Knowledge catalogue
arXiv:2610.06795v1 Announce Type: new Abstract: We introduce Round-Trip KNN Clustering (RTKNNC), a graph-based method for finding cluster structure at several neighbourhood scales without requiring th
arXiv:2602.04448v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models introduce unique challenges for safety alignment due to their sparse routing mechanisms, which can enable d
arXiv:2610.04457v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve strong performance on image recognition and mobile vision applications, but their high-dimensional linear projections
arXiv:2610.04836v1 Announce Type: new Abstract: Remote sensing agents rely on perception, measurement, and raster analysis tools to solve Earth observation tasks. We refer to their judgments and quant
arXiv:2610.06847v1 Announce Type: new Abstract: Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural g
arXiv:2610.04338v1 Announce Type: new Abstract: Machine learning-based weather prediction (MLWP) has achieved strong performance in global weather forecasting. Recent Hierarchical Equal Area isoLatitu
arXiv:2610.05258v1 Announce Type: new Abstract: Ergodic control drives robots to spend time in each region in proportion to a spatial distribution of interest, making it well suited for dense spatiote
arXiv:2610.05908v1 Announce Type: new Abstract: Recent Text-to-Image (T2I) models achieve remarkable visual image generation performance, but they can still generate NSFW (Not-Safe-For-Work) contents,
arXiv:2610.05540v1 Announce Type: cross Abstract: Natural language to SQL (NL-to-SQL) benchmarks are foundational to progress in data analysis research, yet recent work has shown that widely-used benc
arXiv:2610.05066v1 Announce Type: new Abstract: Adapting step-distilled text-to-image (T2I) models through post-training incurs additional computational costs and affects native few-step generation be
arXiv:2610.03825v1 Announce Type: cross Abstract: A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on the first term. We measure the s
arXiv:2603.02348v2 Announce Type: replace Abstract: An agent meets a model as served: through an endpoint with a price card, a shared cache and other tenants, or on whatever hardware a self-hosted mod
arXiv:2610.06213v1 Announce Type: new Abstract: We study the sampling allocation of LinUCB in the small-gap regime, where the reward gaps are of order at most n^{-1/2} over the decision horizon n. Thi
arXiv:2610.04403v1 Announce Type: cross Abstract: Post-training quantization to the GGUF format's mixed-precision K-quants is commonly how open-weight language models reach consumer hardware, yet its
arXiv:2511.07312v2 Announce Type: replace Abstract: Real-world decision-making generally involves hidden information, that is, information that is unknown to one agent but possessed by another. Unfort
arXiv:2610.06021v1 Announce Type: new Abstract: Image editing should change only the attributes specified by an instruction while preserving everything else, yet current methods often make unintended
arXiv:2610.04095v1 Announce Type: new Abstract: Visual grounding models can enhance radiology workflows by linking report findings to image regions. This is particularly valuable for 3D CT, where find
arXiv:2610.06387v1 Announce Type: new Abstract: Large language models (LLMs) have achieved substantial performance gains through increases in model size, training data, and computational resources. Ho
arXiv:2610.05571v1 Announce Type: cross Abstract: In safety-critical domains such as autonomous driving, systems must be evaluated across a large number of environment conditions, often represented as
arXiv:2610.04905v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are a central tool in mechanistic interpretability. However, existing SAEs are primarily trained per layer. The modeling subs
arXiv:2606.19894v2 Announce Type: replace Abstract: Score-based diffusion models have achieved remarkable empirical success, motivating extensive theoretical work to establish their foundations. Howev
arXiv:2610.04696v1 Announce Type: new Abstract: Diffusion and flow models provide expressive policy classes for online reinforcement learning (RL), enabling multimodal behaviors and improved performan
arXiv:2410.18275v2 Announce Type: replace Abstract: In this paper, we study the problem of methodically obtaining a sufficient set of kinesthetic demonstrations, one at a time, such that a robot can b
arXiv:2610.04109v1 Announce Type: new Abstract: Real-world time series are frequently driven by exogenous events and structural shifts, rendering conventional forecasting based solely on historical nu
arXiv:2610.05831v1 Announce Type: new Abstract: Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study t
arXiv:2610.04003v1 Announce Type: cross Abstract: Few-Shot Class-Incremental Learning (FSCIL) requires models to continuously learn new classes from limited samples while retaining prior knowledge, un
arXiv:2610.04356v1 Announce Type: new Abstract: Comprehensive 3D scene understanding for autonomous driving requires modeling geometry, semantics, and motion. However, camera-based occupancy and scene
arXiv:2610.04269v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vuln
arXiv:2610.05141v1 Announce Type: new Abstract: Controlling the camera relative to a moving subject in an existing video is challenging: behaviors such as maintaining a frontal view require the camera
arXiv:2610.04810v1 Announce Type: new Abstract: Real-time agents are often evaluated with the world paused, or with decision time rounded to whole ticks (tick conversion). Tick conversion predicts alm
