SigLIP2 for aerial fire risk classification
arXiv:2610.03689v1 Announce Type: new Abstract: We examine the transfer of a pretrained SigLIP2 image encoder to seven class fire risk classification from aerial imagery. We introduce a reproducible p
Knowledge catalogue
arXiv:2610.03689v1 Announce Type: new Abstract: We examine the transfer of a pretrained SigLIP2 image encoder to seven class fire risk classification from aerial imagery. We introduce a reproducible p
arXiv:2610.03019v1 Announce Type: new Abstract: Hybrid statistical-neural pipelines often assume that a successful statistical first stage leaves a cleaner and more learnable residual target. We exami
arXiv:2610.03679v1 Announce Type: new Abstract: The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this ev
arXiv:2610.03482v1 Announce Type: new Abstract: Hallucination detection is particularly important for medical language models, but repeated-sampling approaches are expensive and existing uncertainty-h
arXiv:2610.02953v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compress
arXiv:2610.02338v1 Announce Type: cross Abstract: A growing body of work suggests that tactile sensing gives robot policies contact information that complements vision in dexterous manipulation. Howev
arXiv:2610.02521v1 Announce Type: new Abstract: Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observatio
arXiv:2610.03265v1 Announce Type: cross Abstract: Large-scale pre-training has improved the generalization of neural operators across diverse PDEs. However, existing PDE foundation models still strugg
arXiv:2610.02660v1 Announce Type: new Abstract: Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Trans
arXiv:2610.03215v1 Announce Type: new Abstract: StanceEval 2026 is the second edition of the StanceEval shared task series on stance detection in Arabic social media text. Stance detection aims to ide
arXiv:2610.02722v1 Announce Type: new Abstract: Structural connectivity (SC) and functional connectivity (FC) provide complementary information on interactions between brain regions and are widely use
arXiv:2610.02991v1 Announce Type: new Abstract: Lower-limb exoskeletons have made considerable progress in reducing energy expenditure during walking. However, designing optimal assistance strategies
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. People really hate AI, so why can’t they get enough? —Will Dou
arXiv:2610.03052v1 Announce Type: new Abstract: Large language models (LLMs) contain broad knowledge, but they cannot access all of it reliably. We study this problem through knowledge accessibility,
arXiv:2610.03225v1 Announce Type: new Abstract: We present the Neuro-Physical Inverter (NPI), a modular, uncertainty-aware framework for geophysical inversion that couples ensemble-based conditioning
arXiv:2610.02383v1 Announce Type: cross Abstract: Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however,
arXiv:2602.18674v2 Announce Type: replace Abstract: We present a theoretical study of the robustness of parameterized neural networks to random input perturbations. Specifically, we analyze local robu
arXiv:2610.02487v1 Announce Type: new Abstract: High-fidelity simulations are essential to scientific and engineering design, but can be expensive to run repeatedly. Learned surrogates offer a faster
arXiv:2610.03324v1 Announce Type: new Abstract: The scale of online content makes hate-speech moderation challenging, while Large Language Models (LLMs) enable harmful material to be produced and adap
arXiv:2502.03979v3 Announce Type: replace-cross Abstract: One of the most significant challenges in Music Emotion Recognition (MER) comes from the fact that emotion labels can be heterogeneous across
arXiv:2610.02779v1 Announce Type: new Abstract: In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video gener
arXiv:2610.03693v1 Announce Type: new Abstract: Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete re
arXiv:2610.02372v1 Announce Type: new Abstract: Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must
arXiv:2610.03147v1 Announce Type: cross Abstract: Streaming sensor applications routinely suffer from delayed or missing observations caused by faults, communication losses, or environmental interfere
arXiv:2610.03224v1 Announce Type: cross Abstract: Diffusion models can synthesise contrast-enhanced CT (CECT) from non-contrast CT (NCCT), avoiding contrast administration and its environmental and pa
arXiv:2512.20620v3 Announce Type: replace-cross Abstract: Uncomfortable sensations similar to motion sickness, called cybersickness, can develop when using Virtual Reality (VR) head-mounted displays.
