b9259
Release b9259 of llama.cpp fixes a nullptr crash in the speculative common module's get_devices_str function (PR #23386). The fix addresses an issue where ggml_backend_dev_by_name appends a nullptr se
Knowledge catalogue
Release b9259 of llama.cpp fixes a nullptr crash in the speculative common module's get_devices_str function (PR #23386). The fix addresses an issue where ggml_backend_dev_by_name appends a nullptr se
Release b9260 of llama.cpp includes OpenCL backend refactoring that improves initialization, GPU identification, and performance by caching global memory size in device context. llama.cpp enables LLM
Release b9263 of llama.cpp includes a merge of HunyuanOCR into HunyuanVL with fixes to OCR vision precision. The update consolidates OCR functionality into the HunyuanVL projector while maintaining co
b9264 is a llama.cpp release that includes improvements to HunyuanVL model support, merging HunyuanOCR functionality and fixing vision precision issues. This build represents an intermediate developme
b9266 is a release tag for llama.cpp, a project for LLM inference in C/C++. This release represents a specific build version of the llama.cpp framework, which enables LLM inference with minimal setup
Release b9270 adds support for the HybridDNATokenizer used by the Carbon-3B model family, implementing a new BPE pre-type for tokenizing DNA sequences. The tokenizer handles DNA k-mers with fixed 6-me
Release b9273 of llama.cpp introduces support for the HybridDNATokenizer with new pre-type and dispatched tokenization logic, alongside pure helper functions for DNA k-mer processing and conversion ut
Release b9275 of llama.cpp includes optimization of the Metal concat kernel and fixes to the GGML_OP_SET kernel threads . The release extends test coverage for copy operations with different source an
arXiv:2509.26005v3 Announce Type: replace-cross Abstract: We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields -- a
arXiv:2503.00565v3 Announce Type: replace-cross Abstract: The multi-armed bandits (MAB) framework is a widely used approach for sequential decision-making, where a decision-maker selects an arm in eac
arXiv:2502.06178v5 Announce Type: replace-cross Abstract: Bayesian optimization is highly effective for optimizing expensive-to-evaluate black-box functions, but it faces significant computational cha
arXiv:2602.08819v2 Announce Type: replace-cross Abstract: Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to
This post likely discusses strategies for creating or embodying cultural relevance and capturing the spirit of the times, possibly in the context of technology, AI, or creative work. The author, Crist
arXiv:2605.21214v1 Announce Type: new Abstract: Reinforcement learning (RL) often exhibits high variance across training runs, leading to unreliable performance and posing a major challenge to deploym
arXiv:2605.21111v1 Announce Type: new Abstract: Feedforward steering control is a key component of hierarchical control architectures for autonomous racing. The goal is to reduce steering corrections
Jagmeet Singh / TechCrunch: Bengaluru-based Scapia, which offers travel-focused co-branded credit cards and an app, raised 63M led by GC, a source says at a 500M+ post-money valuation — Scapia, an Ind
arXiv:2605.20797v1 Announce Type: new Abstract: The present paper introduces a new representation-driven approach to per-instance algorithm selection, applied to black-box optimization, for automatica
arXiv:2605.20610v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal
arXiv:2605.20684v1 Announce Type: new Abstract: Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages a
arXiv:2605.21027v1 Announce Type: new Abstract: Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional
arXiv:2605.20996v1 Announce Type: new Abstract: Most value-based and actor--critic reinforcement learning methods rely on Bellman-style recursions, yet these recursions collapse under non-exponential
arXiv:2505.14654v2 Announce Type: replace-cross Abstract: Chatbots via large language models (LLMs) generate fluent responses but often struggle with when to speak, especially for brief, timely listen
Biomedical AI may be headed for a replication crisis. (This work below is not about AI-generated reports; it’s about studies of biomedicine that use ML in their methods, and how they are evaluted.) In
arXiv:2509.07120v2 Announce Type: replace Abstract: Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models li
Steven Lee Myers / New York Times: Bluesky and Clemson researchers detail a novel Russian influence campaign that hijacked legitimate, influential accounts to spread pro-Kremlin propaganda — The compa
In this post, you will learn how to implement Recursive Language Models (RLM) using Amazon Bedrock AgentCore Code Interpreter and the Strands Agents SDK. By the end, you will know how to process docum
arXiv:2503.22693v2 Announce Type: replace-cross Abstract: The rapid advancements in Large Language Models (LLMs) have unlocked transformative possibilities in natural language processing, particularly
arXiv:2605.20942v1 Announce Type: new Abstract: Structured road understanding of lane geometry, topology, and traffic element relationships is foundational to safe autonomous driving. While vision-lan
