b8931
b8931 is a release version of llama.cpp published on April 25, 2026 . llama.cpp is an LLM inference framework in C/C++ that enables running large language models efficiently on various hardware. The r
Knowledge catalogue
b8931 is a release version of llama.cpp published on April 25, 2026 . llama.cpp is an LLM inference framework in C/C++ that enables running large language models efficiently on various hardware. The r
arXiv:2604.21101v1 Announce Type: new Abstract: For autoregressive modeling of chaotic dynamical systems over long time horizons, the stability of both training and inference is a major challenge in b
arXiv:2510.18091v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence l
arXiv:2502.04416v3 Announce Type: replace-cross Abstract: Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consu
arXiv:2604.21199v1 Announce Type: cross Abstract: Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising
b8913 is a release of llama.cpp, a C/C++ implementation for LLM inference . The release follows the project's rapid development cycle where multiple releases are published in a single day . This speci
arXiv:2604.21772v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) aims to mitigate distributional shifts between training and test domains during inference time. However, existing TTA methods
arXiv:2604.20985v1 Announce Type: cross Abstract: In machine learning applications, privacy requirements during inference or deployment time could change constantly due to varying policies, regulation
arXiv:2602.11871v2 Announce Type: replace Abstract: Large Language Models (LLMs) are a powerful tool for statistical text analysis, with derived sequences of next-token probability distributions offer
arXiv:2604.21276v1 Announce Type: cross Abstract: As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors mak
arXiv:2604.21667v1 Announce Type: cross Abstract: Beyond exploring disaggregated labels for modeling perspectives, annotator rationales provide fine-grained signals of individual perspectives. In this
arXiv:2604.20920v1 Announce Type: new Abstract: Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include K
Highlights: 👉 SOTA coding—93.5% LiveCodeBench, Codeforces 3206, and 80.6% SWE-Bench Verified 👉 Hybrid attention efficiency—27% FLOPs and 10% KV cache vs V3.2 for long-context inference 👉 Three reasoni
New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model i
arXiv:2510.20064v2 Announce Type: replace Abstract: Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection
arXiv:2604.21536v1 Announce Type: cross Abstract: Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantic
arXiv:2604.21360v1 Announce Type: new Abstract: Test-time adaptation (TTA) has emerged as a promising paradigm for vision-language models (VLMs) to bridge the distribution gap between pre-training and
arXiv:2604.21203v1 Announce Type: cross Abstract: We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as p
Sam Altman shared a brief positive message on X expressing satisfaction with recent team accomplishments and progress. The post reflects optimism about ongoing projects and company morale at OpenAI.
arXiv:2604.21435v1 Announce Type: new Abstract: Ultra-High-Resolution (UHR) imagery has become essential for modern remote sensing, offering unprecedented spatial coverage. However, detecting small ob
arXiv:2604.21327v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization sig
arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning
arXiv:2604.21450v1 Announce Type: cross Abstract: Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for
arXiv:2511.13587v2 Announce Type: replace-cross Abstract: Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm
arXiv:2604.08016v2 Announce Type: replace Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an
arXiv:2604.19767v1 Announce Type: cross Abstract: We evaluate speculative decoding with EAGLE3 as an inference-time optimization for PayPal's Commerce Agent, powered by a fine-tuned llama3.1-nemotron-
arXiv:2604.19753v1 Announce Type: new Abstract: We propose a feature-free approach to algorithm selection that replaces hand-crafted instance features with pretrained text embeddings. Our method, Zero
arXiv:2604.20516v1 Announce Type: cross Abstract: Determining identifiability of causal effects from observational data under latent confounding is a central challenge in causal inference. For linear
arXiv:2603.26747v2 Announce Type: replace Abstract: Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies th
arXiv:2604.20093v1 Announce Type: new Abstract: Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independe
arXiv:2604.20452v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as c
looks like new Pareto frontiers across everything: - Context: 400K context in Codex and a 1M in API - API Pricing: 5/m input and 30/m output tokens. - Codex improved its own inference speed 20% lol -
arXiv:2602.15353v2 Announce Type: replace-cross Abstract: Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowled
Recurrent Neural Networks (RNNs) are naturally suited to efficient inference, requiring far less memory and compute than attention-based architectures, but the sequential nature of their computation h
arXiv:2604.20783v1 Announce Type: new Abstract: Internal ice layers imaged by radar provide key evidence of snow accumulation and ice dynamics, but radar-derived layer boundary observations are often
arXiv:2604.19810v1 Announce Type: new Abstract: Can scientific discovery be made arbitrarily easy by choosing the right representation, collecting enough data, and deploying sufficiently powerful algo
there are early signs of 5.5 being a competent ai research partner. several researchers let 5.5 run variations of experiments overnight given only a high level algorithmic idea, wake up to find comple
Hugging Face and AMD have collaborated to quantize the Kimi-K2.6 model to MXFP4 format, enabling efficient inference on AMD hardware. MXFP4 is a low-precision floating-point quantization technique tha
arXiv:2604.20574v1 Announce Type: new Abstract: Purpose: Gaze-following, the task of inferring where individuals are looking, has been widely studied in computer vision, advancing research in visual a
b8891 is a release version of llama.cpp, which is a tool for LLM inference in C/C++. llama.cpp is a free and open-source tool that allows users to run AI models locally on Windows, Linux and macOS. Th
arXiv:2604.19648v1 Announce Type: cross Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary s
arXiv:2604.19561v1 Announce Type: new Abstract: Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Att
arXiv:2604.19124v1 Announce Type: new Abstract: Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity
arXiv:2604.19021v1 Announce Type: new Abstract: Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advanc
arXiv:2604.19736v1 Announce Type: new Abstract: Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundament
Speculative decoding is a technique that accelerates language model inference by using a smaller draft model to generate candidate tokens, which are then verified by a larger model, reducing latency w
arXiv:2604.18907v1 Announce Type: cross Abstract: A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional gene
arXiv:2604.18866v1 Announce Type: new Abstract: Despite advances in object detection, aerial imagery remains a challenging domain, as models often fail to generalize across variations in spatial resol
arXiv:2510.04686v2 Announce Type: replace-cross Abstract: Model merging combines independent solutions with different capabilities into a single one while maintaining the same inference cost. Two popu
As AI inference demand surges and enterprise compute budgets buckle under expanding workloads, x86 efficiency has emerged as one of the most powerful — and underutilized — levers in cloud financial ma
arXiv:2510.04800v3 Announce Type: replace Abstract: Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space mod
arXiv:2604.19536v1 Announce Type: new Abstract: Recent navigation systems achieve strong benchmark results, yet real-world deployment often remains visibly stop-and-go. This bottleneck arises because
This post likely demonstrates running Qwen2 3.6B or 27B model in GGUF format using llama-server with default specifications, showcasing inference capabilities of quantized open-source models. The comm
arXiv:2604.19679v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within
Q1 2026 Shareholder Update https://ir.tesla.com/#quarterly-disclosure We continued to make meaningful progress on the build out of the infrastructure & AI software that underpins our Robotaxi & future
arXiv:2512.19442v3 Announce Type: replace-cross Abstract: Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and sp
arXiv:2604.19144v1 Announce Type: new Abstract: Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). Existing approaches predominantly ad
arXiv:2510.17925v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs an
arXiv:2510.24738v2 Announce Type: replace-cross Abstract: Running offers substantial health benefits, but improper gait patterns can lead to injuries, particularly without expert feedback. While prior
arXiv:2604.19295v1 Announce Type: new Abstract: Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the r