Knowledge catalogue
arXiv:2609.37841v1 Announce Type: new Abstract: Masked generative models offer parallel token prediction, but accurate parallel sampling must account for dependencies among tokens. When dependencies a
Generative recommender systems model recommendation as high‑cardinality event streams, turning user actions, context, and candidate items into tokens for sequence modeling over user behavior. NVIDIA’s
arXiv:2609.37013v1 Announce Type: cross Abstract: Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire relev
Today, we’re expanding our ecosystem of managed remote MCP servers by introducing the Google Cloud CLI remote MCP server in preview. Powered by the popular gcloud and bq (BigQuery) command-line tools,
arXiv:2609.37501v1 Announce Type: cross Abstract: We propose RegLLM, a diagnostic harness for bounded autonomy in regulated agentic workflows. It instruments six trustworthiness signals: citation vali
arXiv:2609.36531v1 Announce Type: new Abstract: Video world models are largely regarded as predictive models of the physical world and are therefore expected to anticipate the consequences of observed
arXiv:2609.36739v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that la
arXiv:2609.37037v1 Announce Type: new Abstract: High-resolution dynamic functional connectivity (DFC) can reveal rapidly evolving brain-network interactions, but short temporal windows yield noisy, of
arXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
arXiv:2609.36683v1 Announce Type: cross Abstract: Molecular optimization is inherently iterative: a candidate is proposed, evaluated against several objectives, and revised while preserving a relation
arXiv:2609.36859v1 Announce Type: new Abstract: We identify and study a structural mechanism for Markovian nonconvex ADMM in reinforcement learning. Using finite discounted MDPs as a canonical proving
arXiv:2508.13009v5 Announce Type: replace Abstract: Recent advances in interactive video generations have demonstrated diffusion model's potential as world models by capturing complex physical dynamic
arXiv:2609.36070v1 Announce Type: cross Abstract: AI accelerator systems are rapidly consolidating into scale-up architectures, where tens to thousands of GPUs communicate over high-bandwidth, single-
OpenAI's New Agent Stack: Superhuman Computer Use, Dots, Decisions API, UltraFast, & the AI Cloud https://www.latent.space/p/devday-2026 @OpenAI’s @AriX and @nikunjhanda explain why Computer Use is al
People are underestimating the impact of ultrafast AI on business. Lemme ramble on this for a second. People are using Ultrafast for impressive game development and crazy fast coding, but business use
arXiv:2609.37485v1 Announce Type: new Abstract: Bi-temporal change understanding, which localizes and characterizes what changed between two satellite images, is central to disaster response and envir
arXiv:2609.37717v1 Announce Type: cross Abstract: Decoder-only transformers are trained only through a terminal next-token prediction loss, yet this loss constrains every intermediate hidden state thr
Wulver v0.5 is a full fine-tune of Krea 2 Raw (the whole 12.8B DiT) for anime and anthro characters, including scenes where several characters interact. We made it at Vaelico, an independent studio. C
arXiv:2609.32965v2 Announce Type: replace Abstract: Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to
arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise their
So I would like to share my analysis of PD disagg that I've run by Horace and many folks at Thinky You may have heard that PD disagg helps with per-token 'tail latencies' in ITL/TPOT, as prefill inter
The Information: Sources: Google is paying ~100 digital publishers for how much their content contributes to AI Overviews, AI Mode, and Gemini in a pilot; payments vary widely — Google has been paying
arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control c
arXiv:2609.37082v1 Announce Type: new Abstract: Long-horizon information-seeking agents often accumulate noisy or misleading context, causing early mistakes to persist and making recovery increasingly
arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,
arXiv:2609.34594v1 Announce Type: new Abstract: Accurate capture of non-cooperative targets is critical. In an attempt to tackle this intractable challenge, an aerial gripper system integrated with a
Bloomberg: After lunch with AI leaders, Trump rejects new federal AI rules, says “we automatically have regulation” via DOJ and FBI but “self-regulation is very important” — President Donald Trump sho
arXiv:2609.35247v1 Announce Type: new Abstract: When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modality, or on internal read-outs, wh
arXiv:2609.33371v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn credential hygiene from a storage problem into an execution-security problem. A key pasted into a pr
arXiv:2609.33931v1 Announce Type: cross Abstract: Modern methods reconstruct or generate simulation-ready articulated objects, predicting not only their geometry but also how their parts are connected
As least year's DevDay, this is what OpenAI said agents would look like. This is before OpenClaw & self-organizing swarms, so this entire approach was scraped soon after: 1) AI is evolving quite quick
arXiv:2609.34924v1 Announce Type: new Abstract: An auditor who checks whether a system's weights are frozen is checking the wrong thing. Our stationarity dichotomy says that iterative self-modificatio
