Knowledge catalogue
arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguist
arXiv:2609.35913v1 Announce Type: cross Abstract: Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal.
arXiv:2609.36294v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) expose interpretable features in large language model activations, yet existing structured SAEs impose single-parent trees
arXiv:2609.36797v1 Announce Type: new Abstract: Stochastic cell updates are often used throughout the life of a neural cellular automaton (NCA), from backpropagation through time to final rollout. Thi
arXiv:2609.37297v1 Announce Type: new Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion t
arXiv:2609.37702v1 Announce Type: cross Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to
arXiv:2609.35021v1 Announce Type: new Abstract: Spatiotemporal prediction aims to learn discriminative representations from correlated temporal signals over spatial structures for accurate future infe
arXiv:2609.32593v1 Announce Type: new Abstract: Current machine learning algorithms primarily rely on instantaneous signals such as loss, margin, and prediction confidence to characterize model behavi
arXiv:2609.32764v1 Announce Type: new Abstract: Detecting distributed denial-of-service (DDoS) attacks in cloud-integrated IoT networks is difficult when labeled traffic is scarce. Generative semi-sup
arXiv:2609.32240v1 Announce Type: new Abstract: A gradient descent method is arithmetically simple if the operations are limited to +,-, imes, and division x/2^t with integer t. An arthmetically simpl
arXiv:2609.33818v1 Announce Type: new Abstract: Visual anomaly detectors identify deviations from known-normal data, but their anomaly signals may mix evidence of actual anomalies with benign visual v
arXiv:2609.32432v1 Announce Type: new Abstract: Flow matching and diffusion can be trained to predict different quantities, most commonly the data x_1, the source noise x_0, or the velocity~v. Althoug
arXiv:2609.33144v1 Announce Type: new Abstract: Looped Transformers can generalize to reasoning chains longer than those encountered during training, but the computations enabling this behavior and li
arXiv:2609.34246v1 Announce Type: new Abstract: Autoregressive neural emulators can drift or diverge over long rollouts despite accurate short-term predictions. We introduce Cascaded Emulation (CasEm)
arXiv:2512.11352v2 Announce Type: replace Abstract: Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (G
arXiv:2609.35745v1 Announce Type: new Abstract: Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient
arXiv:2609.34183v1 Announce Type: new Abstract: Weakly Supervised Semantic Segmentation (WSSS) learns pixel-level predictions from image-level tags. Recent work focuses on improving coarse CAMs extrac
arXiv:2609.34965v1 Announce Type: new Abstract: Many physiological time series, such as cardiac and brain recordings, exhibit cyclostationarity: their statistics vary periodically with an underlying c
arXiv:2609.33048v1 Announce Type: new Abstract: Understanding how individual brain development unfolds over childhood requires modeling developmental trajectories from sparse longitudinal observations
arXiv:2609.34286v1 Announce Type: new Abstract: World models for manipulation are typically trained from video, yet the events that determine how manipulation unfolds, such as making and releasing con
arXiv:2511.15990v2 Announce Type: replace-cross Abstract: Digital agriculture is transforming the way we grow food by utilizing technology to make farming more efficient, sustainable, and productive.
arXiv:2609.35444v1 Announce Type: new Abstract: Robust skeleton-based action recognition requires representations that capture a wide spectrum of motions, from subtle to moderate and strong ones. Exis
arXiv:2609.34629v1 Announce Type: new Abstract: Many complex systems are observed only through temporally unpaired distribution snapshots, making trajectory-based dynamical learning difficult without
arXiv:2609.34408v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is
arXiv:2602.00449v2 Announce Type: replace-cross Abstract: Latent Chain-of-Thought aims to enable step-by-step computation without emitting long rationales, yet its internal mechanisms remain unclear.
