Knowledge catalogue
arXiv:2609.32108v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models leverage large-scale pretraining to ultimately achieve generalist manipulation. Deployed VLA policies must support c
arXiv:2609.31796v1 Announce Type: new Abstract: Activation probes are increasingly used to monitor LLMs in deployment. A probe is typically trained under one inference configuration, then used under w
arXiv:2609.34215v1 Announce Type: cross Abstract: Evaluating how LLM agents recover from mid-task failures is central to deploying reliable agentic systems. Existing checkpoint-based benchmarks measur
arXiv:2609.34929v1 Announce Type: new Abstract: Language models are increasingly used to sample from a specified distribution, for instance, to simulate survey respondents or generate synthetic data.
arXiv:2609.35629v1 Announce Type: new Abstract: Attention often concentrates on a small subset of tokens in the context, but which subset matters changes from one query to the next. To exploit this ch
arXiv:2609.33011v1 Announce Type: new Abstract: We study contextual dueling bandits with general function approximation under the Bradley-Terry-Luce (BTL) preference model. A key challenge in this set
arXiv:2609.33126v1 Announce Type: new Abstract: Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language m
arXiv:2609.35292v1 Announce Type: new Abstract: Recent representation alignment (REPA) methods accelerate diffusion transformer training by aligning projections of the transformer's hidden states with
arXiv:2609.33641v1 Announce Type: cross Abstract: Several businesses apply maintenance, repair, and overhaul (MRO) principles to the life-cycle of their existing products. In cases like casted gas tur
arXiv:2609.33667v1 Announce Type: new Abstract: Attributing and controlling model behavior during training requires identifying each example's contribution quickly enough to act before the next update
arXiv:2609.34499v1 Announce Type: new Abstract: Graph neural networks (GNNs) excel at representation learning on Knowledge Graphs (KGs), achieving stateof-the-art performance on tasks like link predic
arXiv:2609.35333v1 Announce Type: new Abstract: Algorithm Distillation (AD) has demonstrated the remarkable ability of Transformers to perform in-context reinforcement learning without explicit weight
arXiv:2609.32183v1 Announce Type: new Abstract: High-resolution plant imaging enables detailed characterization of plant morphology, but dense scientific analysis remains limited by costly pixel-level
arXiv:2609.32722v1 Announce Type: new Abstract: *Reinforcement learning (RL)* can induce substantial reasoning capabilities in large language models (LLMs), but how much of this capability transfers a
arXiv:2609.34271v1 Announce Type: new Abstract: Although recent 3D generative models produce increasingly realistic assets, controllable 3D asset editing remains challenging. Existing methods are limi
arXiv:2609.35707v1 Announce Type: new Abstract: Recent progress in machine learning is driven by large-scale foundation models, where scaling laws and finding optimal scaling prescriptions for archite
arXiv:2609.32837v1 Announce Type: new Abstract: Ultrasound (US) acquisition depends on the operator's ability to interpret anatomy and anticipate how the view will change with probe motion. Many robot
arXiv:2609.33518v1 Announce Type: new Abstract: Recent 3D large multimodal models (3D-LMMs) rely on a visual bottleneck to compress complex 3D scene evidence into a limited number of visual tokens com
arXiv:2609.33436v1 Announce Type: new Abstract: Attention provides direct access to past representations, but retaining an ever-growing history is costly. Recurrent models bound persistent state, yet
arXiv:2609.33239v1 Announce Type: cross Abstract: Diffusion policies represent multimodal action distributions, but an advantage-weighted update does not specify how to sample from the resulting targe
arXiv:2609.32640v1 Announce Type: cross Abstract: We present Schur-Neural KF (SN-KF), a learning-based correction to the extended Kalman filter (EKF) that preserves the probabilistic conditioning inte
arXiv:2609.33399v1 Announce Type: new Abstract: In realistic education, a solution is often expressed not only in words but in a drawing--a circuit, a geometric construction, a function plot--and a te
arXiv:2609.32391v1 Announce Type: cross Abstract: Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requir
arXiv:2609.34044v1 Announce Type: new Abstract: Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pr
arXiv:2609.33218v1 Announce Type: new Abstract: Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimi
arXiv:2510.21330v2 Announce Type: replace Abstract: Unnormalized probability distributions are central to modeling complex physical systems across various scientific domains. Traditional sampling meth
arXiv:2609.33179v1 Announce Type: cross Abstract: Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to w
arXiv:2609.32036v1 Announce Type: new Abstract: We introduce ScreenHaystack, a dynamic needle-in-a-haystack benchmark for evaluating spatial reliability in GUI grounding. Instead of testing each targe
arXiv:2511.15565v3 Announce Type: replace Abstract: Human pose forecasting predicts future human poses from past observations for applications including action recognition, sports analysis, and human-
