arXiv:2604.17381v1 Announce Type: new Abstract: This paper proposes StrEBM, a structured latent energy-based model for source-wise structured representation learning. The framework is motivated by a broader goal of promoting identifiable and decoupled latent organization by assigning different latent dimensions their own learnable structural biases, rather than constraining the entire latent representation with a single shared energy. In this sense, blind source separation is adopted here as a concrete and verifiable testbed, through which the evolution of latent dimensions […]

Ver mais

In this article we develop a new method for summarizing a ranking distribution, textit{i.e.} a probability distribution on the symmetric group $mathfrak{S}_n$, beyond the classical theory of consensus and Kemeny medians. Based on the notion of textit{local ranking median}, we introduce the concept of textit{consensus ranking distribution} ($crd$), a sparse mixture model of Dirac masses on $mathfrak{S}_n$, in order to approximate a ranking distribution with small distortion from a mass transportation perspective. We prove that by choosing the […]

Ver mais

arXiv:2602.04078v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence. Yet, despite these advances, critical challenges remain — most notably, ensuring robustness to small input perturbations and generalization to out-of-distribution data. These critical challenges underscore the need to understand the underlying fundamental principles that govern robustness and generalization. Among the theoretical tools available, Lipschitz continuity plays a pivotal role in […]

Ver mais

I’m working on a project that involves a DQN trying to optimize some experiments that I have basically gamified to try to reward exploration/diversity of trajectories. I understand the fundamentals underlying DQN but haven’t worked extensively with them prior to this project so I don’t have much intuition built up on it yet. I’ve seen varying ideas regarding training params– I’m training for 200k steps (each step the agent makes 4 actions), but I’m not sure how I […]

Ver mais

The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have been used interchangeably in the literature, with the latter eventually being adopted as the standard critic loss in deep reinforcement learning (RL) architectures. In this work, we show […]

Ver mais

The Problem Nobody Names Six months into the medical CRM calendar project, I opened a PR and spent twenty minutes just figuring out which slice owned the appointment state. The code wasn’t broken. It wasn’t even obviously wrong. It had just quietly become something else. We kept calling it “technical debt” — but that wasn’t quite right either. Technical debt implies a conscious trade-off: ship now, fix later. What we had was different. Nobody made a bad call. Every decision […]

Ver mais

5,000 to 10,000 tokens. That’s what my AI agent was burning before changing a single line of frontend code. I started paying attention to this a while back. I’d ask the agent to do something small (“fix the padding on that card,” “swap this to the secondary variant”) and the actual edit would be maybe 200 tokens of real work. But the agent wouldn’t start with the edit. It would start with a search. Grepping the codebase, reading […]

Ver mais

arXiv:2512.00252v3 Announce Type: replace Abstract: Data assimilation (DA) is a cornerstone of scientific and engineering applications, combining model forecasts with sparse and noisy observations to estimate latent system states. Classical high-dimensional DA methods, such as the ensemble Kalman filter, rely on Gaussian approximations that are violated for complex dynamics or observation operators. To address this limitation, we introduce DAISI, a scalable filtering algorithm built on flow-based generative models that enables flexible probabilistic inference using data-driven priors. The core […]

Ver mais

arXiv:2601.00216v1 Announce Type: new Abstract: In medicine, large language models (LLMs) increasingly rely on retrieval-augmented generation (RAG) to ground outputs in up-to-date external evidence. However, current RAG approaches focus primarily on performance improvements while overlooking evidence-based medicine (EBM) principles. This study addresses two key gaps: (1) the lack of PICO alignment between queries and retrieved evidence, and (2) the absence of evidence hierarchy considerations during reranking. We present a generalizable strategy for adapting EBM to graph-based RAG, integrating […]

Ver mais