Knowledge catalogue
arXiv:2605.04356v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly benefic
arXiv:2605.04764v1 Announce Type: new Abstract: Large language models are increasingly used as surrogate models for low-data optimization, but their optimizer-facing prediction and its uncertainty rem
arXiv:2605.04709v1 Announce Type: new Abstract: A central challenge of visual control with model-based reinforcement learning (RL) is reliable long-horizon planning: long rollouts with learned latent
arXiv:2505.18244v3 Announce Type: replace Abstract: Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale,
arXiv:2605.04998v1 Announce Type: cross Abstract: Chord progression generation is practically important but understudied. Most large-scale symbolic music systems target melody, multi-track arrangement
arXiv:2605.04164v1 Announce Type: new Abstract: Wildfires are a major producer of fine particulate matter, impacting human health and the electrical grid. Accurately forecasting smoke impacts over lon
arXiv:2603.16368v2 Announce Type: replace-cross Abstract: Striking a balance between efficiency and transparent motion is a core challenge in human-robot collaboration, as highly expressive movements
arXiv:2605.04054v1 Announce Type: new Abstract: Achieving endogenous regime switching is crucial for the emergence of autonomous intelligence, yet remains a central challenge for existing machine lear
arXiv:2605.03242v1 Announce Type: new Abstract: Tool-using agent systems powered by large language models (LLMs) are increasingly deployed across web, app, operating-system, and transactional environm
arXiv:2605.04082v1 Announce Type: new Abstract: Model-based solutions for nitrous oxide (N2O) emissions from wastewater treatment plants (WWTP) are informed by operational datasets designed to control
arXiv:2605.04727v1 Announce Type: new Abstract: Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representat
arXiv:2605.04255v1 Announce Type: cross Abstract: Many machine learning problems involve data supported on curved spaces such as spheres, rotation groups, hyperbolic spaces, and general Riemannian man
arXiv:2605.04960v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO
arXiv:2605.05179v1 Announce Type: new Abstract: By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical ave
arXiv:2605.04085v1 Announce Type: cross Abstract: Objectives: Large language models (LLMs) are increasingly used for clinical text summarization, yet structured methods to assess associated patient sa
arXiv:2605.03227v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning. However, their ability to perform ex
arXiv:2603.13824v2 Announce Type: replace-cross Abstract: Recent advances in text-to-audio generation enable models to translate natural-language descriptions into diverse musical output. However, the
arXiv:2605.04410v1 Announce Type: new Abstract: The evaluation of explainable AI (XAI) methods is affected by a lack of standardization. Metrics are inconsistently defined, incompletely reported, and
arXiv:2605.04548v1 Announce Type: new Abstract: Accurate early warning of vineyard disease risk from environmental observations is essential for timely intervention and more sustainable crop protectio
arXiv:2605.04719v1 Announce Type: new Abstract: Tool-integrated Text-to-SQL parsing has emerged as a promising paradigm, framing SQL generation as a sequential decision-making process interleaved with
arXiv:2605.04664v1 Announce Type: new Abstract: Anomaly detection methods can be very useful in identifying interesting or concerning events. In this work, we develop and examine new probabilistic ano
arXiv:2605.03871v1 Announce Type: new Abstract: Language models encode substantial evaluative knowledge from pretraining, yet current post-training methods rely on external supervision (human annotati
arXiv:2605.04722v1 Announce Type: new Abstract: Input Convex Neural Networks (ICNNs) are commonly used in a two-stage manner: one first trains a convex network and then minimizes it over its input in
arXiv:2605.04501v1 Announce Type: new Abstract: In recent years, object detection has achieved significant progress, especially in the field of open-vocabulary object detection. Unlike traditional met
arXiv:2605.04266v1 Announce Type: new Abstract: Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the p
arXiv:2605.04904v1 Announce Type: new Abstract: In this paper, we explore deep learning techniques for individual identification of animals based on their skin patterns. Individual identification is c
arXiv:2605.04368v1 Announce Type: new Abstract: Differential temporal difference (TD) methods are value-based reinforcement learning algorithms that have been proposed for infinite-horizon problems. T
arXiv:2605.05082v1 Announce Type: cross Abstract: We externally validated three deep learning models (DenseNet121, ViT-B/32, and ResNet50) for predicting mammographic breast density from breast ultras
arXiv:2605.04651v1 Announce Type: cross Abstract: Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memor
arXiv:2605.04882v1 Announce Type: new Abstract: Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairne
