Explore documented scientific discoveries, original research and new scientific developments. Search the library by topic, category or date.
arXiv:2610.31729v1 Announce Type: new Abstract: In quantum information theory, standard notions typically presuppose a fixed partition of the world into subsystems, encoded in a tensor product structure of the Hilbert space. Yet, in some scenarios, the subsystem structure is not uniquely fixed.
arXiv QuantumRead article →arXiv:2610.31694v1 Announce Type: new Abstract: Fault-tolerant quantum compilers implement gates through Pauli-product measurements and classical feedback. Verifying such a compiler requires reasoning about the quantum state and the recorded outcomes together: a correction reads an outcome, a gate's internal outcomes must be hidden from its caller, and an application's outcomes must survive optimization.
arXiv QuantumRead article →arXiv:2610.31981v1 Announce Type: new Abstract: On the simplest non-Euclidean manifold, the 1D flat torus, we exhibit a distribution where a recently proposed extension of Riemannian flow matching is globally optimized by a velocity field that pushes samples away from the data distribution.
arXiv MLRead article →arXiv:2610.31968v1 Announce Type: new Abstract: Accurate ambulance travel time estimation is critical for emergency medical dispatch, yet existing decision-support practices often rely on static lookup tables or simplified assumptions regarding how ambulance travel time differs from ordinary passenger-car travel.
arXiv MLRead article →arXiv:2610.31955v1 Announce Type: new Abstract: Recent work from Anthropic introduced a new interpretability tool, called the Jacobian lens (J-lens, Gurnee et al., 2026). This method identified linear directions in the hidden states of frontier language models that had properties reminiscent of working memory-like representations.
arXiv MLRead article →arXiv:2610.31948v1 Announce Type: new Abstract: Reporting the best of $M$ noisy, unbiased scores overstates the winner's value by up to $c\sqrt{V}$, where $V$ is the total noise variance and the sharp constant $c$ depends on how the noise is dependent. It was known only at the two extremes, arbitrary dependence ($\sqrt{(M-1)/M}$) and i.i.d. noise.
arXiv MLRead article →arXiv:2610.31944v1 Announce Type: new Abstract: Emergency medical dispatch increasingly relies on AI-enabled decision support systems when making ambulance dispatch decisions. In this process, accurate ambulance travel time estimates are essential for timely resource allocation and prehospital care. However, existing ambulance travel time estimation approaches typically produce only single point predictions.
arXiv MLRead article →arXiv:2610.31943v1 Announce Type: new Abstract: Looped language models apply one block of layers repeatedly, and the design pays off only if depth is reusable: loop steps beyond the trained budget must remain usable at inference. We ask whether that rests on normalising the state between loop steps, as the released Ouro models do, or on agreement between the loop a model is trained with and the loop it is run with.
arXiv MLRead article →arXiv:2610.31935v1 Announce Type: new Abstract: PDE foundation models enable data-efficient adaptation but are deployed autoregressively, so short-horizon accuracy need not imply reliable simulation. We ask whether the short-horizon advantage of a foundation-model recipe persists when its predictions are repeatedly fed back as inputs for a long horizon.
arXiv MLRead article →arXiv:2610.31931v1 Announce Type: new Abstract: We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural network is the end of a path of small discrete decisions: a sign, a shift by a power of two, a zero gate, an index into a shared table.
arXiv MLRead article →arXiv:2610.31913v1 Announce Type: new Abstract: Large neural networks are increasingly deployed with 1-4 bit weights and 16- or 32-bit activations, yet their dot products still use one multiplier per element. We show that a length-n dot product with k-bit weight codes can be computed with n+2^k additions and at most 2^k decodes and 2^k multiplications.
arXiv MLRead article →arXiv:2610.31909v1 Announce Type: new Abstract: We compare two canonical ways to recover hierarchical clustering from an underlying density $f$: the \emph{density cluster tree} given by connected components of superlevel sets $\{f\ge\lambda\}$, and a \emph{spectral hierarchy} obtained by applying single linkage to diffusion distances induced by a Laplacian operator.
