Knowledge catalogue
This week we launched the world's most accurate document extraction agent over real-world documents. Introducing LlamaExtract Agentic Plus 💫 . It is a complete document extraction model+harness engine
To the extent that AI use boosts firm performance, some early signs here that early AI adopting firms that were already doing well may start to outpace others. Data from OpenAI shows some firms are us
To use Computer History, opt in under Settings → Integrations in the ChatGPT desktop app on Mac. Rolling out globally now to Pro, Business, and Enterprise users, with access in the EEA, UK, and Switze
With all the Suno drama over their download limits and their heavy watermarking that could be used for future copystrikes if you stop paying them, this Minimax Music 3 couldn't be more on time. I trie
arXiv:2608.11638v1 Announce Type: cross Abstract: Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable
When enterprises transition from using simple chat assistants to autonomous, agentic workloads, they quickly run into a hard truth: Agents are prone to inaccurate insights when working with directly r
arXiv:2608.11050v1 Announce Type: cross Abstract: Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of t
arXiv:2608.10470v1 Announce Type: new Abstract: Fair representation learning with a continuous sensitive attribute S requires a representation Z that is statistically independent of S. Existing criter
arXiv:2608.11110v1 Announce Type: new Abstract: When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compa
arXiv:2608.10817v1 Announce Type: new Abstract: Zero-shot object-goal navigation (ZSON) in open-vocabulary scenarios is challenging, as it requires a robot to locate an arbitrarily specified object in
arXiv:2608.10791v1 Announce Type: new Abstract: Runtime hazard monitors for autonomous naviga- tion are conventionally built from geometric quantities: predicted clearance, time to collision, and requ
arXiv:2608.10679v1 Announce Type: cross Abstract: Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are wor
Four small architecture decisions can cost up to 47% of a model's long-context performance. New research from Ai2, Carnegie Mellon, and the University of Washington isolates them. Normalization, GQA,
arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy.
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challen
Grok 4.6 topped the GDPVal-AA benchmark with an Elo score of 1,753. It surpassed competitors Fable 5 Max (1,741 Elo), GPT‑5.6 Sol Max (1,728 Elo) and Grok 4.5 High (1,526 Elo). Elon Musk publicly ackn
A 36‑page ArXiv whitepaper titled **ExtractBench** was released by Jerry Liu (jerryjliu0), describing a large‑scale, schema‑guided benchmark for real‑world document extraction from complex enterprise
arXiv:2608.10672v1 Announce Type: cross Abstract: Social interaction has become one of the most common uses of LLMs, yet research on emotional bonds with AI has focused largely on how users experience
arXiv:2608.10562v1 Announce Type: new Abstract: Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), ye
arXiv:2608.10021v1 Announce Type: new Abstract: Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitati
arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c
arXiv:2608.10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff. Deduplication filters, seman
arXiv:2608.10474v1 Announce Type: cross Abstract: Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increas
Try Grok 4.6 on tough real-world tasks! imo GDPVal is probably the most important benchmark, it measures the performance of models on real world tasks Big leap in performance here to top it at a great
Very interesting new work from Anthropic. (bookmark it) They evolve mind viruses, ideas that spread through a multi-agent system by getting each host to pass them on, then measure what governs the spr
We wrote a 36-page ArXiv whitepaper on ExtractBench 🧑🔬 , our effort to create the most comprehensive, schema-guided, real-world document extraction benchmark. It’s extremely detailed and covers every
Yukon: Open Innovation for Frontier Research Open Innovation has been the driving value at Eigen Labs. But I’ve often struggled with where it is actually better than a great closed team. Finally we fo
⚡️A coalition that secures long-term AI capacity: We’re aggregating long-term compute demand in Europe to determine what capacity is built, where it’s located, and whom it serves. Through these multi-
Imagine this scenario: Your team decides to migrate a core application from an existing commercial database like Oracle or SQL Server to open source PostgreSQL or a fully managed service such as Alloy
arXiv:2608.09289v1 Announce Type: new Abstract: Second language writing research distinguishes grammatical accuracy from native-like idiomaticity, yet automated writing evaluation often conflates thes
arXiv:2608.07637v1 Announce Type: new Abstract: Long-running molecular simulation campaigns require repeated continuation from saved states, provenance-aware progression, adaptive assessment, and occa
