Search: “concepts”

**llm-server v2** is a community-developed local LLM server tool that introduces AI-driven self-tuning capabilities, automatically identifying and applying optimal performance flags for **llama.cpp**

arXiv:2604.08443v1 Announce Type: new Abstract: The potential of Animal-Robot Interaction (ARI) in welfare applications depends on how much an animal perceives a robotic agent as socially relevant, no

arXiv:2604.08133v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the s

arXiv:2601.20524v2 Announce Type: replace Abstract: Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent

arXiv:2604.07041v1 Announce Type: cross Abstract: Text-to-SQL is the task of translating natural language queries into executable SQL for a given database, enabling non-expert users to access structur

arXiv:2604.06674v1 Announce Type: cross Abstract: Meaning in Persian poetry is both historical and relational. Words persist through literary tradition while shifting their force through changing cons

arXiv:2604.06701v1 Announce Type: new Abstract: Autoencoders are widely used for dimensionality reduction, based on the assumption that high-dimensional data lies on low-dimensional manifolds. Regular

arXiv:2604.08111v1 Announce Type: cross Abstract: Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness impl

arXiv:2604.07354v1 Announce Type: new Abstract: The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes do

LoRA (Low-Rank Adaptation) and ControlNet are complementary but fundamentally different tools for controlling Stable Diffusion image generation. LoRA modifies a model's weights to teach it new sty...

arXiv:2601.08950v3 Announce Type: replace Abstract: Despite their growing adoption in education, LLMs remain misaligned with the core principle of effective tutoring: the dialogic construction of know

arXiv:2604.07147v1 Announce Type: cross Abstract: Large language models produce repetitive output when prompted independently across many batches, a phenomenon we term cross-batch mode collapse: the p

arXiv:2604.07180v1 Announce Type: cross Abstract: We propose a geometric framework for longitudinal multi-parametric MRI analysis based on patient-specific energy modelling in sequence space. Rather t

arXiv:2604.08548v1 Announce Type: new Abstract: Human body fitting, which aligns parametric body models such as SMPL to raw 3D point clouds of clothed humans, serves as a crucial first step for downst

arXiv:2511.15496v2 Announce Type: replace Abstract: Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. M

arXiv:2604.08535v1 Announce Type: cross Abstract: Generalization under distribution shift remains a central bottleneck for closed-loop autonomous driving. Although simulators like CARLA enable safe an

Replit has introduced a Tax Skill, an AI-powered tool designed to assist users with tax-related questions and guidance during tax season. The skill likely leverages Replit's AI agent capabilities to h

arXiv:2604.07799v1 Announce Type: new Abstract: Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing appro

Migrating your existing application load balancer infrastructure from an on-premises hardware solution to Cloud Load Balancing offers substantial advantages in scalability, cost-efficiency, and tight

arXiv:2603.23286v3 Announce Type: replace Abstract: Physical knot classification is a fine-grained task in which the intended cue is rope crossing structure, but high accuracy may still come from appe

arXiv:2508.15358v2 Announce Type: replace Abstract: In many planning applications, we might be interested in finding plans that minimally modify the initial state to achieve the goals. We refer to thi

arXiv:2604.06451v1 Announce Type: new Abstract: Manufacturing test flows in high-volume electronics production are typically fixed during product development and executed unchanged on every unit, even

In an April 9, 2026 Substack post, AI skeptic Gary Marcus argues that Anthropic's announcement of its Claude 'Mythos' model was significantly overhyped, offering three key reasons for skepticism: t...

arXiv:2604.07916v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) aims to segment image regions described by natural-language expressions, serving as a bridge between vision and

TGIF! Here are some of our favorite updates from the past week: — Notebooks in @GeminiApp, an integration with @NotebookLM that enables you to retrieve context from your private notebooks or convert y

arXiv:2405.08253v3 Announce Type: replace-cross Abstract: This paper develops a viable notion of learning for sampling-based algorithms that applies in broader settings than previously considered. Mor

arXiv:2604.07522v1 Announce Type: new Abstract: Positional encoding has become the de facto standard for grounding deep neural networks on discrete point-wise positions, and it has achieved remarkable

arXiv:2604.06440v1 Announce Type: cross Abstract: Visual prompting (VP) has emerged as a popular method to repurpose pretrained vision models for adaptation to downstream tasks. Unlike conventional mo

arXiv:2604.08524v1 Announce Type: cross Abstract: Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explan

Anthropic's new hosted service for long-running AI agents, designed to solve the challenge of creating systems that support 'programs as yet unthought of.' It abstracts infrastructure management to en

Interrupt 2026 is LangChain's second annual AI agent conference, scheduled for May 13–14 at The Midway in San Francisco, focused on the question of how to deploy and operate AI agents at enterprise...

The impact that @swyx is already having on the London AI industry with @aiDotEngineer is incredible. Today there were builders from every frontier lab, the UK government, the hottest AI start-ups in L

Anthropic's Frontier Red Team report (April 2026) details the cybersecurity capabilities of Claude Mythos Preview, a general-purpose frontier model that performs strongly across the board but is s...

The specific X post by @ArthurMacwaters (status/2041749804477509654) is not directly accessible or indexed in available search results. However, based on the broader context found, here is a knowle...

A beginner-friendly tutorial demonstrating how to build a ~3.2M parameter LLM from scratch using Mary Shelley's *Frankenstein* as the sole training corpus, designed to run on Kaggle's free GPU in u...

Karpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.