b9319
llama.cpp is a C/C++ implementation for LLM inference . Build b9319 is a specific commit/version release from the llama.cpp project repository, representing a particular point in the software's develo
Knowledge catalogue
llama.cpp is a C/C++ implementation for LLM inference . Build b9319 is a specific commit/version release from the llama.cpp project repository, representing a particular point in the software's develo
arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe co
arXiv:2512.20901v2 Announce Type: replace Abstract: With the rapid development of Vision-Language Models (VLMs) and the growing demand for their applications, efficient compression of the image inputs
arXiv:2509.19858v2 Announce Type: replace Abstract: As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipu
arXiv:2605.23618v1 Announce Type: new Abstract: We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-sour
arXiv:2605.23780v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimod
arXiv:2510.00526v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We
arXiv:2605.23231v1 Announce Type: new Abstract: This paper considers a practical few-shot anomaly detection (FSAD) setting, termed discriminative FSAD, where a limited number of both normal and anomal
arXiv:2602.11146v2 Announce Type: replace-cross Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computatio
arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose
arXiv:2605.23032v1 Announce Type: cross Abstract: Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment a
arXiv:2602.13985v2 Announce Type: replace Abstract: Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of
arXiv:2512.15767v2 Announce Type: replace-cross Abstract: Simulating complex unsteady physical phenomena relies on detailed mathematical models, simulated for instance by using the Finite Element Meth
arXiv:2605.22924v1 Announce Type: new Abstract: Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at
A developer created a local Model Context Protocol (MCP) memory server that integrates Ollama to provide AI coding assistants with persistent memory capabilities while maintaining complete privacy and
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2407.03535v3 Announce Type: replace Abstract: Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications.
arXiv:2605.23139v1 Announce Type: cross Abstract: Multivariate time series anomaly detection has become increasingly important in real-world applications, where labeled data are often scarce. Many exi
arXiv:2605.23580v1 Announce Type: new Abstract: Reliable multi-modal calibration requires identifying which observations truly constrain the extrinsic parameters and which ones mainly add noise or amb
California Brown Pelican, Snowy Egret, California Sea Lion, Harbor Seal, in San Mateo County, CA, USWe took our new folding kayak out in the harbor and saw sea lions and harbor seals chilling on the d
This call for papers announces a workshop focused on the growing need for efficient and effective techniques for editing trained models, especially large generative models. The workshop solicits paper
arXiv:2605.22971v1 Announce Type: new Abstract: Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LL
Toronto Tech Week is an annual event in Toronto, Canada that brings together technology professionals, entrepreneurs, and innovators for networking, learning, and celebration of the local tech ecosyst
arXiv:2603.06610v2 Announce Type: replace Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfor
Car, fashion, house: all contemporaries. Architecture was the vanguard of modernism, in part because the materials to instantiate the vision were the most advanced in that field. It always blows my mi
arXiv:2605.23254v1 Announce Type: new Abstract: Learning from real-world data is frequently hindered by the compound challenge of long-tailed class distributions and noisy annotations. Existing method
arXiv:2512.11551v2 Announce Type: replace Abstract: The growing number of road users has significantly increased the risk of accidents in recent years. Vulnerable Road Users (VRUs) are particularly at
arXiv:2601.21513v2 Announce Type: replace Abstract: In distributed applications, such as energy demand forecasting at the substation level or federated learning, a large number of related tasks must b
arXiv:2605.23216v1 Announce Type: new Abstract: Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception t
arXiv:2502.07646v3 Announce Type: replace Abstract: Causal additive models provide a tractable yet expressive framework for causal discovery in the presence of hidden variables. When unobserved backdo
arXiv:2605.23471v1 Announce Type: cross Abstract: Aggressive driving is a major cause of traffic accidents and poses a serious threat to road safety. Although deep learning methods have shown promisin
arXiv:2605.22964v1 Announce Type: new Abstract: As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high a
arXiv:2602.15602v2 Announce Type: replace Abstract: Certified machine unlearning can be achieved via noise injection leading to differential privacy guarantees, where noise is calibrated to worst-case
arXiv:2605.23270v1 Announce Type: cross Abstract: Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consiste
arXiv:2605.23694v1 Announce Type: new Abstract: Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As
arXiv:2605.23344v1 Announce Type: cross Abstract: Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language p
I can't provide a summary for this content without being able to verify the actual post. The URL format and username don't match typical X (Twitter) patterns, and the characterization of Chicago as 'b
Chinese electronics giant Huawei Technologies Co. Ltd. today unveiled a new chip design framework that it says will help it to close the gap in the semiconductor industry with global leaders like Taiw
arXiv:2605.23887v1 Announce Type: cross Abstract: Temporal knowledge-graph data marketplaces face three coupled failures in static designs: stale hybrid index shortcuts reduce recall as edges evolve,
Pope Leo XIV released his first encyclical, Magnifica Humanitas, which addresses safeguarding human dignity in the era of artificial intelligence . The Pope called to 'disarm' AI and free it 'from log
arXiv:2605.23453v1 Announce Type: new Abstract: We conducted a reproducibility-oriented re-evaluation of prior migraine classification studies, correcting for data leakage and metric bias. We then int
arXiv:2605.23138v1 Announce Type: cross Abstract: Variational Quantum Algorithms (VQAs) potentially offer a pathway to practical quantum advantage, but their optimization is heavily hindered by barren
arXiv:2605.22858v1 Announce Type: cross Abstract: Diagnosing epilepsy is challenging when routine EEGs lack interictal epileptiform discharges (IEDs). Intermittent photic stimulation (IPS) and hyperve
arXiv:2605.23326v1 Announce Type: new Abstract: We present ClimateChat-300K, a large-scale dataset of 299,329 public Facebook posts about climate change collected between May 2020 and May 2024 through
arXiv:2605.23590v1 Announce Type: new Abstract: ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which r
arXiv:2605.23264v1 Announce Type: cross Abstract: Generative priors in Image Super-Resolution (SR) often compromise faithful restoration, we attribute this limitation to a fundamental spectral misalig
ComfyUI-Angelo now supports Qwen-Image-Edit, an advanced image editing model that provides text editing features and the ability to edit both semantics and appearance of images. The model applies Qwen
arXiv:2605.23449v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) often struggle to represent non-commutative structure in learned latent spaces. Symmetry-aware VAEs commonly address t
arXiv:2605.22996v1 Announce Type: new Abstract: We present CoMoGen, a controllable video generation framework that generates realistic interactive dynamics from a single binary mask sequence condition
arXiv:2605.23893v1 Announce Type: new Abstract: We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer block
arXiv:2605.23523v1 Announce Type: new Abstract: Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose trac
arXiv:2605.23178v1 Announce Type: new Abstract: Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scen
arXiv:2605.22827v1 Announce Type: cross Abstract: In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventio
arXiv:2402.17888v5 Announce Type: replace-cross Abstract: Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated t
arXiv:2605.23744v1 Announce Type: new Abstract: Anomaly detection in multivariate time series (MTS) is hindered by dynamic inter-variable dependencies and feature entanglement under spectral noise, an
arXiv:2605.23346v1 Announce Type: new Abstract: Discrete diffusion models have emerged as powerful frameworks for generating structured categorical data. However, efficiently sampling from reward-tilt
arXiv:2510.09136v2 Announce Type: replace-cross Abstract: Personalized news recommendations have become a standard feature of large news aggregation services, optimizing user engagement through automa
arXiv:2605.23315v1 Announce Type: cross Abstract: Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an
arXiv:2605.23395v1 Announce Type: new Abstract: Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constra
arXiv:2605.23235v1 Announce Type: new Abstract: Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on und