Knowledge catalogue
arXiv:2507.02974v3 Announce Type: replace-cross Abstract: As major progress in LLM-based long-form text generation enables paradigms such as retrieval-augmented generation (RAG) and inference-time sca
arXiv:2602.01842v3 Announce Type: replace Abstract: Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive de
arXiv:2509.12464v2 Announce Type: replace Abstract: Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale.
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this sparsity into practical
arXiv:2605.03907v1 Announce Type: new Abstract: Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform
arXiv:2605.03609v1 Announce Type: cross Abstract: Large language models often display heterogeneous moral preferences across settings. We study inference-time steering toward a desired ethical framewo
B9030 is a release build of llama.cpp, a C/C++ implementation for LLM inference . This build release would contain bug fixes, performance improvements, and new features added to the llama.cpp project
arXiv:2605.01106v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target.
arXiv:2605.01495v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conve
arXiv:2404.10370v3 Announce Type: replace Abstract: Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within th
arXiv:2605.02521v1 Announce Type: new Abstract: Affective image editing (AIE) aims to edit visual content to evoke target emotions. However, existing methods often overlook inference efficiency and pr
arXiv:2605.01003v1 Announce Type: cross Abstract: Statistical change point (CP) detection methods typically rely on likelihood-based inference and ignore contextual information about plausible CP loca
arXiv:2605.02888v1 Announce Type: cross Abstract: Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target mo
arXiv:2512.22331v2 Announce Type: replace Abstract: Non-invasive inference of molecular tumor characteristics from medical imaging is a central goal of radiogenomics, particularly in glioblastoma (GBM
arXiv:2602.06932v3 Announce Type: replace Abstract: Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating spe
Release b9016 is a build of llama.cpp, an LLM inference implementation in C/C++ . This build designation represents a specific intermediate version in the project's development cycle, similar to other
arXiv:2605.00078v1 Announce Type: cross Abstract: Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to a
arXiv:2503.14459v2 Announce Type: replace-cross Abstract: Practical and ethical constraints often require the use of observational data for causal inference, particularly in medicine and social scienc
arXiv:2605.00423v1 Announce Type: new Abstract: In wireless communications, recovering the optimal solution to the multiple-input multiple-output (MIMO) detection problem is NP-hard. Obtaining high-qu
arXiv:2605.00789v1 Announce Type: new Abstract: Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency
AI compute resources should not be treated as interchangeable commodities, as different hardware configurations, providers, and architectures significantly impact training costs, inference latency, an
🤝 OpenHuman x Fireworks AI We are excited to announce one of our very first partnerships with Fireworks AI. OpenHuman is now powered by @FireworksAI_HQ: the fastest inference for Qwen3 outside of Alib
arXiv:2605.00707v1 Announce Type: new Abstract: Image editing instructions are heterogeneous: a color swap, an object insertion, and a physical-action edit all demand different spatial coverage and di
arXiv:2605.00146v1 Announce Type: new Abstract: Real-time object detection on energy-constrained platforms is critical for applications such as UAV-based inspection, autonomous navigation, and mobile
arXiv:2605.00557v1 Announce Type: new Abstract: Scientific discovery is an extended process of ideation--surveying prior work, forming hypotheses, and refining reasoning--yet existing approaches treat
This post explores how the processes and tasks a company chooses to automate reflect its core understanding of its business and strategic priorities. By examining automation choices, one can infer wha
ZIT (Z-Image Turbo) is a compact, fast distilled model tuned for photorealism that uses 8 inference steps with a fixed CFG of 1, which limits creativity . ZIB (Z-Image Base) is an undistilled model id
Ollama Cloud launched in September 2025 with fixed-price subscription tiers (20/month Pro, 100/month Max) for cloud-hosted inference , while local deployment remains free with unlimited local usage .
