Knowledge catalogue
arXiv:2609.24377v1 Announce Type: cross Abstract: We study latent-space watermarking through a pretrained generator using a prescribed latent-to-output stochastic mapping, called the renderer. A water
arXiv:2609.23185v1 Announce Type: new Abstract: Lossy compression of scientific simulation data increasingly relies on learned, latent-space architectures such as Residual Vector Quantization (RVQ), w
arXiv:2608.28860v1 Announce Type: new Abstract: Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space interventi
arXiv:2605.21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representat
arXiv:2408.15344v2 Announce Type: replace Abstract: Many scientific and engineering problems involve observing a common phenomenon through multiple heterogeneous sensors or measurement modalities. Suc
arXiv:2610.02801v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades sub
arXiv:2608.16195v1 Announce Type: new Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a profound challenge, particularly in contact-rich and hi
arXiv:2608.11254v1 Announce Type: new Abstract: Accurate solar irradiance forecasting is essential for the reliable integration of photovoltaic power into modern electricity grids. All-sky imagers (AS
arXiv:2608.11435v1 Announce Type: new Abstract: Forward and inverse modeling of parametric dynamical systems requires surrogate models that are not only accurate for state prediction, but also informa
arXiv:2606.01374v1 Announce Type: new Abstract: Observable performance is commonly used to characterize biological systems. In adaptive systems, however, similar performances may arise from distinct o
arXiv:2606.02486v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models generalize across static manipulation but fail when objects move during task execution. They map the current observa
arXiv:2609.37924v1 Announce Type: cross Abstract: Recent work on anchored diffusion language models improves denoising by shaping an intermediate latent space with supervised important-token targets.
arXiv:2609.15668v1 Announce Type: cross Abstract: Through pre-training on extensive text and image datasets, current multi-modal large language models (MLLMs) achieve strong performance on general tas
arXiv:2609.15338v1 Announce Type: cross Abstract: Large Language Models (LLMs) primarily perform inference at the token level, resulting in substantial memory overhead and compromised computational ef
Good Start Labs experiments show that AI training with gameplay can lead to transferable skills: a version trained on a railroad simulation outperformed peers in financial research. Inspired by Twitch
arXiv:2607.26460v1 Announce Type: new Abstract: Mobile manipulation requires generating whole-body action chunks that jointly satisfy goal reaching, collision avoidance, base kinematic constraints, ma
arXiv:2607.23837v1 Announce Type: cross Abstract: Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forge
arXiv:2607.24569v1 Announce Type: cross Abstract: Model-based active flow control requires predictive models that are accurate, stable, and fast enough for real-time optimisation. In controlled wake f
OpenAI’s Codex, an AI‑powered coding engine, has surged beyond the developer community to reach over 10 million users—combining Codex with its new “ChatGPT Work” platform that turns the model into a g
arXiv:2606.04249v1 Announce Type: new Abstract: Prospective reconstruction is crucial in many clinical applications such as MRI-guided radiotherapy, which demands accurate image reconstruction and fas
arXiv:2605.27852v1 Announce Type: cross Abstract: Unified and scalable Transformers have recently achieved remarkable success in modeling diverse phenomena traditionally associated with computer graph
arXiv:2605.17284v1 Announce Type: cross Abstract: End-to-end autonomous driving systems powered by Vision-Language-Action (VLA) models achieve strong performance on common driving scenarios, yet remai
arXiv:2510.04006v2 Announce Type: replace Abstract: Data-driven machine learning (ML) models are reshaping weather forecasting and have shown the potential to accelerate and surpass traditional physic
arXiv:2605.15862v1 Announce Type: new Abstract: Adaptive biomechanical systems may show similar observable gait performance while differing in latent organization and longitudinal behavior. This study
arXiv:2609.31720v1 Announce Type: new Abstract: Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through chara
In September 2026, Anthropic unveiled a suite of new AI products—Claude Tag, Sonnet 5.5, Fable/Mythos 5.1—and infrastructure releases such as Opus 5.5 and a plugins portal, following a record 47 billi
arXiv:2609.30557v1 Announce Type: cross Abstract: Runtime failure monitors can use a model's internal representations to anticipate failures. We audit this monitoring strategy across two autonomous-dr
System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the
arXiv:2609.10898v1 Announce Type: new Abstract: Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally,
