Knowledge catalogue
arXiv:2606.02092v1 Announce Type: cross Abstract: Semantic segmentation of remote sensing imagery requires models that capture both global context and local detail under tight computational budgets. P
arXiv:2602.05649v2 Announce Type: replace Abstract: The long-standing dominance of gradient-boosted decision trees for tabular data has recently been challenged by in-context learning tabular foundati
arXiv:2605.27464v1 Announce Type: cross Abstract: AR smart glasses need continuous behavioral context to offer proactive assistance, yet their most practical always-on sensor, the head-mounted Inertia
arXiv:2605.27489v1 Announce Type: cross Abstract: Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretabilit
arXiv:2605.27678v1 Announce Type: new Abstract: Foundation model training is becoming multimodal, from post-training pipelines to large-scale pretraining. As modality coverage broadens, context window
arXiv:2605.28557v1 Announce Type: cross Abstract: LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remain
arXiv:2503.18893v2 Announce Type: replace Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent st
arXiv:2605.24657v1 Announce Type: new Abstract: Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedl
arXiv:2605.24930v1 Announce Type: new Abstract: Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain challenging because context windows are finite, and pr
In our new paper, EDGE-OPD (EviDence GuidEd On-Policy Distillation), we introduce two key ideas for improving On-Policy Distillation (OPD). First, we use guided rollouts that inject privileged context
arXiv:2605.26099v1 Announce Type: cross Abstract: Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context le
arXiv:2605.22863v1 Announce Type: new Abstract: LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer mode
arXiv:2510.21270v2 Announce Type: replace-cross Abstract: Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems pr
arXiv:2509.17396v4 Announce Type: replace Abstract: Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long convers
arXiv:2605.20868v1 Announce Type: new Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empiric
In this post, we demonstrate how you can extend the conversational memory of Kiro CLI by implementing a custom Model Context Protocol (MCP) server that integrates with Amazon Bedrock AgentCore Memory.
arXiv:2605.18565v1 Announce Type: cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accura
arXiv:2602.03664v3 Announce Type: replace Abstract: Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn a
arXiv:2605.16746v1 Announce Type: new Abstract: LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon inter
arXiv:2605.15723v1 Announce Type: cross Abstract: Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities la
arXiv:2605.14906v1 Announce Type: new Abstract: Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capabili
arXiv:2605.13473v1 Announce Type: new Abstract: Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall.
arXiv:2605.11644v1 Announce Type: cross Abstract: We study positive-data learning of bounded-fan-out linear multiple context-free grammars under a fixed explicit finite monoid homomorphism (h). The ma
May 2026 update: We’ve refreshed this post to reflect our mid-cycle positioning and the evolution of our platform since the report was first published last November. Last fall, Google was recognized a
Every day, thousands of hours of new video content sits waiting to be discovered. Most of it lives in long-form, horizontal formats, while audiences are scrolling through vertical feeds on their phone
// δ-mem: Efficient Online Memory for LLMs // One of the more elegant memory mechanisms I've seen this month. Most long-term memory work either inflates context or retrains the model. This paper shows
arXiv:2605.11496v1 Announce Type: cross Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and
arXiv:2512.06949v3 Announce Type: replace Abstract: Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-
arXiv:2605.10817v1 Announce Type: new Abstract: Clinical EEG interpretation requires reasoning over full EEG sessions and integrating signal patterns with clinical context. Existing EEG foundation mod
arXiv:2605.08587v1 Announce Type: cross Abstract: Long-context language modeling remains central to modern sequence modeling, but the quadratic cost of Transformer attention makes scaling computationa
arXiv:2605.08744v1 Announce Type: cross Abstract: Autoregressive (AR) models can generate high-quality low-poly meshes from point clouds, but they still operate in an all-or-nothing manner: when a loc
arXiv:2605.08580v1 Announce Type: cross Abstract: To cope with the large contexts that long-horizon LLM agents produce, modern frameworks increasingly rely on compaction -- invoking an LLM to rewrite
arXiv:2605.07129v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and
arXiv:2605.07760v1 Announce Type: new Abstract: Platform content moderation applies explicit policy rules and context-dependent conditions to decide whether user content is allowed, restricted, or rem
arXiv:2601.01285v2 Announce Type: replace Abstract: Medical image segmentation requires balancing local precision for boundary-critical clinical applications, global context for anatomical coherence,
arXiv:2605.07068v1 Announce Type: cross Abstract: The LLM Wiki pattern, to compile and provide domain knowledge into a persistent artifact and serve it to LLMs via KV cache inference, promises context
arXiv:2605.01667v1 Announce Type: new Abstract: Orderless encoding methods have shown to improve Convolutional Neural Networks (CNNs) for image classification in the context of limited availability of
arXiv:2605.01373v1 Announce Type: new Abstract: The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, cu
arXiv:2602.13933v2 Announce Type: replace Abstract: Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to ineffici
arXiv:2601.19827v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-re
A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l
Editor’s note: Want to keep up with the latest from Google Cloud? Check back here for a monthly recap of our latest updates, announcements, resources, events, learning opportunities, and more. We host
arXiv:2604.24978v1 Announce Type: new Abstract: Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We
arXiv:2604.22812v1 Announce Type: cross Abstract: STEM dropout rates remain high at universities, particularly in computer science programs with theory-intensive courses. Digital learning environments
arXiv:2604.24506v1 Announce Type: new Abstract: Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models
arXiv:2604.23994v1 Announce Type: cross Abstract: Discrete diffusion language models (dLLMs) enable parallel token updates with bidirectional attention, yet practical generation typically adopts block
arXiv:2604.22565v1 Announce Type: cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evi
arXiv:2604.21344v1 Announce Type: cross Abstract: Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple relate
arXiv:2604.20677v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across i
arXiv:2604.19564v1 Announce Type: cross Abstract: Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhib
arXiv:2604.19457v1 Announce Type: new Abstract: Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy mem
Today at Google Cloud Next, we are unveiling a more proactive Gemini Cloud Assist, our AI-assisted cloud operations platform. This update shifts your Google Cloud operations from manual workflows to a
arXiv:2510.04800v3 Announce Type: replace Abstract: Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space mod
INT3 compression with fused Metal kernels enables large language models to compute attention operations directly on compressed (INT3/INT4) key-value cache representations using custom GPU kernels that
arXiv:2604.19028v1 Announce Type: new Abstract: One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face
As AI models improve, technical practitioners are increasingly turning to agentic AI tools to build with Google Cloud products, from Firebase and the Gemini API, to BigQuery and GKE. But how can you e
arXiv:2604.18835v1 Announce Type: cross Abstract: We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise documen
arXiv:2510.17925v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs an
Succeeding in the agentic era requires a transformation in your data strategy: moving from human-scale to agent-first workloads, evolving from reactive intelligence to proactive action, and shifting f
arXiv:2604.18257v1 Announce Type: cross Abstract: Query auto-completion (QAC) has been widely studied in the context of web search, yet remains underexplored for in-document search, which we term DocQ