b9000 is a build release of llama.cpp, a C/C++ implementation for LLM inference . The release follows the project's rapid development cycle where multiple releases can be published in a single day . A
B9002 is a build release of llama.cpp, a C/C++ implementation for LLM inference. The release includes compiled binaries and artifacts for multiple platforms and hardware configurations, as part of the
llama.cpp b8999 is a build release from the llama.cpp project, which provides LLM inference in C/C++ . This build represents an intermediate development version in the project's rapid release cycle. T
arXiv:2409.16808v1 Announce Type: cross Abstract: Modern applications, such as autonomous vehicles, require deploying deep learning algorithms on resource-constrained edge devices for real-time image
arXiv:2604.26959v1 Announce Type: cross Abstract: Integrating large language models (LLMs) into patient-facing healthcare systems offers significant potential to improve access to medical information.
arXiv:2604.27251v1 Announce Type: cross Abstract: Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further eli
arXiv:2604.02715v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models have become a dominant paradigm for scaling large language models, but their rapidly growing parameter sizes introdu
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
arXiv:2412.05135v2 Announce Type: replace-cross Abstract: We propose a novel method for measuring the discrepancy between a set of samples and a desired posterior distribution for Bayesian inference.
b8983 is a release of llama.cpp, a C/C++ implementation for LLM inference. The release represents a specific build/commit version in the active development of the llama.cpp project, which supports run
Release b8987 of llama.cpp updates cpp-httplib to version 0.43.2 . This is a minor maintenance release from the llama.cpp project, which provides C/C++ inference for large language models. The release
llama.cpp b8990 is a release version of a C/C++ LLM inference tool from the ggml-org project. The release likely contains bug fixes, performance improvements, or new features for local language model
llama.cpp is a C/C++ implementation for LLM inference , and b8991 is a specific release version from the project's ongoing development cycle. The search results indicate that the project doesn't follo
b8992 is a build release from the llama.cpp project, which publishes multiple releases in a single day . llama.cpp enables LLM inference with minimal setup and state-of-the-art performance on a wide r
arXiv:2512.08982v2 Announce Type: replace-cross Abstract: Retinex-based low-light image enhancement benefits from separating reflectance and illumination, yet recent generative approaches often rely o
arXiv:2604.26378v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-p
arXiv:2604.26881v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, de
arXiv:2603.19199v2 Announce Type: replace-cross Abstract: Real-time execution is crucial for deploying Vision-Language-Action (VLA) models in the physical world. Existing asynchronous inference method
Featherless.ai Inc., a serverless inference platform startup that hosts open-source artificial intelligence models, today revealed it has raised 20 million in new funding to expand its global infrastr
arXiv:2604.26070v1 Announce Type: new Abstract: Causal inference in continuous-time sequential decision problems is challenged by hidden confounders. We show that, in latent state-space models with ti
arXiv:2604.26039v1 Announce Type: cross Abstract: The optimal kernel configuration for Mixture-of-Experts (MoE) inference depends on both batch size and the expert routing distribution, yet production
arXiv:2604.25975v1 Announce Type: cross Abstract: Key-value (KV) caching is essential for large language model inference, yet its memory overhead poses a critical bottleneck for long-context generatio
arXiv:2512.18583v2 Announce Type: replace Abstract: Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy op
arXiv:2604.26355v1 Announce Type: new Abstract: Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains unde
arXiv:2604.25925v1 Announce Type: new Abstract: Autoregressive language models suffer from high inference latency due to their sequential decoding nature. Speculative decoding (SD) mitigates this by e
arXiv:2604.26422v1 Announce Type: cross Abstract: Accurate end-to-end tail-latency forecasting is critical for proactive SLO management in microservice systems. However, modeling long-range dependency
arXiv:2505.13963v3 Announce Type: replace Abstract: Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's
Today we’re releasing Qwen-Scope 🔭, an open suite of sparse autoencoders for the Qwen model family. It turns SAE features into practical tools： 🎯 Inference — Steer model outputs by directly manipulati
arXiv:2511.22972v3 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive gene
arXiv:2603.07080v3 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time de
arXiv:2604.26934v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that
b8969 is a release build of llama.cpp (commit bdc9c74), published on April 29, 2026. Llama.cpp is a C/C++ implementation designed to enable LLM inference with minimal setup and state-of-the-art perfor