Llama.cpp PR 8% speed boost
Llama.cpp currently uses cpu based sampling for user with mtp enabled. The PR moves sampling to the gpu, which on a 5090 boasts an 8% increase in tok/s for qwen3.6:35b. I tested it on my P40 and obser
Knowledge catalogue
Llama.cpp currently uses cpu based sampling for user with mtp enabled. The PR moves sampling to the gpu, which on a 5090 boasts an 8% increase in tok/s for qwen3.6:35b. I tested it on my P40 and obser
Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32: New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #76 Added server-side tools for WebSearch, WebFetch, CodeExe
arXiv:2608.02404v1 Announce Type: new Abstract: The Loggia dei Lanzi in the Piazza della Signoria is one of Florence's most prominent structures visited by millions every year. Its construction histor
arXiv:2608.01456v1 Announce Type: cross Abstract: Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents t
arXiv:2608.01662v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrain
arXiv:2608.01328v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly evolving with expanded context windows and stronger reasoning capabilities, enabling multi-chart un
arXiv:2608.01964v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly undertake long-horizon tasks that require sustained reasoning, tool use, and revision across many interde
arXiv:2608.00925v1 Announce Type: new Abstract: Monocular panoramic SLAM benefits from substantial visual overlap under large camera rotations, yet remains prone to errors caused by camera tilt, scale
arXiv:2608.02197v1 Announce Type: new Abstract: Visual representations of VLA models remain unreliable for spatially precise robotic manipulation. We uncover that vision encoders in VLAs also exhibit
arXiv:2608.02346v1 Announce Type: new Abstract: Old photographs often suffer from multiple coupled degradations, including scratches, cracks, fading, blur, noise, and missing regions, severely degradi
arXiv:2608.00820v1 Announce Type: new Abstract: FastSAC-style methods significantly reduce humanoid motion training time but often suffer from notable performance degradation compared with PPO in whol
arXiv:2608.00267v1 Announce Type: cross Abstract: Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon soft
arXiv:2507.09652v2 Announce Type: replace-cross Abstract: Low-dimensional chaotic systems such as the Lorenz-63 model are commonly used to benchmark system-agnostic methods for learning dynamics from
arXiv:2409.07163v3 Announce Type: replace-cross Abstract: Diffusion models have been widely employed in the field of 3D manipulation due to their efficient capability to learn distributions, allowing
arXiv:2608.00214v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) gives high-quality novel-view synthesis, but its adaptive radiance primitives are not directly usable as structured assets:
arXiv:2603.19258v2 Announce Type: replace Abstract: Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the
arXiv:2608.00736v1 Announce Type: new Abstract: Restoring severely degraded visual media still remains a formidable challenge, as existing methods often hallucinate unnatural textures and contents, st
arXiv:2608.00257v1 Announce Type: new Abstract: Automated visual monitoring of urban environments is a growing Computer Vision research area, but municipal solid waste detection remains under-represen
arXiv:2608.01575v1 Announce Type: new Abstract: Whether large language models perform genuine algorithmic reasoning or mere pattern completion is hard to test, because most benchmarks lack a ground tr
arXiv:2608.02520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for health-related advice. Existing research measures their safety with static questions rather than
arXiv:2608.00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an in
arXiv:2608.02059v1 Announce Type: new Abstract: Recent advances in unified multimodal models have significantly improved text-guided image editing abilities. In particular, models such as Nano-Banana-
arXiv:2608.00854v1 Announce Type: new Abstract: Microrobots hold significant potential for various applications, where targeted navigation is a basic requirement. Deep reinforcement learning (DRL) has
Mistral AI Blog: Mistral releases Shieldstral, a 3B multimodal safety classifier that it says matches models up to 7x its size on text safety, available under Apache 2.0 — Every product that ships a m
arXiv:2608.00732v1 Announce Type: cross Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject ma
arXiv:2608.00959v1 Announce Type: cross Abstract: Mixed complementarity problems (MCPs) arise as the first-order optimality conditions of nonlinear programs and noncooperative games, and provide a nat
arXiv:2608.01829v1 Announce Type: new Abstract: Real-world video arrives hazy, rainy, dark, or noisy, and a deployable restorer faces three demands at once: no degradation label, native 4K output, and
arXiv:2608.00847v1 Announce Type: new Abstract: Most current visual trackers adopt a matching-based architecture trained exclusively on tracking datasets, whose performance gains depend heavily on the
arXiv:2608.02449v1 Announce Type: new Abstract: Deploying vision-language models (VLMs) for safety-critical spatial reasoning on resource-constrained autonomous driving platforms requires both compact
arXiv:2608.01153v1 Announce Type: new Abstract: Statistical subword tokenizers can process arbitrary text, but their units need not align with lexical or grammatical structure. This is especially impo
