Knowledge catalogue
Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured documents. Contracts, invoices, reports... All have special layout, language, and
arXiv:2606.05150v1 Announce Type: cross Abstract: The radial basis function neural network (RBFN) trained with a gradient descending algorithm provides an effective fully connected structure in both s
arXiv:2606.04067v1 Announce Type: cross Abstract: As LLMs become increasingly woven into everyday workflows, user queries sent to cloud hosted LLMs routinely mix task-essential content with task non-e
Nemotron 3.5 ASR is built for streaming multilingual speech recognition and voice agents. One 0.6B checkpoint. 40 language-locales. Sub-100ms latency. Cache-aware FastConformer carries context forward
arXiv:2606.04008v1 Announce Type: cross Abstract: Radiated noise in unmanned underwater vehicles (UUVs) is an important indicator for characterizing acoustic signatures and evaluating platform perform
Deploy NVIDIA Nemotron 3.5 Content Safety on Vultr Cloud GPU with Day Zero support for multimodal AI moderation, custom policy enforcement, multilingual safety workflows, and scalable enterprise AI go
Offroad Inc. launched today with 7 million in funding to build what it calls an agentic identity security team, using artificial intelligence agents to investigate and remediate access risks across hu
arXiv:2502.00470v3 Announce Type: replace-cross Abstract: Distributed empirical risk minimization (ERM) is often studied through two influential yet seemingly separate families of methods: CoCoA-type
arXiv:2606.04391v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online sk
arXiv:2606.04528v1 Announce Type: cross Abstract: Few-shot class-incremental learning (FSCIL) in synthetic aperture radar imagery presents unique challenges due to severe data scarcity and SAR-specifi
Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we thought
Our team is at CVPR 2026 if you want to come say hi :) We're presenting ParseBench at CVPR 2026! ParseBench is the most comprehensive document understanding benchmark for VLMs. ✅ It contains 2k pages
arXiv:2606.04599v1 Announce Type: new Abstract: Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in
arXiv:2606.04978v1 Announce Type: new Abstract: LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making me
arXiv:2606.04031v1 Announce Type: new Abstract: Coupled gradient descent--where the update of one parameter block depends on another--underlies bilevel optimization, two-time-scale stochastic approxim
arXiv:2606.05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sam
arXiv:2606.04857v1 Announce Type: new Abstract: Standard IMVC evaluation retrains separate models for different missing-data configurations. We show that this paradigm obscures a fundamental vulnerabi
arXiv:2606.04343v1 Announce Type: new Abstract: Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV
Safety by narrow control has shown to fail many times. Need more transparency on the absolute frontier, and openness close behind. I found another API that offers claude-oceanus-v1-p the pricing and t
arXiv:2606.04500v1 Announce Type: new Abstract: High-throughput microscopy generates large, structured datasets capturing cellular responses to pharmacological perturbations, but accessing these datas
arXiv:2606.04536v1 Announce Type: new Abstract: Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model
arXiv:2606.04503v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fu
arXiv:2606.05158v1 Announce Type: cross Abstract: Multi-agent reasoning systems adopt a 'generate-then-transfer' paradigm that forces end-to-end latency to scale linearly with pipeline depth. We intro
arXiv:2601.04051v3 Announce Type: replace Abstract: Symbolic regression aims to find symbolic expressions that describe datasets. Due to its inherent interpretability, symbolic regression (SR) is a po
The Canadian AI strategy unveiled today advocates for the development of technology that is safe, ethical, trustworthy, and that benefits society as a whole—these are exactly the principles that need
The capabilities of Claude Code and Codex have expanded a lot in recent months, they added many ways to approach work (subagents, skills, goal, workflows, plugins, etc). Given the AI labs can use thei
The new memory system will keep track of important details automatically. If you prefer the legacy saved memories experience, you can switch back in settings. The new memory system is rolling out to P
arXiv:2602.04613v2 Announce Type: replace Abstract: Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) h
arXiv:2606.04101v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load i
We're building in Canada. 🇨🇦 For decades, Canada invested to build the research foundations that made modern AI possible. Now we have to build, train, and scale what comes next here at home. Canada's
We're presenting ParseBench at CVPR 2026 today. 🦙 Come learn why document understanding is an AGI-complete problem (an agent can't act on a doc it can't correctly read, and reading a real enterprise t
