Knowledge catalogue
arXiv:2604.22709v1 Announce Type: new Abstract: While long, explicit chains-of-thought (CoT) have proven effective on complex reasoning tasks, they are costly to generate during inference. Non-verbal
This release adds OpenCL GPU acceleration support for the IQ4_NL quantization format in llama.cpp, enabling more efficient inference of quantized language models on compatible hardware. IQ4_NL is a 4-
b8940 is a build release of llama.cpp, an open-source C/C++ library for LLM inference that enables running large language models locally with minimal setup and high performance. This intermediate buil
arXiv:2604.20915v1 Announce Type: cross Abstract: Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by
b8909 is an intermediate build release of llama.cpp, reflecting the project's practice of publishing multiple releases in a single day . llama.cpp is a C/C++ implementation enabling LLM inference with
B8924 is a release build number from the llama.cpp project, a C/C++ framework for efficient large language model inference on consumer hardware. The llama.cpp project publishes multiple releases in a
B8925 is an intermediate build release of llama.cpp, the C/C++ library for efficient large language model inference. Llama.cpp releases follow a continuous build cycle rather than traditional versioni
arXiv:2501.02576v2 Announce Type: replace Abstract: Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference spe
arXiv:2604.21501v1 Announce Type: new Abstract: Lithology classification in well logs is a fundamental geoscience data mining task that aims to infer rock types from multi dimensional geophysical sequ
arXiv:2604.21611v1 Announce Type: cross Abstract: Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourt
arXiv:2604.20937v1 Announce Type: new Abstract: Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training
arXiv:2604.21221v1 Announce Type: new Abstract: We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality w
arXiv:2603.15055v2 Announce Type: replace-cross Abstract: We present a theory-guided generalized Bayesian methodology for spatio-temporal raster data, which we use to train an ensemble of stochastic f
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often
arXiv:2604.20568v1 Announce Type: new Abstract: Modeling high-dimensional dependencies while keeping likelihoods tractable remains challenging. Classical vine-copula pipelines are interpretable but ca
B8902 is a release build of llama.cpp, an open-source C/C++ framework for running large language model inference on consumer hardware with minimal dependencies. As an intermediate build release from t
B8905 is a build release of llama.cpp, an open-source C/C++ library for large language model inference optimization. The release follows the project's rapid development cycle with frequent intermediat
arXiv:2508.06614v2 Announce Type: replace Abstract: As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance i
arXiv:2604.20079v1 Announce Type: cross Abstract: Auto-regressive Large Language Models (LLMs) achieve strong performance on coding tasks, but incur high memory and inference costs. Diffusion-based la
b8882 is a release of llama.cpp, a C/C++ implementation for LLM inference . The project follows a rapid release cycle with frequent updates to support multiple hardware architectures and platforms. Th
b8883 is a release build of llama.cpp, an open-source software library that performs inference on various large language models, co-developed alongside the GGML tensor library. This intermediate build
llama.cpp is a C/C++ implementation that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware locally and in the cloud. Release b8884 is a build/versio
arXiv:2604.18697v1 Announce Type: cross Abstract: Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to
The era of agentic AI is accelerating from human- to machine-speed operations, while also creating profound stress on legacy technology infrastructure. This new reality pushes foundational systems to
arXiv:2604.18963v1 Announce Type: cross Abstract: Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also under
Excited to share some big news: I've joined @FireworksAI_HQ President. I've spent my career at the intersection of great teams, disruptive technology, and massive market opportunity, from architecting
Google unveiled two eighth-generation Tensor Processing Units—the TPU 8t for training and TPU 8i for inference—designed with specialized architectures for AI model training and agent development. The
INT3 compression with fused Metal kernels enables large language models to compute attention operations directly on compressed (INT3/INT4) key-value cache representations using custom GPU kernels that
arXiv:2604.19018v1 Announce Type: cross Abstract: Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during g
arXiv:2604.18995v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. Ho
arXiv:2603.27134v3 Announce Type: replace Abstract: Are there still barriers to generalization once all relevant variables are known? We address this question via a framework that casts compositional
arXiv:2603.20897v3 Announce Type: replace-cross Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI data centres worldwide with the unavoidable es
arXiv:2604.16733v1 Announce Type: new Abstract: Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and s
arXiv:2510.07143v3 Announce Type: replace Abstract: Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectivene
b8864 is a build release of llama.cpp, an open-source C/C++ library for large language model inference. The project uses rapid release cycles with frequent build tags published as intermediate develop
B8871 is a build release of llama.cpp, an open-source C/C++ implementation for LLM inference. Build releases in the llama.cpp project use alphanumeric identifiers and represent incremental development
b8872 is a release tag from llama.cpp, a project that enables LLM inference in C/C++ . The release represents a specific commit or version update to the llama.cpp codebase. Without access to the speci
b8874 is a release from llama.cpp, a C/C++ library for LLM inference. The llama.cpp project publishes multiple releases in a single day, and b8874 represents an intermediate build version containing u
arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel
arXiv:2604.16590v1 Announce Type: new Abstract: Accurate weather and climate prediction relies on data assimilation (DA), which estimates the Earth system state by integrating observations with models
arXiv:2604.18556v1 Announce Type: new Abstract: Weight quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-
arXiv:2505.07033v2 Announce Type: replace-cross Abstract: Many classification performance metrics exist, each suited to a specific application. However, these metrics often differ in scale and can exh
arXiv:2604.18199v1 Announce Type: new Abstract: Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propo
arXiv:2503.16549v2 Announce Type: replace Abstract: Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially
open-source community will work their magic! If any inference providers could serve kimi k2.6 at 300+ tps reliably, I would be happy to switch from gpt 5.4 xhigh to kimi for daily tasks. It's a really
arXiv:2604.01348v2 Announce Type: replace Abstract: Test-time scaling has emerged as an effective way to improve language models on challenging reasoning tasks. However, most existing methods treat ea
arXiv:2603.05863v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward
arXiv:2604.18396v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency
arXiv:2604.16606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains
B8852 is a release of llama.cpp, an LLM inference library in C/C++ . This build tag likely contains bug fixes, performance improvements, and feature updates from the llama.cpp development cycle, which
Release b8859 is a version of llama.cpp, an open-source project that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware. The llama.cpp project uses a
arXiv:2602.22159v2 Announce Type: replace Abstract: Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, nois
arXiv:2603.08899v2 Announce Type: replace Abstract: Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to
arXiv:2604.15714v1 Announce Type: cross Abstract: Always-on converter health monitoring demands sub-mW edge inference, a regime inaccessible to GPU-based physics-informed neural networks. This work se
arXiv:2604.15728v1 Announce Type: cross Abstract: Large language model (LLM) routing has emerged as a critical strategy to balance model performance and cost-efficiency by dynamically selecting servic
arXiv:2603.03188v2 Announce Type: replace-cross Abstract: We introduce a novel framework for uncertainty quantification in clustering that combines martingale posterior distributions with density-base
arXiv:2604.15613v1 Announce Type: cross Abstract: We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic sol
b8842 is a release of llama.cpp, a C/C++ implementation for LLM inference. The llama.cpp project publishes multiple releases in a single day as part of its active development cycle. This specific rele
arXiv:2604.14682v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model (LLM) inference. It uses a small draft model to propose a tree of future tokens. A larger target
arXiv:2604.15180v1 Announce Type: cross Abstract: Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promisin