Ver mais

About half a year ago, I organized all my deep learning-related videos in a handy blog post to have everything in one place. Since many people liked this post, and because I like to use my winter break to get organized, I thought I could free two birds with one key by compiling this list below. Here, you find a list of approximately 90 machine learning lectures I recorded in 2020 and 2021! Once again, I hope this […]

Ver mais

There are two things from our announcement today I wanted to highlight. First, a key part of our mission is to put very capable AI tools in the hands of people for free (or at a great price). I am very proud that we’ve made the best model in the world available for free in ChatGPT, without ads or anything like that.  Our initial conception when we started OpenAI was that we’d create AI and use it to […]

Ver mais

Someone has to prompt the Claudes, talk to customers, coordinate with other teams, decide what to build next. Engineering is changing and great engineers are more important than ever. — Boris Cherny, Claude Code creator, on why Anthropic are still hiring developers Tags: careers, anthropic, ai, claude-code, llms, coding-agents, ai-assisted-programming, generative-ai

Ver mais

arXiv:2603.26757v1 Announce Type: new Abstract: Does multi-view demonstration truly improve robot manipulation, or merely enhance cross-view robustness? We present a systematic study quantifying the performance gains, scaling behavior, and underlying mechanisms of multi-view data for robot manipulation. Controlled experiments show that, under both fixed and randomized backgrounds, multi-view demonstrations consistently improve single-view policy success and generalization. Performance varies non-monotonically with view coverage, revealing effective regimes rather than a simple “more is better” trend. Notably, multi-view data breaks the […]

Ver mais

arXiv:2502.06168v2 Announce Type: replace Abstract: We study an online dynamic pricing problem where the potential demand at each time period $t=1,2,ldots, T$ is stochastic and dependent on the price. However, a perishable inventory is imposed at the beginning of each time $t$, censoring the potential demand if it exceeds the inventory level. To address this problem, we introduce a pricing algorithm based on the optimistic estimates of derivatives. We show that our algorithm achieves $tilde{O}(sqrt{T})$ optimal regret even […]

Ver mais

arXiv:2602.03915v1 Announce Type: new Abstract: Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and generalized to new tasks. These have become foundational for image and video generation and, more recently, physical simulation. As existing tokenizers are designed for the explicit requirements of realistic visual perception of images, it is necessary to ask whether these approaches are optimal for scientific images, which exhibit a […]

Ver mais