arXiv:2609.33940v1 Announce Type: new Abstract: Detecting failures in World Model (WM)-based planning requires monitoring whether the model is behaviorally aligned with the current task, which in turn
arXiv:2609.33764v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) perform well on homophilic graphs but struggle in heterophilic settings, where connected nodes often carry dissimilar label
arXiv:2609.33143v1 Announce Type: cross Abstract: Quarter-ahead revenue forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrativ
Data connectivity and integration firm CData Software Inc. today introduced Connect AI Gateway, a platform designed to control how artificial intelligence agents choose models, use tools and access co
arXiv:2609.32271v1 Announce Type: new Abstract: Post-hoc Bayesian fine-tuning places Gaussians around trained low-rank adapters, yet a calibrated posterior does not by itself yield a useful generaliza
arXiv:2609.33147v1 Announce Type: new Abstract: Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large language models without centralizing private client data. Its factorized
arXiv:2609.31786v1 Announce Type: cross Abstract: Maximum likelihood estimation of Markov deterioration hazard models for infrastructure asset management is sensitive to the numerical conditioning of
Over the last three decades in cybersecurity, I’ve witnessed major paradigm shifts — yet none match the velocity and complexity of today’s landscape. Attackers are now using AI to move at machine spee
arXiv:2609.35099v1 Announce Type: new Abstract: We present e3j, a fast Euclid-equivariance backend for geometric deep learning applications with JAX bindings for GPU and TPU. Leveraging both optimized
arXiv:2609.32176v1 Announce Type: new Abstract: The support recovery problem in mixture of linear classifiers intends to identify which features actually matter when data is generated by a mixture of
arXiv:2609.34633v1 Announce Type: new Abstract: Long-term memory supports the self-evolution of LLM agents by retaining experience and skills across tasks and enabling their retrieval, reuse, and revi
arXiv:2609.34166v1 Announce Type: new Abstract: We study the knowledge matrix of a trained feedforward network as a higher representation of its inputs. A network is a pair (W,f), a thin representatio
🚨 JUST NOW: Elon Musk and Jensen Huang give an INSIDE LOOK at the big meeting between top AI firms and President Trump today, saying they'll now be 'grading each other's homework' 😆 @elonmusk: 'We sig
arXiv:2609.35598v1 Announce Type: cross Abstract: We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fi
arXiv:2609.32874v1 Announce Type: cross Abstract: The first sentence of this abstract--and the introduction to these proceedings--was authored by a human, but the bulk of this document was generated b
arXiv:2601.06025v2 Announce Type: replace-cross Abstract: We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of s
arXiv:2609.31806v1 Announce Type: new Abstract: Accurate medium-term, from a few months to a few years, electricity load forecasts are crucial for informed decision-making in power plant maintenance s
arXiv:2609.33804v1 Announce Type: cross Abstract: Modeling spatiotemporal coupling is a key challenge in building physical intelligence across scales, from microscopic to macroscopic. Existing models
arXiv:2609.34986v1 Announce Type: cross Abstract: We describe the Nurnberg NLP system for ChildSafeAds 2026. The shared task asks what a monitoring system for commercial content in child-facing YouTub
Digital workspace company Omnissa LLC today unveiled new artificial intelligence agents for information technology teams and virtual desktop users, a managed cloud PC service and an AI governance prod
It’s OpenAI’s turn in the fall tech events calendar. The company is hosting its annual DevDay on September 29th in San Francisco, and during a live keynote featuring CEO Sam Altman, it revealed severa
Sarah Perez / TechCrunch: OpenAI expands ChatGPT plugins with interactive panels and file viewers, launches a Plugin Creator tool, and adds MCP Events support for plugin automations — OpenAI isn't onl
arXiv:2601.04692v2 Announce Type: replace-cross Abstract: In this work, we examine hateful memes from three complementary angles - how to detect them, how to explain their content and how to intervene
arXiv:2609.35499v1 Announce Type: new Abstract: As the world moves towards sustainable energy sources, hydrogen (H2) can be treated as an eco-friendly alternative to fossil fuels due to its high energ
arXiv:2509.22161v4 Announce Type: replace Abstract: Vector quantization, which discretizes a continuous vector space into a finite set of representative vectors (a codebook), has been widely adopted i
arXiv:2609.34179v1 Announce Type: cross Abstract: Retrieval-augmented generation systems are extensively instrumented with metrics, benchmarks, traces, and automated judges, but these tools do not dec
arXiv:2609.32389v1 Announce Type: new Abstract: Filmmakers and visual artists routinely need to compose multiple references, actors, locations, props, cultural elements, into a single coherent shot, b
arXiv:2609.32899v1 Announce Type: new Abstract: Hyperbolic space can embed intrinsic hierarchies in data with low distortion due to the exponential growth of volume with distance from the origin. Howe