Knowledge catalogue
Google I/O is a virtual event featuring two keynote presentations: a Consumer Keynote at 10:00 AM PT and a Developer Keynote at 1:30 PM PT. The event showcases Google's latest products, innovations, a
I've been thinking a lot about the two different groups of evals you need in general agents/agents which handle broad tasks: 1. Benchmark evals - this is a suite of up to 100 eval cases which test the
arXiv:2605.17415v1 Announce Type: cross Abstract: We propose IVF-TQ, an IVF index with a codebook-free residual layer: a fixed random rotation followed by precomputed Lloyd-Max scalar quantization dep
arXiv:2605.16812v1 Announce Type: new Abstract: While Local Differential Privacy (LDP) serves as a foundational primitive for distributed data collection, its stringent noise injection requirement oft
🔥 JD Vance just wrapped his press briefing by voicing his FULL SUPPORT for Tommy Robinson's Unite the Kingdom rally 'What you see all over the west is this idea that the way to generate prosperity is
arXiv:2603.29167v2 Announce Type: replace Abstract: We study a systems-level visual inference problem: using an expensive privileged modality during training while preserving a fixed-cost, single-moda
Join tunneling – the underground movement Elon Musk on why tunnels became reality: “Everyone thought it was a joke. We made it a company” The idea behind The Boring Company is actually simple physics
Join us as a Forward Deployed Engineer! looking for someone to help us bring Hermes agent to the world. if you're a hermes agent power user and want to help others become one as well, hit my dms or em
arXiv:2602.15405v2 Announce Type: replace Abstract: Robust classification in noisy environments remains a fundamental challenge in machine learning. Standard approaches typically treat signal enhancem
arXiv:2602.17679v2 Announce Type: replace Abstract: Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing
arXiv:2508.00712v2 Announce Type: replace-cross Abstract: We introduce JSON Bag-of-Tokens model (JSON-Bag) as a method to generically represent game trajectories by tokenizing their JSON descriptions
arXiv:2605.16896v1 Announce Type: new Abstract: Contextual Automatic Speech Recognition (ASR) faces challenges with large-scale keyword dictionaries, as excessive irrelevant candidates introduce noise
I can't verify this claim based on reliable sources. The post appears to make allegations about San Diego police withholding information regarding a mosque shooting and the identities of suspects, att
arXiv:2605.18657v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) have demonstrated notable success in general-purpose forecasting tasks; however, their adaptation to specialized
.@karpathy at @AnthropicAI = more open-source from them? They're already contributing datasets: https://huggingface.co/Anthropic but would be super cool to see more (massive potential for impact obvio
arXiv:2601.06633v2 Announce Type: replace-cross Abstract: Open-ended tasks, such as coding problems that are common in computer science education, provide detailed insights into student knowledge. How
arXiv:2605.16278v1 Announce Type: cross Abstract: The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that ma
arXiv:2605.16376v1 Announce Type: cross Abstract: Kelvin is a lightweight learned pre-encoder that sits in front of an unmodified libx264 encoder. It applies content-adaptive pixel adjustments, bounde
arXiv:2605.18556v1 Announce Type: cross Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, curre
arXiv:2605.17856v1 Announce Type: new Abstract: Process-based simulation models encode decades of scientific understanding across the Earth sciences, yet the communities most exposed to climate risk a
arXiv:2605.18261v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has demonstrated promising potential to enhance the reasoning capabilities of large language model
Mark Maurer / Wall Street Journal: KPMG partners with Anthropic to embed Claude into its tax and advisory platforms; KPMG's tax and legal services unit saw revenue grow ~8% YoY to $9.3B in 2025 — The
arXiv:2605.16439v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning t
arXiv:2605.18071v1 Announce Type: new Abstract: Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the ful
arXiv:2605.17730v1 Announce Type: cross Abstract: Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to t
arXiv:2605.16743v1 Announce Type: new Abstract: Cross-embodiment learning from human demonstrations is hindered by the visual gap between human and robot embodiments. While self-supervised learning (S
arXiv:2602.01705v3 Announce Type: replace-cross Abstract: Reinforcement learning has become a central paradigm for improving LLM reasoning, but most existing methods optimize policies over discrete to
What the numbers mean for financial services Executive summary Lambda is the first to publish an audited STAC-AI™ LANG6 result on NVIDIA HGX 8xB200, with independently verified performance data that F
