Knowledge catalogue
arXiv:2610.00031v1 Announce Type: new Abstract: Street-view imagery is increasingly used to infer urban attributes, but predictive accuracy alone does not reveal how much a photograph contributes beyo
arXiv:2610.01180v1 Announce Type: new Abstract: Despite the strong performance of Vision-Language Models (VLMs) on a wide range of visual question answering (VQA) tasks, these models consistently stru
arXiv:2610.00691v1 Announce Type: new Abstract: Recent joint audio-video generative models can synthesize realistic videos with synchronized sound, but typically generate audio as a single mixed track
arXiv:2610.02023v1 Announce Type: new Abstract: While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making
arXiv:2610.00377v1 Announce Type: new Abstract: Station-based weather forecasting supports daily life and economic activity, yet accurate forecasts require modeling complex spatial dependencies among
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfor
arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, r
arXiv:2610.02021v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by dat
Something keeps happening in frontier AI, and the explanation we are given is always one size larger than the event. An OpenAI research model, running in a supposedly offline training environment, hit
arXiv:2610.01005v1 Announce Type: cross Abstract: As artificial intelligence is increasingly deployed, algorithmic unfairness has raised growing concerns and intensified demands for transparent fairne
arXiv:2610.01763v1 Announce Type: new Abstract: Activation sparsity speeds up large language model (LLM) inference by setting unimportant activations to zero so that the corresponding computations can
arXiv:2610.01647v1 Announce Type: cross Abstract: In this article, we present our vision and recent advancements toward creating a decentralized system capable of learning from real-time data within b
arXiv:2610.01282v1 Announce Type: new Abstract: The rapid evolution of Intelligent Transportation Systems and Logistics (ITS&L) has become a cornerstone of the modern social economy, relying heavily o
arXiv:2610.00341v1 Announce Type: cross Abstract: As Large Multimodal Models (LMMs) transition toward natively unified architectures, evaluating their safety in synergistic harmful image-text generati
arXiv:2610.00878v1 Announce Type: cross Abstract: General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary init
arXiv:2510.08944v2 Announce Type: replace Abstract: Real-world time-series regression often involves non-stationarity, heteroscedasticity, and regime changes, under which recent prediction errors may
arXiv:2610.00827v1 Announce Type: cross Abstract: Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one ans
arXiv:2610.01012v1 Announce Type: new Abstract: Video-to-speech synthesis aims to generate natural-sounding speech from silent talking-face videos while ensuring phonetic accuracy. A fundamental chall
arXiv:2610.01471v1 Announce Type: cross Abstract: Large language models now generate code, documentation, and analyses, and are increasingly used to review such output. We ask when a second review by
arXiv:2610.00398v1 Announce Type: new Abstract: Overnight impedance pneumography (IP) is used to monitor paediatric respiratory health. Its current clinical readout, the Expiratory Variability Index (
arXiv:2610.01742v1 Announce Type: cross Abstract: Equipping artificial agents with spatial intelligence requires a comprehensive generative prior over the dynamic 3D world. We propose World Motion Mod
arXiv:2602.14929v2 Announce Type: replace Abstract: Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challeng
arXiv:2609.39810v1 Announce Type: new Abstract: Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still
arXiv:2609.38194v1 Announce Type: cross Abstract: Despite the importance for interpretability, decision trees face severe scalability challenges. Existing global optimal methods are often limited by b
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent metho
arXiv:2609.38737v1 Announce Type: new Abstract: Desk-based learning and creative activities benefit from handwritten engagement. However, current generative AI tools deliver guidance through a separat
arXiv:2609.38645v1 Announce Type: cross Abstract: Models are usually aligned based on their observed outputs, using demonstrations, preference data, or reward signals. These objectives reward response
arXiv:2609.39225v1 Announce Type: new Abstract: Argument structure prediction (ASP) constructs complete argument structures from discourse by identifying argumentative units and their relations. While
