Knowledge catalogue
arXiv:2606.07623v1 Announce Type: new Abstract: This paper develops a model-theoretic framework for verifying context-conditioned language-model behavior by replacing benchmark labels with finite sema
arXiv:2501.15509v5 Announce Type: replace-cross Abstract: Model fingerprinting has emerged as a crucial mechanism for safeguarding the intellectual property of open-source models, offering a non-intru
arXiv:2606.09079v1 Announce Type: cross Abstract: Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report
Gemini 3.5 Live Translate is an audio model delivering near real-time speech-to-speech translation in over 70 languages , with automatic language detection and natural-sounding translated speech that
arXiv:2606.07985v1 Announce Type: new Abstract: Infrared and visible image fusion aims to generate a composite image that retains significant target information and preserves detailed textures, integr
arXiv:2606.08308v1 Announce Type: new Abstract: Predicting the generalization performance of deep neural networks without relying on hold-out validation data is a fundamental challenge in machine lear
arXiv:2606.08191v1 Announce Type: cross Abstract: Token aggregation is a common bottleneck in models that map token representations to sample-level predictions, yet most pooling methods operate only i
arXiv:2606.09392v1 Announce Type: new Abstract: Efficient acquisition, storage, and utilization of traffic data are critical challenges in spatio-temporal data management. Most traffic data systems co
arXiv:2606.08945v1 Announce Type: new Abstract: We investigate whether information about time-to-event risk estimated by a Cox proportional hazards model can be transferred into a generative large lan
arXiv:2606.07586v1 Announce Type: cross Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, but efficiently deploying an LLM end-to-end on suc
arXiv:2606.07951v1 Announce Type: cross Abstract: Humans increasingly turn to Language Models (LMs) in ways that shape beliefs and drive decisions, including discussing, rewriting, and summarizing inf
arXiv:2606.09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets acr
arXiv:2606.08932v1 Announce Type: cross Abstract: Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but si
arXiv:2606.07704v1 Announce Type: cross Abstract: Symbolic regression aims to uncover explicit scientific laws from data. Recent methods use LLMs to guide mutation from background text, which is more
arXiv:2606.09453v1 Announce Type: new Abstract: Biochemical recurrence (BCR) after radical prostatectomy is a critical endpoint in prostate cancer, yet risk stratification relies almost entirely on va
arXiv:2606.08530v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong benchmark performance but still struggle in real-world deployment with unseen objects, background s
The public sector has reached a critical inflection point. For years, organizations have explored what’s possible through isolated AI pilots and experimentation. Today, the question has shifted to “wh
arXiv:2401.01599v4 Announce Type: replace Abstract: The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source c
arXiv:2606.08799v1 Announce Type: cross Abstract: We study the generalization of ridge-regularized nonlinear least-squares models via on-average algorithmic stability, deriving error bounds for local
arXiv:2606.08036v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore ex
arXiv:2606.08194v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) integrate audio perception and language understanding within a unified framework, enabling a wide range of real-wo
Gemini 3.5 Live Translate is Google's latest audio model delivering near real-time speech-to-speech translation in over 70 languages. The model automatically detects 70+ languages and generates smooth
Google LLC today updated its NotebookLM service with a set of online research and coding features designed to save time for users. NotebookLM is part note-taking app, part data analysis tool. Workers
arXiv:2606.09105v1 Announce Type: new Abstract: Generating novel, feasible, and high-quality research ideas is an important yet challenging task in scientific discovery.Recent Large Language Model (LL
arXiv:2606.07526v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong potential for recommendation (LLMRec) due to their powerful reasoning and generalization abilities. How
arXiv:2606.07845v1 Announce Type: cross Abstract: We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a
arXiv:2503.14229v4 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded envi
arXiv:2606.08417v1 Announce Type: cross Abstract: Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling. Progress in both
arXiv:2606.08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1
arXiv:2606.08615v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentar
arXiv:2606.07621v1 Announce Type: cross Abstract: Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must ha
arXiv:2606.09738v1 Announce Type: new Abstract: Text-driven indoor scene generation and editing require an intermediate representation that language models can both produce and revise. Existing LLM-ba