arXiv:2609.33166v1 Announce Type: new Abstract: In-context reinforcement learning (ICRL) enables large language model agents to adapt to new environments using their interaction history without updati
arXiv:2609.35167v1 Announce Type: new Abstract: Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific
arXiv:2609.32100v1 Announce Type: new Abstract: The neural scaling law relating longer training to better performance through a power law is central to today's large language models (LLMs), yet its or
arXiv:2609.33101v1 Announce Type: cross Abstract: Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examinatio
arXiv:2609.32980v1 Announce Type: new Abstract: Graph reconstruction from partial observations often comes with structural side information, such as degree bounds, triangle counts, or an edge-density
arXiv:2609.32696v1 Announce Type: cross Abstract: Data shape determines how features are structured, how patterns are separated, and how distributions cover the underlying domain. Poor data shape can
arXiv:2609.35449v1 Announce Type: new Abstract: With limited annotation budgets, choosing which images to label determines how much a model improves. Data-selection methods that use features from a se
arXiv:2609.32296v1 Announce Type: new Abstract: Efficient sampling from Boltzmann distributions is central to modelling complex physical systems. Markov Chain Monte Carlo (MCMC) methods suffer from cr
arXiv:2609.32941v1 Announce Type: new Abstract: Inferring quantities of interest (QoI) from data is a central task in Science and Engineering. In such contexts, we often have access to both quantitati
arXiv:2609.35341v1 Announce Type: new Abstract: Evaluating semantic similarity between videos is a fundamental challenge in computer vision, essential for tasks ranging from out-of-distribution (OOD)
arXiv:2609.33695v1 Announce Type: new Abstract: Decoding signals over unknown channels with minimal pilot overhead is a critical challenge in next-generation communications. Existing deep learning app
arXiv:2609.34161v1 Announce Type: cross Abstract: Multivariate time series anomaly detection (MTAD) is crucial for ensuring the safe and reliable operation of complex systems. Many existing methods le
arXiv:2609.33607v1 Announce Type: new Abstract: Pretrained graph-text models align graph representations with textual semantics, enabling recognition of unseen classes and transfer across graph domain
arXiv:2609.35457v1 Announce Type: new Abstract: Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instea
arXiv:2609.35751v1 Announce Type: new Abstract: Looped Transformers reuse one block of layers several times: by spending extra computation they push a model of fixed size further, and so use its param
If I were given one final message, and the premise were that I genuinely understood what was happening—that this was the last thing I would ever say, with no possibility of another response—I don’t th
arXiv:2609.35512v1 Announce Type: new Abstract: Self-training generative models - the continued improvement of a model using its own outputs - is becoming increasingly important as high-quality traini
Waylon Cunningham / Reuters: Investigation: McDonald's is utilizing an AI pricing engine across nearly 14,000 restaurants to generate location-specific “optimal prices” for menu items — McDonald's is
Just arrived at @OpenAI #DevDay, and I’m predicting proactive intelligence will steal the show. We’ve gone from statistics to machine learning to intelligence. Now the next step is AI that doesn’t jus
arXiv:2609.32203v1 Announce Type: new Abstract: Large vision-language models (VLMs) can judge visual similarity, but their judgments are not directly available as compact image embeddings for efficien
arXiv:2609.31988v1 Announce Type: new Abstract: We investigate the applicability of Lagrangian and Hamiltonian Neural Network models to a dissipative system that has explicit time dependence in its La
The article discusses the newly released Jev AI model, which functions as a general‑purpose text classifier that can perform classification tasks more quickly and cheaply than large language models li
arXiv:2609.31720v1 Announce Type: new Abstract: Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through chara
arXiv:2609.33620v1 Announce Type: new Abstract: Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a r
arXiv:2609.35166v1 Announce Type: new Abstract: Discrete diffusion models offer the ability to re-draft, revisiting and correcting earlier tokens throughout generation. This capability depends on the
arXiv:2503.17915v2 Announce Type: replace-cross Abstract: Real-world degraded images often contain multiple co-occurring degradation types, making composite image restoration fundamentally different f
arXiv:2609.34895v1 Announce Type: new Abstract: Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusions. We hypothesize that this limitat
arXiv:2510.22654v3 Announce Type: replace Abstract: This paper addresses the problem of sequential decision-making under learning budget constraints. Such settings naturally arise in applications like
arXiv:2609.31868v1 Announce Type: cross Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effec
arXiv:2609.33741v1 Announce Type: cross Abstract: Inverse Optimal Transport (OT) based methods for representation learning learn representations such that the global OT coupling between a pair of data
arXiv:2609.35072v1 Announce Type: new Abstract: We consider the problem of trajectory valuation in reinforcement learning: how to identify and mitigate detrimental trajectories during online training.
arXiv:2609.33681v1 Announce Type: new Abstract: This paper presents the application and experimental evaluation of a systematic method for optimal sensor placement in soft robots. Existing methods eit
arXiv:2609.34423v1 Announce Type: new Abstract: Non-stationary online learning has attracted much attention in recent years, as static regret is insufficient to guide algorithm design in changing envi
arXiv:2609.33377v1 Announce Type: new Abstract: Deterministic neural networks and neural operators provide point predictions with no intrinsic measure of reliability. Yet, predictive uncertainty may s
arXiv:2609.32094v1 Announce Type: cross Abstract: Temporal dynamics in learning behavior can be revealed through period segmentation in Transition Network Analysis (TNA). Cristea et al. demonstrated t