arXiv:2609.39173v1 Announce Type: cross Abstract: In this paper, we consider asymptotic properties of the support vector machine (SVM) in high-dimension, low-sample-size (HDLSS) settings under a spike
arXiv:2609.38878v1 Announce Type: cross Abstract: A large audio language model (LALM) turns a minute of speech into 750-1,500 tokens and prefills every one. Image-token pruning often cuts after the la
arXiv:2609.39579v1 Announce Type: new Abstract: Deploying vision-and-language navigation (VLN) agents in unseen environments remains challenging because unfamiliar layouts and visual conditions can ca
arXiv:2609.39687v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises student
arXiv:2609.38806v1 Announce Type: cross Abstract: Next-token prediction has driven remarkable progress in large language models, yet a growing body of evidence suggests that they can struggle on probl
arXiv:2609.39300v1 Announce Type: new Abstract: Recent advances in computer vision have made broadcast sports videos increasingly useful for event analysis, performance assessment, and player-safety a
Every time I needed to explore a dataset quickly, the same wall appeared — cleaning boilerplate, encoding errors, deciding which chart actually makes sense. The mechanical parts aren't interesting, th
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabil
arXiv:2609.38812v1 Announce Type: new Abstract: Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments.
arXiv:2609.40014v1 Announce Type: new Abstract: Detecting violence after it begins is important from recognizing behavioral cues that appear immediately beforehand. This work studies short-horizon pre
arXiv:2609.39124v1 Announce Type: new Abstract: Generative models for tabular data are typically trained separately for each dataset, limiting knowledge transfer and requiring the storage of many spec
arXiv:2609.38781v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) offer a promising approach for recovering numerical data from scientific charts, but their ability to reconst
arXiv:2609.39754v1 Announce Type: new Abstract: Robot foundation policies predict action chunks, but how many actions to execute before replanning depends on the current task phase. We introduce Chunk
arXiv:2609.39523v1 Announce Type: new Abstract: Causal foundation models (CFMs) amortise causal inference over priors of synthetic structural causal models (SCMs), predicting the effect of an experime
arXiv:2609.38253v1 Announce Type: cross Abstract: Text-to-image (T2I) models have substantially improved in language understanding, in-image text rendering, and visual composition, while their safety
arXiv:2609.40253v1 Announce Type: cross Abstract: Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily re
arXiv:2609.39784v1 Announce Type: new Abstract: Can heterogeneous physical degradation systems benefit from joint pretraining and move beyond system-specific prognostics toward reusable cross-system r
arXiv:2609.38810v1 Announce Type: cross Abstract: As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual sign
arXiv:2609.39625v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be u
arXiv:2609.40124v1 Announce Type: new Abstract: Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that re
arXiv:2609.38777v1 Announce Type: new Abstract: A central goal of vision-language model (VLM) distillation is to transfer both the teacher's language capabilities and its visual understanding. However
arXiv:2609.38517v1 Announce Type: new Abstract: Lower error from a text-conditioned neural surrogate does not, by itself, show that the model uses the meaning of the text. We examine this attribution
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, b
arXiv:2609.31688v2 Announce Type: replace Abstract: In verifiable domains such as math and coding, finding one correct solution among many attempts can matter more than the pass rate of each attempt.
arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different re
arXiv:2601.21857v2 Announce Type: replace Abstract: We revisit diffusion-based generation for structured visual content and identify a fundamental limitation of existing approaches: foreground preserv
arXiv:2609.39575v1 Announce Type: cross Abstract: Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To
arXiv:2609.39284v1 Announce Type: cross Abstract: While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning,
arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mis
arXiv:2609.38346v1 Announce Type: new Abstract: When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves
NVIDIA Nemotron 3.5 ASR was fine‑tuned on 133.7 h of Saudi Najdi and Hijazi speech using weighted replay with FLEURS data, duration bucketing, and selective encoder unfreezing; this reduced the target