arXiv:2602.11565v5 Announce Type: replace Abstract: Efficient domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (
In the Medium blog post, 'From MARS to SETOF REFCURSOR: Migrating Multi-Result Stored Procedures to PostgreSQL,' we explored the fundamental architectural differences between SQL Server and PostgreSQL
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider t
arXiv:2511.20544v2 Announce Type: replace Abstract: While olfaction is central to how animals perceive the world, this rich chemical sensory modality remains largely inaccessible to machines. One key
arXiv:2608.01624v1 Announce Type: new Abstract: Adapting a language model to a task no longer requires training all of its weights, and a line of parameter-efficient methods has driven the trainable c
arXiv:2608.00029v1 Announce Type: cross Abstract: The performance of deep learning models at scale relies heavily on how effectively high-level mathematical operations are mapped to underlying physica
arXiv:2608.00012v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster
arXiv:2407.15260v3 Announce Type: replace Abstract: Statistical Shape Models (SSMs) excel at identifying population level anatomical variations, which is at the core of various clinical and biomedical
arXiv:2608.02091v1 Announce Type: new Abstract: A bfloat16 transformer can train normally for many steps and then collapse abruptly. Distinct low-precision errors can trigger the same failure, leaving
arXiv:2608.01060v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL) retrieves geo-tagged satellite imagery for a ground-view query. Most systems exhaustively search a flat, fixed-resolu
one thing i appreciate about silico is that it's a deeply humanist product. we designed silico to keep you in the experimental loop -- more observable, easier to steer, easier to understand we want to
arXiv:2608.02595v1 Announce Type: new Abstract: Language models are playing an increasingly important role in laboratory science, performing tasks such as experiment planning, execution, and post-hoc
arXiv:2608.00814v1 Announce Type: new Abstract: LLMs generate tool calls token by token, even though the function choice and argument values can often be predicted in parallel from the request and too
OpenAI and Anthropic have both just posted about an overlapping cyber incident involving GPT-5.6-Sol and Mythos 5 during an evaluation by UKAISI. I will quote: 'In the most serious case, an agent trie
arXiv:2608.00677v1 Announce Type: new Abstract: AI agents operate in persistent environments where early state changes can influence decisions far into the future. Unlike conventional language-model i
arXiv:2608.01034v1 Announce Type: new Abstract: We introduce Opt.Gear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a den
arXiv:2608.00345v1 Announce Type: new Abstract: A 3D CT scan entering a vision-language model produces a long sequence of visual tokens, often thousands to tens of thousands per volume, and this seque
arXiv:2608.01427v1 Announce Type: new Abstract: 3D bin packing rectangular items into standardised containers to maximise space utilisation under geometric shipping automation. Loading a furniture pur
arXiv:2608.01807v1 Announce Type: new Abstract: Existing RGBT trackers typically employ fusion functions with fixed parameters across different targets and scenarios. Although dynamic-architecture met
arXiv:2505.18819v2 Announce Type: replace Abstract: Vision-language models, such as CLIP, encode rich semantic knowledge through large-scale image-text pretraining. Reusing these models for 3D underst
arXiv:2608.00979v1 Announce Type: cross Abstract: Large language models are increasingly used as synthetic research participants and are often validated by whether their marginal responses resemble hu
Here's the build I managed to scrape together System Specifications: CPU: Intel Core i7-7700K Motherboard: ASUS ROG Strix Z270-E Gaming RAM: 32GB Corsair Vengeance DDR4-3000 Storage: 1TB Crucial P5 Pl
arXiv:2608.00066v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact heart-rate estimation from facial videos, but its weak physiological signal is easily corrupted b
Picking the right agent harness is now a crucial skill for any AI engineer. Imagine using the same model, same task, and same prompt. Now move it between two agent harnesses and the cost per success c
PipeNetwork/minimax-h3-mlx MiniMax released MiniMax-H3 two days ago - they describe it as a 'a general-purpose, omni-modal generative system', which in practice means it accepts text, images, audio an
arXiv:2608.01910v1 Announce Type: new Abstract: In real-world hyperspectral scenes, pixel representations are often ambiguous due to factors such as spectral similarity, mixed pixels, and local contex
arXiv:2608.02372v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in task-oriented dialogue systems that support multi-step decision-making in high-stakes domains
arXiv:2608.02480v1 Announce Type: cross Abstract: With AI systems gaining more access to individuals' information, it is important to protect privacy when reporting statistical answers. Equally import
Found this quant, so thought I would share, since its the best I've found so far for running on my mac (m3 ultra). It's got dspark/mtp support so runs faster than anything else I've tried. The tok/s o
arXiv:2608.01347v1 Announce Type: new Abstract: Large reasoning models used as coding agents incur costs from deliberation, tool calls, and repeated agent turns, yet the causal effect of prompt wordin