Knowledge catalogue
Speculative decoding is a technique implemented in llama.cpp that speeds up inference by using a smaller, faster model to predict multiple tokens ahead, which a larger model then verifies in parallel,
arXiv:2607.06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed water
arXiv:2601.12494v3 Announce Type: replace-cross Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect
arXiv:2607.05533v1 Announce Type: new Abstract: Computational pathology foundation models (PFMs) have advanced whole-slide image analysis. However, their size and inference cost hinder local deploymen
arXiv:2607.05736v1 Announce Type: new Abstract: Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture
My team talks directly to *my* AI workforce. They can skip me entirely. It's the first time working with AI agents actually feels team-oriented and collaborative (and not just one person becoming more
arXiv:2607.05577v1 Announce Type: new Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether
arXiv:2607.05623v1 Announce Type: new Abstract: We re-implement the NAVER LABS IWSLT 2025 instruction-following pipeline for the IWSLT 2026 Shared Task (constrained condition, short audio track), adap
arXiv:2607.05955v1 Announce Type: cross Abstract: Interactive 3D segmentation aims to extract object masks in point clouds with minimal user clicks. Despite recent progress, most existing approaches s
arXiv:2607.05722v1 Announce Type: new Abstract: We introduce Nemotron-Labs-Diffusion, a tri-mode language model (LM) that unifies AR, diffusion, and self-speculation decoding within a single architect
New in Claude Code: /checkup Run /checkup to: 1. Clean up unused skills/MCPs/plugins and save context 2. Dedup your local CLAUDE.md against the checked in CLAUDE.md 3. Break up root CLAUDE.md into nes
Nice stats on usage of open models across OpenCode. GLM-5.2 is still underrated, but one of the models that has really surprised me on agentic tasks is deepseek-v4-flash. Extremely cheap and effective
nope! OpenAI would not have the nerve. Hey @GaryMarcus, quick question. Did you get months of early access to OpenAI's GPT-5.6 Sol like every AI influencer on X apparently did? Asking because their re
Not another demo or benchmark. @ShoucongChen is a senior member of our technical staff. A real project, scoped at 1-month. Delivered in 4 days with GLM5.2 Fast. The best devs deserve >400 t/sec. Take
NVIDIA Nemotron 3 Ultra is offering leading performance at lower cost than top closed models with the largest and most widely adopted AI agent orchestration platform. LangChain tuned its Deep Agents h
arXiv:2602.00846v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) struggle with alignment due to the limitations of existing reward models (RMs), which are predominantly vis
arXiv:2607.05805v1 Announce Type: new Abstract: Dilution refrigerators are the enabling infrastructure of superconducting quantum computers, yet their fault diagnosis is still dominated by threshold a
- OpenAI continually outperforms Anthropic models on computer use (with Claude, I’m surprised when it works, with Codex, I expect it to work) - when I prompt with Fable 5.5, I feel like I’m motivating
OpenAI: OpenAI launches GPT-Live, a new generation of voice models built on a full-duplex architecture, meaning they can listen and speak at the same time — A new generation of voice models for natura
OpenAI Group PBC today introduced GPT-Live, a family of artificial intelligence models optimized to process spoken instructions. The model series will power ChatGPT’s voice mode. Additionally, OpenAI
OpenAI: OpenAI says it found widespread task issues in SWE-Bench Pro, estimates ~30% of tasks are broken, and retracts its earlier recommendation to adopt the benchmark — Through a detailed audit, we
arXiv:2607.05737v1 Announce Type: new Abstract: In the Versatile Video Coding~(VVC) standard, adaptive loop filter~(ALF), including Geometry transformation-based Adaptive Loop Filter~(GALF) and Cross
arXiv:2607.06337v1 Announce Type: cross Abstract: Robotic tree-fruit harvesting is a flagship problem for agricultural automation, but progress is bottlenecked by the cost and irreproducibility of fie
Our audit of SWE-Bench Pro found that a meaningful share of public tasks contain issues that can distort results. Some correct solutions fail because of hidden requirements, contradictory instructions
Own the frontier: 'In our evals, Nemotron 3 Ultra with a tuned LangChain Deep Agents harness provides advanced agent performance at a much lower inference cost. The main takeaway is that agent perform
arXiv:2607.05476v1 Announce Type: new Abstract: Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of inte
arXiv:2312.08230v2 Announce Type: replace Abstract: Detecting partial extrinsic symmetry in 3D geometry is a fundamental yet persistent challenge in computer vision and graphics, critical for tasks ra
arXiv:2607.05483v1 Announce Type: cross Abstract: Agentic workflows often operate over shared, structured state. Because LLM context windows are limited, each model invocation is typically shown only
