Knowledge catalogue
arXiv:2609.27374v1 Announce Type: cross Abstract: Test-time scaling with parallel branches is widely adopted to improve performance on challenging reasoning tasks. The predominant approach, repeated s
arXiv:2609.27094v1 Announce Type: cross Abstract: Automatic tagging is a core task in Music Information Retrieval (MIR), yet most tagging systems exploit only audio. Live music performance is inherent
Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enter
Introduction The landscape of software supply chain security has undergone a significant shift. Recent campaigns demonstrate that sophisticated threat actors are systematically targeting the engineeri
arXiv:2609.27074v1 Announce Type: cross Abstract: This study introduces a dual-matrix computational architecture to mathematically quantify the morphological and theological divergence of 196 Hindu an
arXiv:2609.27355v1 Announce Type: cross Abstract: Unlearning ensures LLM compliance by removing the influence of private or copyrighted training data. However, since LLM models typically undergo post-
arXiv:2609.26855v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-ar
A while ago I posted 15 tok/s output and 100-120 tok/s prompt processing with the IQ3_XXS quant on a 12GB RTX 5070 using llama.cpp. Since then I built my own inference engine for this one model and th
Here's my *first* implementation of KVA projectors on QFN (just the uncensored model for now) the highlights are basically as follows for using the projectors at each different layer: Starting at laye
arXiv:2609.27035v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout i
arXiv:2609.27667v1 Announce Type: new Abstract: Reinforcement learning (RL) achieves strong performance in sequential decision-making but remains brittle under dynamic uncertainty and distributional s
arXiv:2609.27289v1 Announce Type: cross Abstract: Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to
arXiv:2609.27413v1 Announce Type: new Abstract: Alignment-free RGB-T salient object detection (RGB-T SOD) aims to identify salient objects from unregistered RGB and thermal image pairs without costly
Scribd, Inc. is home to one of the world's largest collections of human-created content. Scribd’s products leverage one of the world's largest collections of human-created content and intelligent tool
arXiv:2609.26820v1 Announce Type: cross Abstract: Physiological time series such as electrocardiograms (ECG) and electroencephalograms (EEG) exhibit complex temporal structure, substantial acquisition
arXiv:2609.26907v1 Announce Type: cross Abstract: Memes often derive their harmful, hateful, or sarcastic meaning from small but decisive visual, textual, or cross-modal cues. Existing multimodal clas
arXiv:2609.28013v1 Announce Type: cross Abstract: Machine-learned interatomic potentials (MLIPs) for solid-liquid interfaces in advanced materials applications, e.g., electrochemistry, catalysis and c
arXiv:2609.27904v1 Announce Type: new Abstract: As information technology advances, digital content has become widely adopted across diverse fields such as news broadcasting, entertainment, commerce,
arXiv:2609.27287v1 Announce Type: new Abstract: Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized bur
arXiv:2609.26854v1 Announce Type: cross Abstract: Sound Scene Generation is about the automatic synthesis of artificial sound scenes. We introduce SsgCaps, a publicly available dataset of human-engine
arXiv:2606.18305v2 Announce Type: replace-cross Abstract: Operator learning is an emerging field at the intersection of machine learning and scientific computing. By learning mappings between function
arXiv:2609.27227v1 Announce Type: new Abstract: Objective assessment of robotic surgery uses instrument kinematics, which must be reconstructed when only video is available. We introduce a kinematic r
arXiv:2409.13568v3 Announce Type: replace Abstract: Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing methodo
arXiv:2609.28077v1 Announce Type: new Abstract: Steel surface defect detection is critical for automated industrial quality control but remains challenging due to subtle inter-class texture difference
arXiv:2609.27149v1 Announce Type: new Abstract: Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense atte
arXiv:2609.28048v1 Announce Type: cross Abstract: Modern information retrieval (IR) systems rarely represent time, yet many information needs depend on it: in clinical, journalistic, and legal search,
arXiv:2609.26811v1 Announce Type: new Abstract: Local learning trains each layer with its own auxiliary loss and no global backward pass, which makes layer updates structurally parallel. Two problems
arXiv:2607.10669v2 Announce Type: replace Abstract: Bayesian optimization (BO) is widely used for expensive black-box problems, yet practical performance depends not only on high-level algorithmic cho
arXiv:2609.28272v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mecha
arXiv:2609.27577v1 Announce Type: new Abstract: Multimodal joint training often suffers from modality imbalance, where a dominant modality suppresses the optimization of others. Existing methods mainl