arXiv:2610.06605v1 Announce Type: new Abstract: Transformers asked to multiply multi-digit numbers in a single forward pass often fail, and interpretability studies of pretrained language models find
arXiv:2610.04690v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is standard for speech representation learning, but mainstream models are designed around single-speaker audio, limitin
arXiv:2610.04893v1 Announce Type: new Abstract: Industrial Internet of Things (IIoT) systems generate high-dimensional sensor telemetry from interconnected components, where faults can propagate acros
arXiv:2610.05325v1 Announce Type: new Abstract: In the field of deep learning, has seen significant advancements; however, shadow removal remains a persistent challenge owing to the variable sizes and
arXiv:2610.03076v1 Announce Type: cross Abstract: Neural network-based approaches have emerged as efficient alternatives to traditional optimization-based procedures for the calibration of stochastic
arXiv:2610.04130v1 Announce Type: cross Abstract: In this paper we investigate whether geometrically aligned astronomical representations are also scientifically interchangeable. We analyze every laye
arXiv:2610.04117v1 Announce Type: new Abstract: Policy mirror descent (PMD) has a mature finite-time theory in discounted Markov decision processes (MDPs), but less is known in the average-reward sett
arXiv:2304.03056v1 Announce Type: cross Abstract: In this work, we derive sharp non-asymptotic deviation bounds for weighted sums of Dirichlet random variables. These bounds are based on a novel integ
arXiv:2610.06308v1 Announce Type: cross Abstract: We study deterministic and randomized midpoint discretizations of Langevin dynamics for a target pi propto e^{-V}, where 0 prec alpha Ipreceqnabla^2Vp
arXiv:2610.05679v1 Announce Type: new Abstract: We study the offline gap between deterministic calibration distance C and its fractional relaxation L for binary unit-weight sequences under total absol
arXiv:2610.06804v1 Announce Type: new Abstract: A language model can give a correct answer more probability than any single incorrect answer and still usually sample an incorrect one, because the inco
arXiv:2610.04594v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) faithfulness detectors are widely used to audit reasoning models, yet a detector is itself a predictor whose verdicts are treat
arXiv:2610.06257v1 Announce Type: new Abstract: Foundation models can generate scientific code, but authoring a scientific simulator (an executable program encoding hypotheses about how mechanisms gen
arXiv:2610.06598v1 Announce Type: cross Abstract: Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from
arXiv:2610.06770v1 Announce Type: cross Abstract: Neural solvers for partial differential equations (PDEs) can approach an accurate solution while their parameters grow without bound. In such cases, t
arXiv:2610.04008v1 Announce Type: cross Abstract: Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing err
arXiv:2610.04017v1 Announce Type: new Abstract: Localizing behavior to individual components of a language model is a central goal of mechanistic interpretability. However, scoring components one at a
arXiv:2610.05290v1 Announce Type: new Abstract: In recent years, federated stochastic bilevel optimization has attracted increasing attention due to its wide range of applications in machine learning.
arXiv:2610.06229v1 Announce Type: new Abstract: Spherical data arise in many scientific applications. Often spherical transformers disregard the geometry of the underlying spherical domain, causing di
arXiv:2508.01802v2 Announce Type: replace Abstract: Soccer analytics draws on two kinds of information: spatio-temporal data describing where players and the ball are, and event data describing what t
arXiv:2610.05455v1 Announce Type: new Abstract: We propose a force-based model for social navigation of a tour-guide robot. Social forces due to various factors like obstacles, user position and headi
arXiv:2610.05544v1 Announce Type: new Abstract: Real-world deployment of active learning typically forces practitioners to choose an acquisition strategy before any data is labeled. This is a daunting
arXiv:2610.04940v1 Announce Type: new Abstract: A coding agent may safely modify one repository while silently breaking downstream services, libraries, or datastores that depend on it. Exhaustively ru
arXiv:2610.06513v1 Announce Type: cross Abstract: Evaluating text generation requires measuring how well the generated distribution matches the data distribution. For autoregressive models, this is do
arXiv:2603.07865v2 Announce Type: replace-cross Abstract: Text-to-audio (T2A) diffusion models generate high-quality audio but require tens of neural function evaluations (NFEs), resulting in substant
arXiv:2601.17657v4 Announce Type: replace Abstract: Robotic and autonomous systems need dense spatial cues, yet adding a dedicated depth estimator can duplicate visual processing already performed by
arXiv:2610.05029v1 Announce Type: new Abstract: Vision-language foundation models such as CLIP provide strong semantic representations, but their patch tokens are not directly optimized for dense metr
arXiv:2610.05642v1 Announce Type: cross Abstract: Emerging mission classes such as on-orbit servicing, satellite inspection, and active debris removal require trajectory design methods that are adapta
arXiv:2610.03931v1 Announce Type: new Abstract: This paper presents sparse calibration-based personalization for kernel-based gait phase and walking speed co-estimation from wearable inertial measurem
arXiv:2610.04203v1 Announce Type: new Abstract: Surface reconstruction under sparse-view settings remains challenging due to limited geometric cues. Volume rendering methods based on signed distance f