arXiv:2608.01344v2 Announce Type: replace Abstract: Stage-one stellarator design searches a high-dimensional family of three-dimensional plasma boundaries and fixed-boundary MHD equilibria for configu
arXiv:2608.07895v1 Announce Type: cross Abstract: Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behavi
Security operations platform startup Blumira Inc. today launched Hearth, a vendor-agnostic artificial intelligence command center that lets security teams investigate and act across their existing too
arXiv:2608.09025v1 Announce Type: new Abstract: Financial agents can turn correct context into an unauthorized effect: a customer-facing commitment, trade, or deployed policy. We present SAGE-Fin, a f
arXiv:2608.09360v1 Announce Type: cross Abstract: The demand for maritime surveillance has given rise to the need for monitoring fishing vessel activities, particularly in addressing the challenge of
arXiv:2608.08642v1 Announce Type: new Abstract: We study exact Kullback--Leibler (KL) projection for low-rank factorizations whose two nonnegative factors have prescribed row marginals and a shared, l
ExtractBench is one of the most comprehensive benchmarks for real-world document extraction. ✅ It covers 4869 pages, across 67 document types, spanning 8 real-world domains: finance, energy, gov, auto
arXiv:2608.07474v1 Announce Type: new Abstract: Prior work showed that human-in-the-loop oversight becomes structurally untenable in high-loss domains when AI output velocity V exceeds human cognitive
Runtime intelligence startup FriskAI Inc. launched today with 3.6 million in pre-seed funding to give enterprises a record of what their artificial intelligence agents actually do once they go into pr
arXiv:2608.08941v1 Announce Type: cross Abstract: Operational Design Domain (ODD) specifications describe where an automated driving system (ADS) is permitted to operate, but they do not prescribe wha
arXiv:2608.09480v1 Announce Type: new Abstract: A model alone does not determine how a programming agent acts. What the model sees, how actions enter the environment, how feedback returns, and how one
arXiv:2608.07627v1 Announce Type: new Abstract: Hospitals are racing to embed AI, while coping with the surge in adaptation of the technology in other industries, into the triage management, documenta
arXiv:2608.09048v1 Announce Type: new Abstract: Deep learning-based building footprint extraction from high-resolution imagery often produces topologically inconsistent vectors unfit for direct GIS da
arXiv:2608.09225v1 Announce Type: cross Abstract: The key-value (KV) cache is the primary throughput optimization in modern large language model (LLM) inference, enabling prefix reuse across requests.
arXiv:2608.07500v1 Announce Type: cross Abstract: Research on human-GenAI collaboration yields conflicting findings: GenAI can enhance creativity yet reduce collective diversity, with uneven benefits
arXiv:2608.07640v1 Announce Type: new Abstract: Land Surface Temperature (LST) is a widely used satellite-derived measure of urban surface heat, but there is no shared benchmark for forecasting it at
arXiv:2608.08915v1 Announce Type: new Abstract: Situated language use is multimodal and embodied. For example, gestures can carry information that is absent or underspecified in the speech signal, yet
arXiv:2608.08588v1 Announce Type: cross Abstract: Hamiltonian Monte Carlo (HMC) is a successful generic inference method in probabilistic programming, but in its ordinary formulation it needs gradient
arXiv:2511.20849v2 Announce Type: replace-cross Abstract: We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed
arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large L
arXiv:2608.08467v1 Announce Type: new Abstract: The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequentl
arXiv:2608.09870v1 Announce Type: cross Abstract: Uniform stability is a classical tool for controlling the generalization error of a learning algorithm. Bousquet, Klochkov, and Zhivotovskiy (2020) sh
arXiv:2608.08820v1 Announce Type: new Abstract: Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such
For organizations deploying AI agents at scale, there’s often a critical divide between structured and unstructured data. While large language models (LLMs) excel at parsing text documents, emails, an
Looking for a faster specialized model for your Agent Work? @nvidia Nemotron 3.5 Lightning (30B MoE, 3B active params) is now live on Fireworks. It’s distilled from NVIDIA Nemotron 3 Ultra to be your
arXiv:2410.10523v3 Announce Type: replace-cross Abstract: The aim of this book is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimi
arXiv:2608.07556v1 Announce Type: cross Abstract: Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original a
In August 2026, Together AI entered into a multi‑year partnership with IBM and NVIDIA to deliver enterprise‑grade open‑source AI inference on IBM Cloud. The collaboration deploys a dedicated NVIDIA B3
arXiv:2608.08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global