MEME: Multi-entity & Evolving Memory Evaluation
arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil
Knowledge catalogue
arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil
arXiv:2605.12368v1 Announce Type: new Abstract: Solving partial differential equations (PDEs) with machine learning typically requires training a new neural network for every new equation. This optimi
arXiv:2605.12128v1 Announce Type: new Abstract: Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Althou
Amber Tong / Bloomberg: Metis TechBio, a biotech company using AI to deliver and formulate drugs, surged as much as 185% in its Hong Kong market debut after raising ~$270M in its IPO — Shares of Metis
Maybe I'm just punch-drunk in my third week attending Musk v. Altman, but I have become very, very fond of Microsoft during the course of this trial. They don't want to be here any more than I do. The
Gyana Swain / CSO: Microsoft unveils MDASH, a security system that orchestrates 100+ AI agents to find vulnerabilities, and says it identified 16 previously unknown Windows flaws — The agentic tool, c
Emma Roth / The Verge: Microsoft updates Edge with new AI features, including letting Copilot gather information from open tabs and use browsing history for more relevant answers — The new features in
Microsoft Edge is adding a new feature that will allow its Copilot AI chatbot to gather information from all of your open tabs. When you start a conversation with Copilot, you can ask the chatbot ques
Microsoft Corp. today detailed a new artificial intelligence-powered vulnerability discovery system that uncovered 16 previously unknown flaws in Windows networking and authentication components, incl
arXiv:2602.09587v2 Announce Type: replace Abstract: The scarcity of high-quality data remains a primary bottleneck in adapting multimodal generative models for medical image editing. Existing medical
mimalloc is an open-source, modern, scalable memory allocator that is a drop-in replacement for malloc and free. It is relatively small (~12K lines), with clear internal data structures, and is easy t
arXiv:2605.12242v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) transcripts often contain disfluencies, such as fillers, repetitions, and false starts, which reduce readability and
arXiv:2605.11841v1 Announce Type: cross Abstract: Tree ensembles such as random forests (RFs) and gradient boosting machines (GBMs) are among the most widely used supervised learners, yet their theore
arXiv:2605.12070v1 Announce Type: new Abstract: Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization
arXiv:2605.12262v1 Announce Type: cross Abstract: We introduce missingness-MDPs (miss-MDPs), a novel subclass of partially observable Markov decision processes (POMDPs) that incorporates the theory of
arXiv:2605.11617v1 Announce Type: new Abstract: Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decis
arXiv:2605.11808v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinati
arXiv:2605.12185v1 Announce Type: new Abstract: Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect para
arXiv:2605.11333v1 Announce Type: cross Abstract: The fast pace of artificial intelligence~(AI) innovation demands an agile methodology for observation, reproduction and optimization of distributed ma
arXiv:2605.11900v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) can provide flexible traffic surveillance where fixed roadside cameras are unavailable, costly, or impractical. However,
arXiv:2605.05945v2 Announce Type: replace-cross Abstract: The recent advancement of Vision Language Action (VLA) models has driven a critical demand for large scale egocentric datasets. However, exist
arXiv:2605.12119v1 Announce Type: new Abstract: Generative novel view synthesis faces a fundamental dilemma: geometric priors provide spatial alignment but become sparse and inaccurate under view chan
arXiv:2412.13050v2 Announce Type: replace-cross Abstract: In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language M
arXiv:2605.12410v1 Announce Type: cross Abstract: We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history
arXiv:2503.09051v2 Announce Type: replace Abstract: We propose a novel model-level GNN explanation framework that shifts the explanation target from class-wise rule extraction to rule-based logit reco
arXiv:2502.12276v2 Announce Type: replace Abstract: Computational methods for analyzing prose and poetry utilize word embeddings and other abstract representations that sometimes obscure context-rich
arXiv:2602.15451v3 Announce Type: replace-cross Abstract: Deep generative modeling to stochastically design small molecules is an emerging technology for accelerating drug discovery and development. H
arXiv:2411.19093v4 Announce Type: replace Abstract: Access to drinking water and sanitation services is essential for health and well-being, yet large global disparities persist. Sustainable Developme
More accurate statement IMHO would be: there won’t immediately be an AI jobpocalyspe. Saying there never will be one hardly seems plausible. Even less plausible is the claim that there will be an AI j
more demos on Interaction Models collaboratively doing system design, reading papers, fact-checking with live generative UI 1. (System design) - The Interaction Models see your screen and collaborates
arXiv:2605.11836v1 Announce Type: cross Abstract: Lifelong Model Editing aims to continuously update evolving facts in Large Language Models while preserving unrelated knowledge and general capabiliti
arXiv:2605.11402v1 Announce Type: new Abstract: Deep learning-based website fingerprinting has emerged as an effective technique for inferring the websites users visit. Although existing methods achie
arXiv:2605.12228v1 Announce Type: new Abstract: Mobile manipulation requires coordinated control of high-dimensional, bimanual robots. Imitation learning methods have been broadly used to solve these
Mother's Day may have passed, but we're not done showcasing mothers who build on Replit. When Noni started a family, she put her dream of building apps on hold. A busy home, a busy classroom, and no t
arXiv:2501.02955v2 Announce Type: replace Abstract: In recent years, vision language models (VLMs) have made significant advancements in video understanding. However, a crucial capability - fine-grain
arXiv:2605.05680v2 Announce Type: replace Abstract: This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distri
arXiv:2605.11336v1 Announce Type: cross Abstract: Web search queries concern place far more often than existing labelling schemes suggest, yet the landscape of geospatial web search queries - what peo
arXiv:2605.11204v1 Announce Type: cross Abstract: Local interaction laws governing multi-agent systems can be difficult to recover from trajectory data, even when the dynamics are observed faithfully.