arXiv:2609.34970v1 Announce Type: new Abstract: Safety-aligned LLMs can exhibit emergent misalignment (EM): narrow domain adaptation unexpectedly triggers catastrophic safety failures across unrelated
arXiv:2609.34277v1 Announce Type: new Abstract: Pathological assessment relies on recognizing fine-grained visual details in histological images. Vision-language models (VLMs) increasingly support pat
arXiv:2609.33694v1 Announce Type: new Abstract: Vision-language models (VLMs) answer visual questions by combining visual information extraction with downstream problem solving. We investigate a funda
arXiv:2609.32456v1 Announce Type: new Abstract: World modeling under partial observation requires reasoning about the complete worlds that remain compatible with limited visual evidence. Occluded obje
arXiv:2609.31737v1 Announce Type: new Abstract: The thermal behavior of wood is a critical factor in advanced material assembly. However, pixel-level thermal analysis remains fundamentally constrained
arXiv:2609.32698v1 Announce Type: new Abstract: Recent vision-language-action (VLA) policies demonstrate promising generalization across diverse short-horizon tasks. However, they remain unreliable on
arXiv:2609.34235v1 Announce Type: new Abstract: Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their
arXiv:2609.33780v1 Announce Type: new Abstract: Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present a comprehensive study of route dive
arXiv:2602.07919v2 Announce Type: replace-cross Abstract: Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods
arXiv:2609.32966v1 Announce Type: new Abstract: Reinforcement learning (RL) trains representations on data selected by the agent's policy, which then uses the resulting returns to guide its next choic
arXiv:2603.02772v2 Announce Type: replace Abstract: Motion planners tuned under nominal conditions can fail when execution conditions change. Existing differentiable adaptation methods provide efficie
arXiv:2609.35432v1 Announce Type: new Abstract: Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions. This directness ties a policy to
arXiv:2609.32746v1 Announce Type: cross Abstract: While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several
arXiv:2609.32689v1 Announce Type: new Abstract: LLM-based agents are increasingly used for time-series forecasting because they can organise contextual information, perform multi-step analysis, and gu
arXiv:2410.02331v3 Announce Type: replace Abstract: The increasing demand for transparent and reliable models, particularly in high-stakes decision-making areas such as medical image analysis, has led
arXiv:2609.32268v1 Announce Type: new Abstract: Standard autoencoder (AE) inference uses a single encoder-decoder pass, though the latent may not be optimal for each sample under a fixed decoder. We a
arXiv:2609.31788v1 Announce Type: new Abstract: Progress in 3D CT report generation is usually sought in increasingly sophisticated architectures and larger pools of training data. We find instead tha
arXiv:2609.34736v1 Announce Type: cross Abstract: Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly
arXiv:2609.34294v1 Announce Type: new Abstract: Unsupervised visible-infrared person re-identification (USL-VI-ReID) learns person representations that can be compared across modalities without identi
arXiv:2602.05464v2 Announce Type: replace-cross Abstract: Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent methods construct conditional sub
arXiv:2609.33082v1 Announce Type: new Abstract: Developmental screening videos show how children perform specific behaviors, but clinical records usually contain outcomes rather than descriptions of w
arXiv:2609.34479v1 Announce Type: new Abstract: Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding.
arXiv:2609.34801v1 Announce Type: new Abstract: Foundation models are increasingly adapted to individual users, but an apparent personalization gain can simply reflect a stronger population model. Thi
arXiv:2609.31801v1 Announce Type: new Abstract: Complex systems such as vehicles, patients, or genomes emit discrete event sequences whose operative question is causal, not predictive: which events ca
arXiv:2511.14422v2 Announce Type: replace-cross Abstract: U-shaped split federated learning (U-SFL) enables resource-constrained Internet of Things devices to collaboratively train models with an edge
arXiv:2609.32529v1 Announce Type: new Abstract: Open-prompt detectors allow users to specify targets with text, visual exemplars, or both. We argue that existing designs underuse the visual modality i
arXiv:2609.32340v1 Announce Type: new Abstract: Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an
arXiv:2609.34538v1 Announce Type: new Abstract: Looped Transformers reuse a shared block across recurrent depths, making autoregressive decoding expensive because every generated token requires many s
arXiv:2609.34604v1 Announce Type: new Abstract: World models learn environment dynamics from interaction experience. These dynamics depend on the current state and actions, as well as on properties th
arXiv:2609.35576v1 Announce Type: cross Abstract: Large language models are increasingly deployed as stateful assistants that retain information across interactions and use tools to read, modify, and
arXiv:2609.32546v1 Announce Type: new Abstract: Large language models can generate several records within one autoregressive completion, making earlier answers available as context for later records.