This post likely describes a feature allowing users to relocate or organize their side conversations (chat panels or sidebars) to different positions within an interface, providing flexibility in how
Crowdsourced cybersecurity company Bugcrowd Inc. today launched Reinforcement Learning Environments, a new offering that lets frontier artificial intelligence labs train models on real vulnerable soft
This guide demonstrates how to build a coding assistant using Weaviate's Model Context Protocol (MCP) integration, enabling retrieval-augmented generation (RAG) capabilities over codebases and documen
In this post, we show you how OPLOG developed three AI agents using the Strands Agents SDK, deployed them to Amazon Bedrock AgentCore, and integrated Amazon Bedrock with Anthropic’s Claude Sonnet and
This solution combines the power of Amazon Bedrock AgentCore, Strands Agents, and Amazon Quick transforms to deliver a secure, scalable, and intelligent system for building and operating AI agents whi
In this post, we demonstrate how to build an AI-powered recruitment assistant using Amazon Bedrock that brings efficiencies to candidate evaluation, generates personalized interview questions, and pro
arXiv:2605.21029v1 Announce Type: new Abstract: Utilizing LLMs for automated taxonomy construction presents a clear opportunity for the comprehensive, yet efficient mapping of potentially complex doma
arXiv:2605.20786v1 Announce Type: new Abstract: This paper reflects on twenty years of building NLP resources and research infrastructure for Arabic, a language spoken by hundreds of millions yet hist
arXiv:2601.15133v3 Announce Type: replace Abstract: Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale
Telcos are building sovereign AI factories based on the NVIDIA Cloud Partner reference architecture to provide secure, in-country AI infrastructure with controls and performance suited for enterprise
arXiv:2603.08155v3 Announce Type: replace Abstract: Classifier-Free Guidance (CFG) is a cornerstone of modern conditional diffusion models, yet its reliance on the fixed or heuristic dynamic guidance
arXiv:2605.20872v1 Announce Type: new Abstract: Adaptive densification is the engine of 3D Gaussian Splatting (3DGS). However, when transposed to the optimization-based Generative Distillation paradig
arXiv:2605.20915v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making
arXiv:2605.20439v1 Announce Type: new Abstract: Explainable AI (XAI) techniques aim to provide insights into predictive models and enhance user performance, yet they often fall short of these expectat
Liveness detection and synthetic media detection models often fail to generalize across unseen data and struggle with content from different models. Understanding how factors like data source diversit
arXiv:2602.06500v2 Announce Type: replace Abstract: Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promi
arXiv:2605.20282v1 Announce Type: new Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-leve
can’t believe people assume that success on highly verifiable problems in math (where we don’t even know how many tests were performed and how many might have failed) iautomatically generalize to ever
arXiv:2605.20337v1 Announce Type: new Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into hi
arXiv:2510.00520v2 Announce Type: replace Abstract: Foundation models are reshaping medical imaging, yet their application in echocardiography remains limited, hindered by a heavy reliance on private
arXiv:2605.20468v1 Announce Type: new Abstract: Effective medication management in Parkinson's Disease (PD) is challenging due to heterogeneous disease progression, variable patient response, and medi
arXiv:2605.20269v1 Announce Type: new Abstract: Many bandit deployments (recommendation, clinical dosing, ad targeting) share two facts prior work handles only in isolation: rewards live on a low-dime
arXiv:2602.04907v2 Announce Type: replace Abstract: Causal discovery is a data-driven paradigm for analyzing complex systems, while physics-based models, such as ordinary differential equations (ODEs)
arXiv:2605.20782v1 Announce Type: new Abstract: Objective: The growing availability of large-scale observational clinical datasets and challenges in conducting randomized controlled trials have spurre
arXiv:2506.04042v2 Announce Type: replace Abstract: Knowledge editing is pivotal for efficiently updating the parametric memory of Large Language Models (LLMs), enabling them to function as evolving a
arXiv:2605.20341v1 Announce Type: new Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is co
Gary Marcus examines and fact-checks recent claims made by OpenAI and Anthropic in their public announcements and media coverage. The post links to detailed analysis questioning the mathematical valid
arXiv:2512.09806v2 Announce Type: replace Abstract: Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these
arXiv:2605.20992v1 Announce Type: new Abstract: We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape with 6D
arXiv:2605.20975v1 Announce Type: new Abstract: Federated Learning enables collaborative model training across decentralized data sources without data transfer. Averaging-based FL is limited by the pr
arXiv:2605.20268v1 Announce Type: cross Abstract: Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolati
arXiv:2605.21177v1 Announce Type: cross Abstract: This work presents extsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activate