arXiv:2609.10715v1 Announce Type: new Abstract: We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining beyond standard next-token prediction (NTP). Alongsid
arXiv:2609.04516v1 Announce Type: cross Abstract: Recent work on controllable music generation has focused on autoregressive models, leaving diffusion-based systems comparatively underexplored. We pre
arXiv:2609.00332v1 Announce Type: cross Abstract: Generative models for implied volatility surfaces must produce outputs that satisfy static no-arbitrage constraints. We study these constraints in lat
arXiv:2608.21595v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning ability of vision-language models (VLMs), and diversifying the rollouts wit
arXiv:2608.13305v1 Announce Type: cross Abstract: Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly
arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-
arXiv:2606.31268v1 Announce Type: cross Abstract: The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. D
arXiv:2602.15382v2 Announce Type: replace Abstract: Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete
arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web s
arXiv:2605.06225v2 Announce Type: replace-cross Abstract: Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong con
arXiv:2602.09034v2 Announce Type: replace-cross Abstract: Neuroimaging does not observe causal variables directly: hemodynamics and volume conduction distort signals so that statistical dependence nee
arXiv:2604.08636v1 Announce Type: cross Abstract: Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimizat
At AI Engineer New York 2026, Anthropic introduced **dynamic workflows** (also called “flows”), a new type of multi‑agent orchestration designed for large, ambitious workloads using Claude Managed Age
Standard Bots develops AI‑native industrial robot arms (used for machine tending, welding, assembly) that rely on a shared pretrained base model with 1–2 billion parameters. The model is adapted to ea
From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly underst
Ahmad Al‑Dahle joined Airbnb as CTO in January 2026 after leading Meta’s Llama generative‑AI models (2023–2025). He is steering an “inside‑out AI” strategy that deploys internal AI tools—such as the c
arXiv:2604.02751v3 Announce Type: replace Abstract: Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate
Radical Numerics, led by CEO Eric Nguyen, is deploying “biological chain‑of‑thought” and multimodal perception techniques to stay ahead of the evolving bio‑defense arms race, enabling rapid design of
In September 2026 OpenAI announced that an AI‑assisted team using the Astra‑next model solved the Navier–Stokes Millennium Prize Problem in 88 hours. The effort employed roughly 10,000 agents processi
GPT‑6 Astra is a lightweight, high‑performance OpenAI model that can be hired for under $6 an hour and outperforms rivals on tests such as FrontierMath (97.6%) and ARC‑AGI‑3 (99.9%). The authors burne
Simile AI’s CEO Joon Sung Park describes how the company moved from the 2024 “Summer of Simulative AI” and its landmark *Generative Agents* paper to building digital twins that predict individual and
ChatGPT Work was launched by OpenAI on July 9, 2026 as an agent‑oriented knowledge‑work platform that combines chat, Codex tools and cloud agents across fourteen model configurations. Within three wee
Poolside AI’s co‑CEO Eiso Kant explains that a small, top‑research team built a model‑factory capable of training Laguna S, a 118‑billion‑parameter mixture‑of‑experts model that outperforms the ~1 tri
According to this Latent Space article, OpenAI has launched GPT 5.6 with variants named Sol, Terra, and Luna, while integrating Codex capabilities into ChatGPT to create a broader superapp platform. T
SpaceX's AI division has launched Grok 4.5, positioned as their first Opus-class model following the acquisition of Cursor. The release represents a significant capability upgrade in SpaceX's AI offer
Lilian Weng provides a comprehensive summary of 35 research papers focusing on Harness Engineering approaches for Reasoning and System Integration (RSI), covering recent developments in this specializ
This article discusses how AI infrastructure needs to adapt to support autonomous agents effectively, with insights from Modal's CTO on the technical and architectural requirements for agent deploymen
This article from Latent Space provides an overview of Fable, covering its capabilities, architecture, or use cases as an AI model or framework. The guide likely serves as a reference resource for dev
This dispatch from Latent Space discusses debates within the AI engineering community regarding 'loops' in AI systems and the current state of AI engineering practices. The article likely covers techn
Andrew Qu from Vercel discusses how AI agents represent a fundamentally different category of software compared to traditional applications, exploring their unique characteristics and implications for
This dispatch examines the emerging capabilities and challenges of AI autoresearch systems, analyzing the tension between autonomous AI agents conducting research and the preservation of human agency