arXiv:2607.05915v1 Announce Type: new Abstract: PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule
arXiv:2607.06440v1 Announce Type: new Abstract: Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences. We study personaliz
arXiv:2607.06196v1 Announce Type: new Abstract: Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional law
arXiv:2607.05992v1 Announce Type: cross Abstract: Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heav
arXiv:2607.05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Rea
arXiv:2607.06008v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong performance in long-horizon tasks that require planning, tool use, and interaction with external env
arXiv:2607.05626v1 Announce Type: new Abstract: Background: Depression frequently co-occurs with ADHD and autism spectrum disorder (ASD), but population-level differences in symptom expression between
arXiv:2607.05479v1 Announce Type: cross Abstract: Generative AI (GenAI) systems store and process client data in three distinct ways: in the model's parameters through training and memorisation, in th
arXiv:2607.06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, vis
Prompt: ANNALS — a living kingdom in a single file Working title behavior: the app titles itself per seed — 'The Annals of Vaelmere', 'The Annals of Osterholt' — because the central conceit is that yo
TL;DR Elastic recently published a benchmark claiming that their proprietary, disk-based index (dubbed “DiskBBQ”) delivers up to 7x higher throughput than Qdrant when deployed on nodes with network-at
arXiv:2603.02277v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, cr
Really excited to partner with @nvidia on the NemoClaw Deep Agents Blueprint Deep Agents is a fully open source agent harness that we are tuning to make perform incredibly well with open models Introd
Artificial intelligence optimization startup Refiant Inc. today launched Protea, a suite of long-context AI models led by a 10 million-token context window that the company says ranks among the larges
Rewriting Bun in Rust Jarred Sumner has been promising this blog post (since May 9th) about his Zig to Rust rewrite of Bun for significantly longer than it took him to finish the rewrite. Honestly, it
arXiv:2607.06148v1 Announce Type: new Abstract: Fine-grained food image retrieval is a key task in computational gastronomy, with applications in food traceability, dietary monitoring, and smart cater
arXiv:2607.05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generali
arXiv:2607.06411v1 Announce Type: cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of
arXiv:2607.05613v1 Announce Type: new Abstract: Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly, leading to pervasiv
arXiv:2509.25723v4 Announce Type: replace Abstract: Visual Place Recognition (VPR) requires robust retrieval of geotagged images despite large appearance, viewpoint, and environmental variation. Prior
arXiv:2607.05443v1 Announce Type: cross Abstract: Scientists increasingly rely on open-source tools to support their research workflows, yet discovering relevant software among over 600 million GitHub
arXiv:2607.05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback. In applied settings, the environment usually prov
arXiv:2604.00421v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned rout
This OpenAI article discusses methods for distinguishing meaningful performance indicators from random variation when evaluating AI coding capabilities. It likely covers evaluation methodologies, stat
arXiv:2606.13757v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed in automated code-review systems, where their approvals can determine which code is mer
arXiv:2509.24966v2 Announce Type: replace Abstract: Understanding how people interact with their surroundings and each other is essential for enabling robots to act in socially compliant and context-a
Carmen Arroyo / Bloomberg: SpaceXAI launches Grok 4.5, its first model built in partnership with Cursor, designed to “handle difficult, long-running” legal, finance, and coding tasks — SpaceXAI has un
Elon Musk’s SpaceXAI Corp. has released a new model called Grok 4.5, in what is its first major launch since it went public a few weeks earlier. In a blog post earlier today, the company said Grok 4.5
arXiv:2607.05721v1 Announce Type: new Abstract: Uncertainty estimation is essential not only for the trustworthy deployment of large language models (LLMs) but also as a foundation for self-refinement
arXiv:2508.16560v4 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) extract features from LLM internal activations, meant to correspond to interpretable concepts. A core SAE training
arXiv:2607.06229v1 Announce Type: cross Abstract: Major cloud data platforms now expose large language model capabilities as native SQL functions, enabling analysts to perform classification, filterin
arXiv:2607.05436v1 Announce Type: new Abstract: The rapid scaling of over-parameterized machine learning architectures, particularly LLMs, raises a profound crisis: do these systems exhibit genuine in