arXiv MLRead article →arXiv:2610.31897v1 Announce Type: new Abstract: Scaling laws continue to reward increases in model scale, while the resulting computational and memory demands drive greater reliance on cloud infrastructure for inference. Yet unreliable network connectivity, communication delays, and privacy requirements can make such reliance impractical, motivating local execution on edge devices.
arXiv MLRead article →arXiv:2610.31889v1 Announce Type: new Abstract: Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process. This decoupling directly enables compositional generation and inference-time scaling, where sample quality can be refined simply by increasing sampling steps.
arXiv MLRead article →arXiv:2610.31884v1 Announce Type: new Abstract: While animals and people tend to learn a task more quickly and reliably when they first train on simpler versions of it, curriculum learning's effectiveness in artificial settings varies, and appears substantially greater in reinforcement learning than in supervised learning.
arXiv MLRead article →arXiv:2610.31869v1 Announce Type: new Abstract: Covariate-aware time series foundation models (TSFMs) accept a future path for a control variable and return a forecast, inviting what-if queries. The query is interventional; the models are trained on observational data. We determine whether their answers are the conditional slope $\partial E[Y|X]$ or the interventional effect $\partial E[Y|do(X)]$, at three levels.
arXiv MLRead article →arXiv:2610.31867v1 Announce Type: new Abstract: Synthetic rewrites, where a language model rewrites a natural document e.g. into a target style, are now a standard ingredient of pretraining corpora. However, critical aspects of their use remain poorly understood, such as how much compute should be spent rewriting training data and whether a model trained on rewrites can outperform the rewriter.
arXiv MLRead article →arXiv:2610.31862v1 Announce Type: new Abstract: This article provides an introduction to the mathematical foundations and algorithmic frameworks used to align Large Language Models (LLMs) with human intentions, preferences, and values. We discuss standard alignment techniques, such as fine-tuning (SFT), reinforcement learning with human feedback (RLHF), and direct preference optimization (DPO).
arXiv MLRead article →arXiv:2610.31855v1 Announce Type: new Abstract: Partial differential equations (PDEs) are indispensable tools for modeling complex phenomena in physics and engineering. Physics-Informed Neural Networks (PINNs) have emerged as a powerful alternative to traditional numerical solvers by directly incorporating physical constraints into neural network loss functions.
arXiv MLRead article →arXiv:2610.31850v1 Announce Type: new Abstract: Urban region representation learning encodes heterogeneous urban signals, such as mobility flows, points of interest, and land-use patterns, into unified embeddings for downstream tasks, including check-in prediction, crime forecasting, and service demand estimation.
arXiv MLRead article →arXiv:2610.31819v1 Announce Type: new Abstract: Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model. Traditionally, a fundamental characteristic of speculative decoding is that it is lossless with respect to the verifier distribution, guaranteeing speed without sacrificing quality.
arXiv MLRead article →arXiv:2610.31818v1 Announce Type: new Abstract: Mixture-of-experts (MoE) transformers, the standard backbone for modern large-scale deep learning, employ conditional computation: only a sparse subset of model weights is used in each forward pass. In MoE transformers, this sparsity arises in the MoE operator, which generalizes the multi-layer perceptron in the classical transformer.
arXiv MLRead article →arXiv:2610.31809v1 Announce Type: new Abstract: A bug report describes what went wrong, but rarely where the code should change. Existing repository-level localization methods often let language models iteratively decide what code to inspect next, requiring repeated model calls and substantial token usage. We investigate whether these inspection decisions can instead be planned before source retrieval.
arXiv MLRead article →arXiv:2610.31791v1 Announce Type: new Abstract: Automated research is largely evaluated by benchmark performance, but the value of research rarely reduces to a single score. Humans judge a work's holistic contribution through peer review, which is hard to model because it is noisy and depends on many factors. However, what if, given only the paper, we could predict its peer-review decision directly?
arXiv MLRead article →