arXiv:2605.18678v1 Announce Type: cross Abstract: We present Lance, a lightweight native unified model supporting multimodal understanding, generation, and editing for both images and videos. Rather t
LangSmith Engine is a tool within the LangChain ecosystem that provides visibility and debugging capabilities for AI applications built with LangChain. This technical deep-dive likely covers how the e
LangGraph.js Long-Term Memory Store is now generally available. This integration brings long-term memory across sessions, across users, and across time, with Atlas as the unified backend for checkpoin
arXiv:2605.16758v1 Announce Type: new Abstract: Large Language Models (LLMs) remain substantially less data-efficient than humans. Pre-pretraining (PPT) on synthetic languages has been proposed to clo
arXiv:2605.16321v1 Announce Type: new Abstract: Language carries thought and coordination among humans but rarely reaches further along the spectrum of diverse intelligence. Yet non-neural systems --
arXiv:2409.02428v4 Announce Type: replace-cross Abstract: Achieving the effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and m
arXiv:2605.18646v1 Announce Type: new Abstract: Backdoor attacks on language models pose a growing security concern, yet the internal mechanisms by which a trigger sequence hijacks model computations
arXiv:2508.04047v2 Announce Type: replace Abstract: Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while e
arXiv:2602.08437v5 Announce Type: replace Abstract: In Chomsky's provocative critique 'The False Promise of CHATGPT,' Large Language Models (LLMs) are characterized as mere pattern predictors that do
arXiv:2605.16352v1 Announce Type: cross Abstract: Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream obje
arXiv:2605.16899v1 Announce Type: new Abstract: A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert t
arXiv:2605.17902v1 Announce Type: new Abstract: Stochastic-process-based degradation modeling is a core approach for estimating the distribution of remaining useful life (RUL); however, the selection
arXiv:2605.17256v1 Announce Type: cross Abstract: This work introduces a latency-aware benchmarking framework for evaluating deep learning models in power system anomaly detection using high-fidelity,
arXiv:2605.16961v1 Announce Type: cross Abstract: Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically tran
arXiv:2605.18597v1 Announce Type: new Abstract: Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inf
arXiv:2605.17137v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into evolutionary frameworks has established a new paradigm for automated heuristic discovery. Despite t
arXiv:2601.20888v3 Announce Type: replace-cross Abstract: We study sampling from posterior distributions in Bayesian linear inverse problems where A, the parameters to observables operator, is computa
arXiv:2605.17766v1 Announce Type: new Abstract: Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhib
LaunchDarkly, a feature control platform that helps developers and software engineers launch and manage products, today announced the launch of AgentControl, a new solution providing real-time managem
arXiv:2605.16358v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, se
arXiv:2508.15878v2 Announce Type: replace-cross Abstract: Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling
arXiv:2605.17289v1 Announce Type: cross Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shifting the bottleneck from inference execution to the
arXiv:2605.18704v1 Announce Type: cross Abstract: Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise that invalidate the station
arXiv:2605.17927v1 Announce Type: new Abstract: In various surgical procedures, regions of interest (ROIs) such as organs or lesions are often occluded by overlying tissues, requiring surgeons to achi
arXiv:2605.16357v1 Announce Type: cross Abstract: WiFi fingerprint-based indoor localization has been widely studied, but most existing approaches focus on absolute positioning and rely on dense coord
arXiv:2605.17419v1 Announce Type: cross Abstract: Rainfall-induced landslides pose a growing risk worldwide as climate change intensifies extreme rainfall events. To provide sufficient evacuation time
arXiv:2605.17379v1 Announce Type: cross Abstract: Large language models pretrained on general-domain corpora often exhibit tokenization inefficiencies when applied to specialized domains. Although con
arXiv:2605.17362v1 Announce Type: new Abstract: Matrix reordering in large sparse solvers seeks a permutation that minimizes factorization fill-in to reduce memory and computation. Because the minimum
arXiv:2601.01123v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A
arXiv:2601.22297v2 Announce Type: replace Abstract: The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). A
arXiv:2605.17316v1 Announce Type: cross Abstract: Sensor networks increasingly govern modern infrastructure, yet the data they lose are rarely missing in the uniform-random patterns assumed by standar
arXiv:2605.16632v1 Announce Type: cross Abstract: Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transf