arXiv:2609.27321v1 Announce Type: new Abstract: Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training r
arXiv:2609.27948v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visua
arXiv:2609.27679v1 Announce Type: new Abstract: What reusable computation should a tabular foundation model learn when every table defines a new supervised task? We develop in-situ representation refi
arXiv:2609.27819v1 Announce Type: new Abstract: Federated wearable models eventually serve people absent from source training, but favorable average accuracy does not establish that unlabeled onboardi
arXiv:2609.28385v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) supervises mathematical reasoning through final-answer correctness, but provides little guidance
arXiv:2609.27124v1 Announce Type: cross Abstract: Federated Learning enables decentralized model training by exchanging model updates--rather than raw data--with a central parameter server (PS). While
arXiv:2609.27396v1 Announce Type: new Abstract: DSpark-style parallel drafters have made speculative decoding highly effective, yet their draft phase remains serialized on the critical path of every r
arXiv:2609.26955v1 Announce Type: new Abstract: Fairness audits in production ML typically occur once, at deployment, on a single domain. Both fail in practice: fairness can shift after retraining or
arXiv:2609.27203v1 Announce Type: new Abstract: xlog is a CUDA-native logic programming engine integrating neural perception with deterministic Datalog, probabilistic inference, and epistemic world vi
arXiv:2609.22476v1 Announce Type: cross Abstract: Transmission system operators face rising complexity from renewable integration, reduced inertia, and tighter security margins. Large language models
arXiv:2609.25541v1 Announce Type: new Abstract: Tabular foundation models learn to predict cell values in context, whereas world-model self-supervision asks for prediction in representation space (LeC
arXiv:2609.25781v1 Announce Type: new Abstract: Graph Incremental Learning has garnered increasing attention as dynamic graph data continues to emerge across diverse fields. Conventional approaches pr
arXiv:2602.01163v2 Announce Type: replace Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporar
arXiv:2609.26539v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly been used to investigate how children acquire syntax at an early stage of development. This is notably th
arXiv:2609.24446v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subseque
arXiv:2609.26167v1 Announce Type: new Abstract: Activation-energy pruning -- removing weights whose product of magnitude and cumulative pre-synaptic spike count falls below a threshold -- was establis
arXiv:2511.16043v2 Announce Type: replace Abstract: Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting s
arXiv:2609.25047v1 Announce Type: new Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line
arXiv:2609.25961v1 Announce Type: new Abstract: Generative visual models offer a foundation for learning representations of physical dynamics, yet their extension to continuous control raises a fundam
arXiv:2609.25731v1 Announce Type: new Abstract: Medium-resolution (10-30 m) burned area mapping is vital for monitoring wildfires and their impacts, but remains difficult to scale. Existing methods re
arXiv:2609.25930v1 Announce Type: new Abstract: Detecting and localizing 3D point-cloud defects is essential for industrial inspection. However, existing methods often suffer from imprecise localizati
arXiv:2609.24921v1 Announce Type: new Abstract: Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such
arXiv:2609.25040v1 Announce Type: cross Abstract: Banana crop diseases threaten food security across the world, yet field diagnosis remains difficult because of limited expert access and visual simila
arXiv:2609.25891v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may on
arXiv:2609.25007v1 Announce Type: cross Abstract: The performance of state-of-the-art speaker verification (SV) systems severely degrades on short utterances due to insufficient speaker-specific infor
arXiv:2609.26147v1 Announce Type: new Abstract: Modern LLMs are deployed as families of post-trained variants (base, instruct, chat, code) derived from a shared set of pre-trained weights. We present
arXiv:2609.26021v1 Announce Type: new Abstract: Dynamic black-box optimization presents significant challenges for Bayesian Optimization (BO), as the objective function evolves over time, causing opti
arXiv:2609.25814v1 Announce Type: new Abstract: Dynamic graphs are widely used to model time-evolving relational systems in real-world applications. Dynamic graph neural networks provide an effective
arXiv:2609.25937v1 Announce Type: new Abstract: Frozen visual foundation models provide transferable features for visual place recognition, but fixed aggregation can suppress useful distinctions in ne
arXiv:2609.26460v1 Announce Type: new Abstract: Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study