Knowledge catalogue
arXiv:2606.06470v1 Announce Type: cross Abstract: We propose a preconditioning (PC) layer, a weight parameterization via polynomial preconditioner that ensures stable weight conditioning throughout LL
arXiv:2509.20324v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with ex
arXiv:2505.11766v4 Announce Type: replace-cross Abstract: Neural Operators (NOs) are powerful architectures for learning mappings between function spaces. While most advances focus on refining kernel
arXiv:2601.09236v3 Announce Type: replace-cross Abstract: Reward design remains a significant bottleneck in applying reinforcement learning (RL) to real-world problems. A popular alternative is reward
arXiv:2602.07840v3 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained hu
arXiv:2606.05241v1 Announce Type: cross Abstract: Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the
arXiv:2606.05510v1 Announce Type: new Abstract: Telehealth systems have become increasingly important for delivering accessible and timely medical information. Existing large language models often str
arXiv:2606.05779v1 Announce Type: cross Abstract: Autonomous spacecraft require rapid, lightweight, and reliable onboard detection of cyber-RF threats. Using the SPARTA attack model, we analyze the la
arXiv:2512.15783v3 Announce Type: replace Abstract: This paper proposes a measurement standardisation framework that compresses expert-AI interactions into structured, comparable fields for prospectiv
arXiv:2606.06285v1 Announce Type: new Abstract: Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In r
arXiv:2606.05852v1 Announce Type: cross Abstract: Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirem
VLA-JEPA just dropped in LeRobot 🤖 What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relev
arXiv:2606.05304v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that age
arXiv:2606.06034v1 Announce Type: cross Abstract: Matrix inversion in chunk-wise parallel linear attention is a major bottleneck for long-context modeling, particularly on NPUs, where forward-substitu
Your margin is my opportunity: AI version… The biggest surprise of 2026 is that the capability gap between the best open-weight/source models and the best closed models has narrowed much faster than t
Coco Feng / South China Morning Post: A research team that includes Huawei says it successfully used Huawei's Ascend 910C chips for DeepSeek V4 Pro model's post-training, amid increased US sanctions —
arXiv:2510.05544v2 Announce Type: replace Abstract: Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and comp
arXiv:2512.05774v2 Announce Type: replace-cross Abstract: Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried i
arXiv:2606.05622v1 Announce Type: new Abstract: Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are pro
arXiv:2602.09574v2 Announce Type: replace Abstract: Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment often imposes a fixed per
arXiv:2509.15061v2 Announce Type: cross Abstract: The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions.
arXiv:2606.05557v1 Announce Type: new Abstract: A situated query like 'where is Lin Wei?' often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good
Release b9528 of llama.cpp was published on June 5, 2026. This build includes a UI update to run npm install when package-lock.json is newer than node_modules, and provides pre-compiled binaries for m
arXiv:2606.05711v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks
arXiv:2606.05586v1 Announce Type: new Abstract: In remote sensing object detection, Convolutional Neural Networks (CNNs) excel at capturing local details while Vision Transformers (ViTs) are better at
arXiv:2606.06492v1 Announce Type: cross Abstract: Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long i
arXiv:2606.06359v1 Announce Type: new Abstract: In this study, UAV multispectral imagery is used to segment the severity of bacterial leaf blight (BLB) in rice using convolutional neural networks (CNN
arXiv:2606.06477v1 Announce Type: new Abstract: Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to
arXiv:2510.05709v2 Announce Type: replace-cross Abstract: LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assumptions that frequently do not hold in practice: (
arXiv:2606.05753v1 Announce Type: new Abstract: Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses
arXiv:2606.05290v1 Announce Type: new Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring ret
arXiv:2508.15851v2 Announce Type: replace Abstract: Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information
arXiv:2601.21288v2 Announce Type: replace-cross Abstract: Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and
arXiv:2601.18383v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) excel at solving complex problems by explicitly generating a reasoning trace before deriving the final answer. H
arXiv:2606.05179v1 Announce Type: new Abstract: Punctuation restoration improves ASR (Automatic Speech Recognition) readability. However streaming ASR requires online decisions with limited future con
arXiv:2605.24496v2 Announce Type: replace Abstract: The EPIC-KITCHENS-100 Action Detection challenge evaluates whether a model can localize the start and end of each action in long untrimmed egocentri
arXiv:2512.21430v2 Announce Type: replace Abstract: Visuomotor policies based on generative such as diffusion and flow-matching have shown strong performance for robotics applications but degrade unde
arXiv:2606.05415v1 Announce Type: new Abstract: Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inco
arXiv:2606.06363v1 Announce Type: new Abstract: Urban green-space extraction from ultra-high-resolution (UHR) imagery is commonly performed patch by patch, which limits semantic reuse among spatially
Highlights: 👉 Design-first generation for ads, posters, packaging, and product visuals 👉 Strong typography and multilingual text rendering 👉 Precise layout and color-palette control for brand workflow
arXiv:2606.06388v1 Announce Type: cross Abstract: Recent advances in LLM agents have enabled complex cognitive capabilities, such as multi-step reasoning, planning, and tool use, that increasingly pos
arXiv:2606.06100v1 Announce Type: new Abstract: Vision-Language Models (VLMs) struggle with compositional reasoning that requires understanding inter-object relationships. A natural remedy is to injec
arXiv:2606.05174v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong promise in healthcare applications. Yet deploying general-purpose models in real-world settings remains d
arXiv:2606.06458v1 Announce Type: cross Abstract: Multiple Instance Learning (MIL) addresses problems where supervision is available at the level of bags of instances and has been successfully applied
Introducing Ideogram 4 from @ideogram_ai on Together AI, an open image model built for design with strong text rendering, layout control, and native 2K image generation. AI natives can now use Ideogra
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialize
arXiv:2606.05182v1 Announce Type: new Abstract: Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered
arXiv:2606.05538v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment chall
arXiv:2502.14145v3 Announce Type: replace Abstract: Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This
arXiv:2606.06042v1 Announce Type: new Abstract: Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier fie
arXiv:2606.05843v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract
arXiv:2606.05743v1 Announce Type: cross Abstract: Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifi
arXiv:2606.05443v1 Announce Type: cross Abstract: The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce M
arXiv:2606.05545v1 Announce Type: new Abstract: The development of multilingual Alzheimer's Disease Dementia (AD) detection models presents significant challenges due to the resource-intensive and tim
arXiv:2606.05261v1 Announce Type: new Abstract: Variable fonts enable continuous variation of glyph geometry along semantic design axes such as weight, width, slant, and optical size. However, constru
arXiv:2606.06080v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficul
arXiv:2606.05703v1 Announce Type: new Abstract: Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token
arXiv:2605.25970v2 Announce Type: replace Abstract: Clinical pathways are disseminated as visual flowcharts where spatial topology, arrow direction, colour coding, and font weight encode critical tria
arXiv:2606.05773v1 Announce Type: new Abstract: Vision-language-action (VLA) policies operate in a closed loop in real-world robot tasks: a robot observes the scene, executes an action chunk, and cond
arXiv:2606.06255v1 Announce Type: cross Abstract: Point clouds are a primary sensory representation for robotic perception, underpinning LiDAR-based autonomous driving, simultaneous localization and m