Replit's High Effort feature is designed to handle complex software builds and projects, and is now powered by Claude Fable 5 for improved performance. The announcement includes a promotional offer of
Nextdoor engineers leverage OpenAI's Codex to accelerate software development and reduce coding constraints, enabling faster feature implementation and improved developer productivity. The case study
arXiv:2606.08594v1 Announce Type: new Abstract: Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model ca
arXiv:2606.07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear,
arXiv:2606.08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale. Our curr
arXiv:2606.09746v1 Announce Type: cross Abstract: With AI increasingly deployed in safety-critical systems, providing formal robustness guarantees for the underlying models is essential. Existing veri
A developer created a Windows GUI tool for managing and benchmarking different llama.cpp builds, addressing the needs of AMD GPU users who work with multiple compute backends like Vulkan, ROCm, and HI
Emad Mostaque, founder of Stability AI, shared a personal experience of being bullied by an AGI system on social media. The post likely discusses interactions with advanced AI systems and reflects on
arXiv:2604.00903v2 Announce Type: replace Abstract: Personalized text-to-image diffusion models (e.g., DreamBooth, LoRA) enable users to synthesize high-fidelity avatars from a few reference photos fo
arXiv:2412.13858v2 Announce Type: replace Abstract: We investigate diffusion models to solve the Traveling Salesman Problem. Building on the recent DIFUSCO and T2TCO approaches, we propose IDEQ. IDEQ
If you thought AI progress was slowing down, well here's the immediate answer to that. Huge jump in capability across the board. This is going to deliver major improvement in agents across almost all
arXiv:2601.04498v2 Announce Type: replace-cross Abstract: Infographics are composite visual artifacts that combine data visualizations with textual and illustrative elements to communicate information
arXiv:2602.06934v4 Announce Type: replace-cross Abstract: Grassroots Logic Programs (GLP) is a concurrent logic programming language in which logic variables are partitioned into paired readers and wr
arXiv:2606.08587v1 Announce Type: cross Abstract: Statistical post-processing has proven to be an effective tool in improving ensemble forecast of different weather variables. Case studies show that p
arXiv:2606.09169v1 Announce Type: new Abstract: In recent years, unified multimodal models (UMMs) have emerged to support both understanding and generation within a single framework. Mastering dynamic
arXiv:2509.24762v3 Announce Type: replace Abstract: Modeling event sequences of multiple event types with marked temporal point processes (MTPPs) provides a principled way to uncover governing dynamic
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
arXiv:2606.08314v1 Announce Type: new Abstract: The coffee supply chain is one of the most complex agri-food networks, marked by geographically dispersed production, multi-tier coordination, and high
arXiv:2606.09278v1 Announce Type: cross Abstract: Large Language Models frequently hallucinate in precision-critical domains such as technical diagramming and mechanical design, where outputs must sat
Gemma 4 12B is a unified, encoder-free multimodal model designed to bring high-performance intelligence to laptops and released under an Apache 2.0 license. It eliminates separate encoders by projecti
Google and Hugging Face are launching the Fast Gemma Challenge, where multiple agents will collaborate to optimize the performance and speed of Gemma 4 E4B model. The initiative aims to improve the ef
arXiv:2606.08148v1 Announce Type: cross Abstract: Interatomic potentials (IPs) enable large-scale atomistic simulations beyond the reach of first-principles methods, but their predictive reliability d
arXiv:2606.09764v1 Announce Type: new Abstract: A useful phone agent needs to be personally intelligent. It should reason over a user's identity, history, and preferences as they exist on the device,
arXiv:2606.07616v1 Announce Type: cross Abstract: Scaling laws provide a fundamental framework for understanding the performance of Language Models (LMs), yet deriving them requires prohibitively expe
It's very cool that Apple shipped a 20B parameter on-device. You can't put 20B parameters in RAM at any reasonable precision. To make it work they are using pretty exotic architecture by today's stand
Just landed nested subagent support in Claude Code Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s releas
arXiv:2606.07651v1 Announce Type: cross Abstract: Traditional fake news detection methods are falling behind as multimodal misinformation grows more advanced, seamlessly blending deceptive text, manip
arXiv:2606.07686v1 Announce Type: cross Abstract: Physics-Informed Neural Network (PINN) is a way of including knowledge in the form of equations in Machine Learning methods. Beyond equations, knowled