arXiv:2610.03473v1 Announce Type: new Abstract: We propose UniDynamics, a diffusion-based framework for future 4D dynamic scenes (RGB, depth, and optical flow) generation from a single event-RGB pair,
arXiv:2307.07113v2 Announce Type: replace-cross Abstract: In this paper, we consider the decentralized, stochastic nonconvex strongly-concave (NCSC) minimax problem with nonsmooth regularization terms
arXiv:2311.18837v2 Announce Type: replace-cross Abstract: Diffusion models have achieved significant success in image and video generation. This motivates a growing interest in video editing tasks, wh
arXiv:2610.02801v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades sub
arXiv:2610.02614v1 Announce Type: new Abstract: AI models serving a heterogeneous population must act on the principles appropriate to each user and context. While post-training has been shown to narr
arXiv:2610.03713v1 Announce Type: cross Abstract: Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary predictio
arXiv:2511.12749v3 Announce Type: replace-cross Abstract: Forecasting many sparse series requires two choices: how much of each series' own past to retain, and how much to borrow from other series. We
arXiv:2610.03465v1 Announce Type: cross Abstract: K-fold cross-validation (CV) is widely used as evidence of out-of-sample performance, although folds are neither independent experiments nor equally i
arXiv:2610.03646v1 Announce Type: new Abstract: Stationarity rewards memory, but after a change the same history can mislead. We ask when forgetting should be permitted. E-process-authorized Thompson
arXiv:2610.02641v1 Announce Type: cross Abstract: Removing an input-scaling module changes both a classifier and the perturbations reaching its encoder. A robustness difference can therefore reflect t
arXiv:2610.02355v1 Announce Type: new Abstract: Increasing the batch size during training is a common practice in large language model (LLM) pretraining, yet the theoretical justification behind its s
arXiv:2610.03290v1 Announce Type: cross Abstract: Lung ultrasound (LUS) is attractive for tuberculosis (TB) screening at primary-care level, but labelled cohorts are small. Echocardiography carries no
arXiv:2610.02263v1 Announce Type: cross Abstract: Patient-level lung ultrasound (LUS) diagnosis requires integrating findings acquired across multiple anatomical zones, yet clinical examinations frequ
arXiv:2610.03546v1 Announce Type: new Abstract: EEG foundation models (EFMs) capture reusable knowledge from large-scale EEG data, while many EEG recordings also include companion physiological signal
@abuchanlife - training frontier models is expensive - distilling a frontier model is cheap - this market force alone tells us that frontier foundation models will be free/open. - there are others. ht
Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper shows that agreement can hide shared errors, while disagreement
Banger paper from CMU on harness learning. (bookmark it) Also, pay attention to this important new AI engineering skill of improving agents by editing their harness code instead of their weights. Seei
Language is not fundamental to human consciousness. In terms of evolution, it arrived only recently on our timeline. Consciousness evolved over millions of years through sensory awareness, emotion, an
Side note. The idea that current models are conscious is absurd and downright offensive. Do not confuse competent information processing and sentience, they are wholly unrelated. You can be entirely i
arXiv:2610.01229v1 Announce Type: new Abstract: A compact dynamic-scene representation must retain both the surfaces seen over time and the appearance needed to render them from new viewpoints. We pre
arXiv:2610.02116v1 Announce Type: new Abstract: A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification of medical abstracts. The work addresses the disa
arXiv:2610.00111v1 Announce Type: new Abstract: Model judges now supervise multimodal systems at scale, filtering training data, selecting outputs, and supplying the reward that shapes multimodal reas
arXiv:2610.01375v1 Announce Type: new Abstract: A user's movie, news, and dialogue histories differ in their native actions and outputs, yet each interaction supplies evidence that can update user mem
arXiv:2410.13548v3 Announce Type: replace Abstract: We resolve a fundamental question about the ability to perform a statistical task, such as learning, when an adversary corrupts the sample. Such adv
arXiv:2610.00533v1 Announce Type: cross Abstract: This paper addresses the control of multi-input strict-feedback nonlinear systems subject to a joint capacity constraint, in which the admissible inpu
arXiv:2610.01185v1 Announce Type: new Abstract: Multiple UAVs can cooperatively transport heavy payloads while controlling their position and orientation. Trajectory-based methods offer high agility w
arXiv:2610.01813v1 Announce Type: new Abstract: Mitotic counting is an important component of tumour grading, diagnosis and prognostic assessment across several tumour types, but manual assessment is
arXiv:2610.02069v1 Announce Type: cross Abstract: Rare weather regime transitions pose a challenge for data-driven modeling due to class imbalance. In this study, we develop a probabilistic deep learn
arXiv:2610.01389v1 Announce Type: new Abstract: Modern retrieval systems must both be automated and interactive, allowing users to search and refine results in real time. We present AiSearch, a flexib
arXiv:2610.02098v1 Announce Type: new Abstract: Mechanistic interpretability aims to recover the internal computations responsible for model behavior. Progress in automated circuit discovery is often
arXiv:2610.01692v1 Announce Type: new Abstract: Wrist electrodermal activity (EDA) differs in amplitude from one person to the next, so affect-recognition models normalize their input before classific
arXiv:2610.00052v1 Announce Type: cross Abstract: We evaluate six language-model configurations on requests for six distinct random integers from 1-49. Across 1,200 attempted calls using four English
arXiv:2610.00564v1 Announce Type: new Abstract: Operator learning on probability measures can be accomplished with transformers. For measures with polynomial tails, the exponential weighting in softma
arXiv:2610.00988v1 Announce Type: new Abstract: Cryptic ligand-binding pockets are not apparent in experimentally determined apo structures, making them difficult to identify from unbound receptor geo