arXiv:2605.04702v1 Announce Type: new Abstract: Identity-preserving text-to-video generation (IPT2V) empowers users to produce diverse and imaginative videos with consistent human facial identity. Des
arXiv:2605.04084v1 Announce Type: new Abstract: Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-
arXiv:2506.20911v2 Announce Type: replace Abstract: We develop a cost-efficient neurosymbolic agent to address challenging multi-turn image editing tasks such as ``Detect the bench in the image while
arXiv:2510.00468v4 Announce Type: replace Abstract: We provide evidence that eigenanalysis of the empirical neural tangent kernel (eNTK) can surface feature directions in trained neural networks. Acro
arXiv:2605.04666v1 Announce Type: new Abstract: The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory
arXiv:2605.04993v1 Announce Type: new Abstract: Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimizati
arXiv:2605.05034v1 Announce Type: new Abstract: Despite the strong performance of Convolutional Neural Networks (CNNs) in disease classification, their effectiveness often depends on access to large a
arXiv:2510.01641v3 Announce Type: replace Abstract: Recent advancements in image motion deblurring, driven by CNNs and transformers, have made significant progress. Large-scale pre-trained diffusion m
arXiv:2505.03597v2 Announce Type: replace Abstract: Fixed-length fingerprint representations, which map each fingerprint to a compact and fixed-size feature vector, are computationally efficient and w
arXiv:2605.04519v1 Announce Type: new Abstract: Single-cell ATAC-seq (scATAC-seq) enables high-resolution mapping of chromatin accessibility, yet privacy regulations and data size constraints hinder m
arXiv:2605.04071v1 Announce Type: new Abstract: Autoregressive models can predict clinical events, but generating patient-conditioned multi-step trajectories that respond to intervention tokens and te
arXiv:2605.05077v1 Announce Type: new Abstract: Accurate image segmentation is essential for modern computer vision applications such as image editing, autonomous driving, and medical image analysis.
arXiv:2605.04421v1 Announce Type: new Abstract: Continuous-time (CT) Transformers improve irregular and long-range modeling over CT-RNNs by exploiting inputs or outputs embeddings with continuous dyna
arXiv:2605.04157v1 Announce Type: new Abstract: SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating
arXiv:2511.01202v3 Announce Type: replace-cross Abstract: Despite the unprecedented empirical triumphs of LLMs across diverse real-world applications, the prevailing research paradigm remains overwhel
arXiv:2512.22671v2 Announce Type: replace Abstract: Structured width pruning of GLU-MLP layers, guided by the Maximum Absolute Weight (MAW) criterion, reveals a systematic dichotomy in how reducing th
arXiv:2602.23547v2 Announce Type: replace Abstract: Sentences like 'She will go to France or Spain, or perhaps to Germany or France.' appear formally redundant, yet become acceptable in contexts such
arXiv:2605.04065v1 Announce Type: new Abstract: Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, exi
arXiv:2605.03090v1 Announce Type: cross Abstract: For over a century, the electric grid has relied on a single statistical assumption: load diversity, the principle that the uncorrelated demands of mi
arXiv:2605.04590v1 Announce Type: new Abstract: Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application
arXiv:2605.03986v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) built using AI agents fulfill a variety of user intents that may be used to design and build a family of related applications.
arXiv:2605.03205v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowled
arXiv:2605.04327v1 Announce Type: new Abstract: We propose an architecture for integrating high-level, human-provided safety rules and operator-aligned semantic preferences into autonomous robot navig
arXiv:2605.04572v1 Announce Type: cross Abstract: Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors l
arXiv:2605.02902v1 Announce Type: cross Abstract: Recommendation feeds work well when people are simply browsing, and search works well when they can formulate a query. Between these two cases is a co
arXiv:2605.04678v1 Announce Type: cross Abstract: Latent actions serve as an intermediate representation that enables consistent modeling of vision-language-action (VLA) models across heterogeneous da
arXiv:2605.04515v1 Announce Type: new Abstract: While Video Large Language Models (Video-LLMs) excel in general understanding, they exhibit systematic deficits in fine-grained physical reasoning. Exis
arXiv:2605.04649v1 Announce Type: new Abstract: High-precision assembly frequently involves tight-tolerance insertions, where even slight pose errors can cause jamming or excessive interaction forces,
arXiv:2604.01496v2 Announce Type: replace-cross Abstract: We introduce SWE-ZERO to SWE-HERO, a two-stage SFT recipe that achieves state-of-the-art results on SWE-bench by distilling open-weight fronti
arXiv:2605.04535v1 Announce Type: new Abstract: Inferring continuum models directly from video is hampered by two facts: the recorded field is uncalibrated image intensity rather than a physical state