We’ve been researching new ways for ChatGPT memory to carry context across conversations and keep it useful over time. Today, that work is rolling out as a more capable memory system in ChatGPT. https
arXiv:2606.04233v1 Announce Type: new Abstract: A robotics benchmark score measures success under one fixed evaluation setup, yet is routinely treated as evidence of general manipulation capability. W
arXiv:2606.04389v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We
arXiv:2603.09242v2 Announce Type: replace Abstract: The growing realism of generative models has blurred the boundary between real and synthetic content, posing significant challenges to reliable AI-g
arXiv:2606.04375v1 Announce Type: new Abstract: Differentially private stochastic gradient descent (DP-SGD) injects noise into every updated coordinate, making the injected noise energy scale with the
arXiv:2606.04662v1 Announce Type: cross Abstract: Muon improves training efficiency over Adam in large language-model training by about two times, but the local geometric source of this advantage rema
OpenAI introduced a new memory system for ChatGPT that allows users to review and control what the AI remembers across conversations through a memory summary feature. This update provides enhanced tra
This entry documents a Wordle game result where the player solved puzzle #1,810 in 4 attempts, using the color-coded feedback system (black for incorrect letters, yellow for correct letters in wrong p
arXiv:2606.04906v1 Announce Type: cross Abstract: Although it is generally agreed that AI-generated text poses a broad societal risk, there is no common understanding in the AI-generated text detectio
This benchmark demonstrates how integrating Alluxio with Ray Data achieves 20x faster training data read speeds for cross-region machine learning workloads on Anyscale's platform. The study shows perf
95% token reduction. 30x faster execution. 90%+ task completion. Today at #MSBuild, we announced a major shift to move reasoning upstream: Pinecone Nexus now integrates directly with @Microsoft OneLak
arXiv:2606.03646v1 Announce Type: new Abstract: This paper constructs the first benchmark on semi-supervised multi-modal crowd counting. To lay the foundation for this unexplored task, we first formul
arXiv:2601.04120v2 Announce Type: replace-cross Abstract: Optimal control of obstacle problems arises in a wide range of applications and is computationally challenging due to its nonsmoothness, nonli
A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon
arXiv:2606.03148v1 Announce Type: new Abstract: Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we
arXiv:2606.02663v1 Announce Type: cross Abstract: Recent advances in machine learning have produced probabilistic weather forecasting models comparable to state-of-the-art numerical weather predictors
arXiv:2606.03965v1 Announce Type: cross Abstract: Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little
arXiv:2606.03774v1 Announce Type: new Abstract: Eye tracking is essential for smart glasses, as it provides insight into user attention for ambient intelligence applications. However, most existing ey
arXiv:2606.02915v1 Announce Type: new Abstract: Visual posters are a compact medium for communicating dense information, yet progress on automatic poster generation remains difficult to measure becaus
arXiv:2604.04087v2 Announce Type: replace Abstract: We introduce ArrowFlow, a machine learning architecture that operates entirely in the space of permutations. Its computational units are ranking fil
This week we've got tandem hands-ons with Google's new Gemini AI agent - Spark - from my colleagues David Pierce and Jay Peters. Their takeaways are similar: It's so effective that it's scary. Spark k
arXiv:2507.21638v2 Announce Type: replace Abstract: The development of reinforcement learning (RL) algorithms has been largely driven by ambitious challenge tasks and benchmarks. Games have dominated
arXiv:2606.02604v1 Announce Type: cross Abstract: ESG and climate risk data remain fragmented across heterogeneous Scope 1, Scope 2, and Scope 3 reporting environments, while conventional validation p
arXiv:2606.03173v1 Announce Type: cross Abstract: The rise of `kidfluencers' on YouTube has raised ethical concerns about child digital labor and exploitation. While emerging legislation attempts to r
arXiv:2606.02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amor
b9491 is a release of llama.cpp , a C/C++ implementation of large language model inference that enables running LLMs locally with minimal dependencies. This release likely contains bug fixes, feature
arXiv:2606.03287v1 Announce Type: new Abstract: Feed-forward models for 3D reconstruction have achieved strong performance using deep cross-view attention to exchange information across images. Howeve
arXiv:2606.03259v1 Announce Type: new Abstract: Translation quality depends on purpose: the same source text demands different translations depending on audience, tone, and communicative intent. Yet M
arXiv:2606.03647v1 Announce Type: cross Abstract: Accurately evaluating adversarial robustness is a longstanding challenge. A flawed attack design can inflate robustness estimates, making deployment r