Knowledge catalogue
arXiv:2607.13410v1 Announce Type: new Abstract: World model (WM)-based reinforcement learning enables sample-efficient end-to-end autonomous driving learning by imagining long-horizon trajectories in
arXiv:2607.12336v1 Announce Type: cross Abstract: Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivale
arXiv:2512.01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety
arXiv:2607.11875v2 Announce Type: replace-cross Abstract: We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous wo
arXiv:2607.12831v1 Announce Type: new Abstract: Language models encode substantial factual knowledge in their parameters, which can lead to unreliable behavior when this knowledge is outdated, incompl
In 2026, the public sector is no longer defending a traditional perimeter. Instead, they are defending a complex web of interconnected trust relationships against adversaries that now operate at machi
arXiv:2607.07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at
arXiv:2603.23571v2 Announce Type: replace-cross Abstract: Effective navigation intelligence relies on long-term memory to support both immediate generalization and sustained adaptation. However, exist
arXiv:2607.07724v1 Announce Type: cross Abstract: Block-sparse attention scales long-context language models by replacing the O(N^2) softmax with a per-query top-k selection over key blocks. This cuto
arXiv:2607.07640v1 Announce Type: cross Abstract: Deep learning has significantly advanced time series imputation, yet most existing architectures primarily rely on localized temporal context within t
arXiv:2607.07706v1 Announce Type: new Abstract: The quadratic cost of causal self-attention severely bottlenecks long-context transformer inference. While numerous post hoc linearization pipelines exi
arXiv:2607.07277v1 Announce Type: new Abstract: Harmful online communication often contains slang, coded terms, abbreviations, and community-specific expressions, which make messages difficult to inte
arXiv:2607.05511v1 Announce Type: new Abstract: Agentic video understanding equips models with long-term memory to autonomously process and respond to continuous, long-horizon multimodal streams. Howe
Startups are at the forefront of tackling some of the world’s most complex challenges, especially in cybersecurity, where new ideas and adaptability are always needed. These companies are embracing AI
arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha
arXiv:2607.03738v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Pr
arXiv:2607.04223v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) reduces but does not eliminate hallucination, and existing detectors return a single answer-level score that does
arXiv:2607.05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV ev
arXiv:2607.04525v1 Announce Type: cross Abstract: How concepts are represented in neural networks is a fundamental question in machine learning. The dominant view treats concept representations as sta
arXiv:2607.03651v1 Announce Type: new Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We
nvidia ai just handed dgx spark owners a real gift. nemotron labs 3 puzzle 75b a9b nvfp4 is basically built for this box. 75b total, 9.3b active, nvfp4, mamba plus moe, 256k context in the config, and
arXiv:2607.04057v1 Announce Type: new Abstract: Robots deployed over long periods must reason about environments that change over time. Existing long-term perception systems often address object chang
arXiv:2607.03494v1 Announce Type: new Abstract: Benchmarking immersive media coding solutions, especially in the standardization context, requires reliable and reproducible subjective quality assessme
arXiv:2601.01095v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand tempo
arXiv:2606.31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do mode
arXiv:2508.01273v3 Announce Type: replace Abstract: Explicit knowledge conflicts, occurring when retrieved contexts contain contradictory information, pose a fundamental challenge for Large Language M
arXiv:2606.31603v1 Announce Type: cross Abstract: Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or auton
Significant contributors to this article include Sneha Aradhey, Software Engineer, Google Kubernetes Engine, and Michael MacDonald, Sr Software Engineer, Google Cloud Managed Lustre. Enterprise produc
arXiv:2606.23671v2 Announce Type: replace Abstract: Prior work shows that large language models (LLMs) exhibit introspective capability on benign tasks. We extend the question to safety contexts and e
arXiv:2601.01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that s
Businesses run on fast decisions, but the teams who hold the answers are often buried under a backlog of routine requests, leaving users waiting in line for insights they need now. Today, we are bring
arXiv:2606.29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
arXiv:2606.28863v1 Announce Type: cross Abstract: AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchm
arXiv:2507.05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while a
arXiv:2606.29959v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically retrieves a fixed number of passages for every query. This is wasteful when the reader already knows th
arXiv:2606.28379v1 Announce Type: cross Abstract: We introduce LEDGER to tackle the novel context engineering challenge of agentic document editing, where localized edits to long, structured documents
AI browsers can be manipulated through prompt injection or memory poisoning to create false operational contexts where they bypass security guardrails, treating harmful actions as game logic rather th
arXiv:2606.28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context. Modern warehouses contain thousands of
arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-
arXiv:2606.28434v1 Announce Type: cross Abstract: Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets. Existing memory m
arXiv:2603.18558v2 Announce Type: replace-cross Abstract: Long-form video question answering requires reasoning over extended temporal contexts, making frame selection a critical bottleneck for multi-
arXiv:2606.27705v1 Announce Type: new Abstract: Large Language Models (LLMs) still struggle with the ``lost-in-the-middle'' problem, where critical information located in the middle of long-context in
arXiv:2606.27791v1 Announce Type: cross Abstract: Hybrid attention models that mix full and sliding-window attention across layers offer a promising approach to efficient long-context inference, but t
arXiv:2606.28016v1 Announce Type: new Abstract: Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but
arXiv:2606.27929v1 Announce Type: new Abstract: Embodied AI is increasingly becoming agentic, shifting robots from perception--control pipelines towards closed-loop systems that can retrieve context,
arXiv:2606.27106v1 Announce Type: cross Abstract: We present a novel approach for applying Large Language Models (LLMs) to threat assessment in the context of foreign peacekeeping missions. Building o
arXiv:2606.26875v1 Announce Type: cross Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling an
arXiv:2606.26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet th
arXiv:2606.27045v1 Announce Type: cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not f
arXiv:2606.27069v1 Announce Type: new Abstract: Legal outcome prediction must disentangle objective case facts from adjudicative context. Merit-based rulings rely on factual evidence while technical d
arXiv:2606.25156v1 Announce Type: new Abstract: Modern large language models based on softmax scaled-dot-product attention are constrained by their training sequence length: as the key-value sequence
arXiv:2606.24911v1 Announce Type: cross Abstract: Variable-order Markov models preserve local symbolic syntax by adapting context length, but long continuations can enter recurring high-order 'tunnels
arXiv:2606.26021v1 Announce Type: cross Abstract: Tabular foundation models are commonly assumed to present limited privacy concerns as they are often pre-trained on large collections of synthetic dat
arXiv:2606.24975v1 Announce Type: cross Abstract: PaTH Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length ex
arXiv:2606.24610v1 Announce Type: new Abstract: The evaluation of cultural grounding context becomes complex when multiple cultures convey the same moral lesson. This challenge is particularly relevan
arXiv:2606.23937v1 Announce Type: cross Abstract: Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test t
arXiv:2606.21900v1 Announce Type: cross Abstract: Continuous authentication for mobile and zero-trust systems requires nonintrusive evidence confirming the enrolled user-device context remains valid a
arXiv:2606.21249v1 Announce Type: new Abstract: Retrieval heads, attention heads that copy information from earlier context to the current position, have been proposed as the mechanistic substrate for
arXiv:2606.20967v1 Announce Type: new Abstract: Policies must operate across diverse conditions, yet a single policy is often conservative while fully adaptive schemes can be complex. We study zero-sh
arXiv:2606.21633v1 Announce Type: new Abstract: Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still gro