arXiv:2605.12134v1 Announce Type: new Abstract: Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There
arXiv:2509.21711v2 Announce Type: replace-cross Abstract: As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of dat
arXiv:2605.11530v1 Announce Type: new Abstract: Single-model ensembles (SMEs) have attracted attention as a way to approximate some of the benefits of deep ensembles within a single network. However,
arXiv:2605.12460v1 Announce Type: cross Abstract: The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or c
arXiv:2605.12176v1 Announce Type: new Abstract: This paper presents the Constrained Multi-Task Representation Learning (CMTRL) framework for linear bandits. We consider T linear bandit tasks in a d di
arXiv:2605.11835v1 Announce Type: cross Abstract: Spiking neural networks (SNNs) promise low-power event-driven computation for temporally rich tasks, but commonly used neuron models often trade off g
arXiv:2605.12341v1 Announce Type: cross Abstract: Conformal prediction constructs prediction sets with finite-sample coverage guarantees, but its calibration stage is structurally constrained to a sca
arXiv:2605.11959v1 Announce Type: cross Abstract: Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features
arXiv:2605.11181v1 Announce Type: new Abstract: The recent empirical success of the Muon optimizer has renewed interest in non-Euclidean optimization, typically justified by similarities with second-o
arXiv:2605.11396v1 Announce Type: new Abstract: The Muon optimizer has emerged as a compelling alternative to Adam for training large language models, achieving remarkable computational savings throug
Bloomberg: Musk v. Altman: Microsoft executive Michael Wetter testifies that Microsoft has spent 100B+ on OpenAI, including its investments and to build infrastructure — Microsoft Corp. has spent more
AI Security Institute: Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them — In February 2026,
NASA is moving quickly to define next year's Artemis III mission in Earth orbit, a crewed flight that will test rendezvous and docking capabilities between the agency's Orion spacecraft and commercial
arXiv:2302.12039v2 Announce Type: replace Abstract: We summarize the current state of the field of NLP & Law with a specific focus on recent technical and substantive developments. To support our anal
arXiv:2605.11665v1 Announce Type: new Abstract: Robot learning research is fragmented across policy families, benchmark suites, and real robots; each implementation is entangled with the others in a c
arXiv:2605.11762v1 Announce Type: new Abstract: Learning robust navigation policies remains a core challenge in robotics. Offline imitation learning suffers from distribution shift and compounding err
Dutch artificial intelligence infrastructure giant Nebius Group N.V. said today it’s recruiting the core engineering team from AI orchestration software firm Clarifai Inc. in an effort to boost its ma
Emma Roth / The Verge: Netflix says its ad tier now has 250M monthly active viewers, up from 94M in 2025, and is expanding to 15 new countries, as it tests an ad personalization tool — The streaming s
arXiv:2509.06697v2 Announce Type: replace-cross Abstract: Accurate forecasting of exchange rates remains a persistent challenge, particularly for emerging economies such as Brazil, Russia, India, and
arXiv:2605.12343v1 Announce Type: new Abstract: Most learned PDE solvers follow a global-surrogate paradigm: a neural operator is trained to map full problem descriptions to full solution fields for a
arXiv:2605.11327v1 Announce Type: new Abstract: Classical deep learning typically operates on individual cases. Despite its success, real-world usage often requires repeated inference to estimate stat
New paper in Nature. The more a government controls its domestic media, the more it dominates AI training data, the more pro-regime outputs we get from AI. By scraping the open web, LLMs are unwitting