Knowledge catalogue
arXiv:2605.18035v1 Announce Type: new Abstract: Hard-thresholding is an important type of algorithm in machine learning that is used to solve ell_0 constrained optimization problems. However, the true
NEW paper worth reading: MetaCogAgent MetaCogAgent equips a multi-agent system with metacognition so each agent decides whether it should answer or delegate. In other words, it aims for self-aware tas
New upgrades to the @GeminiApp are you helping you get more done: ✨Gemini Spark is your 24/7 personal AI agent that can take action on your behalf, under your direction. It seamlessly integrates with
arXiv:2605.17128v1 Announce Type: cross Abstract: Jailbreak attacks on large models have drawn growing attention due to their close ties to societal safety. This work identifies a practical yet unexpl
arXiv:2605.17364v1 Announce Type: new Abstract: Media bias detection has predominantly been framed as a classification task: assign a political label to an article or outlet. We argue this framing is
arXiv:2605.18396v1 Announce Type: new Abstract: Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves on
arXiv:2605.16893v1 Announce Type: new Abstract: Recent studies introduce conditional memory modules that decouple knowledge storage from neural computation, enabling more direct knowledge access. Comp
arXiv:2605.16514v1 Announce Type: cross Abstract: Understanding why some sequential planning problems are harder than others requires models that go beyond average performance. They should capture the
arXiv:2605.17390v1 Announce Type: cross Abstract: Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly recommended for AI systems, but its progress is bot
arXiv:2605.16317v1 Announce Type: new Abstract: Accurate, unified models for event cameras (ECs) remain elusive, hampering calibration and algorithm design. We develop a foundational probabilistic mod
arXiv:2605.18238v1 Announce Type: new Abstract: Digital entities such as AI agents and humanoid robots increasingly operate alongside real humans, yet their identity infrastructure is based on credent
arXiv:2605.16423v1 Announce Type: new Abstract: Network quantization has emerged as one of the most practical model compression techniques, which significantly reduces a model's memory and compute con
arXiv:2605.16537v1 Announce Type: new Abstract: Open-source mobile manipulators have reached 660 (XLeRobot) but every sub-1,000 platform shares three limitations: a fixed-height workspace, reactive-on
arXiv:2605.16979v1 Announce Type: new Abstract: Mobile robots operating in human-centered environments must generate not only collision-free paths but also trajectories that follow local behavioral co
arXiv:2605.18593v1 Announce Type: cross Abstract: Open-vocabulary embodied AI agents increasingly rely on vision-language models such as CLIP for object perception and task grounding. However, the sha
This blog post from Anthropic's Claude discusses the practical effectiveness of using HTML within Claude's code interpreter, likely exploring how HTML can be leveraged for web development, data visual
The Nuxt MCP Toolkit has been updated to support MCP apps, expanding its capabilities for developers working with Nuxt and Model Context Protocol applications. This enhancement likely enables better i
At this year’s Google I/O conference, NVIDIA and Google Cloud are accelerating the work of more than 100,000 developers in the companies’ joint developer community, which provides curated learning pat
NVIDIA agent skills enable specialized agents to deliver targeted capabilities across enterprise workflows , with governance provided through verified, scanned, and signed skills. JFrog AI Catalog aut
Zack Whittaker / TechCrunch: NYC Health + Hospitals says hackers accessed its network from Nov. 2025 to Feb. 2026, exposing personal data, medical records, and fingerprints of 1.8M+ people — New York
arXiv:2605.16818v1 Announce Type: cross Abstract: Learning physical dynamics directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and oft
arXiv:2605.18481v1 Announce Type: new Abstract: Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We
arXiv:2605.18509v1 Announce Type: new Abstract: Automated decision-making algorithms drive applications such as recommendation systems and search engines. These algorithms often rely on off-policy con
arXiv:2603.03308v2 Announce Type: replace-cross Abstract: How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are affect
arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system
arXiv:2605.17340v1 Announce Type: new Abstract: Time series foundation models rely on large-scale pretraining over diverse datasets across domains, yet their heterogeneity in temporal patterns could h
OlmoEarth v1.1 represents an updated release of Allen AI's open-source language models designed with improved efficiency compared to the original version. The update likely focuses on reduced computat
arXiv:2605.17488v1 Announce Type: new Abstract: The landscape of joint audio and video generation has been fundamentally transformed by the advent of powerful foundation models. Despite these strides,
arXiv:2605.17360v1 Announce Type: new Abstract: Real-time duplex interaction is essential for multimodal AI systems operating in real-world scenarios, where models must continuously process streaming
arXiv:2602.02262v3 Announce Type: replace-cross Abstract: LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require
arXiv:2605.18577v1 Announce Type: new Abstract: Omni-proactive streaming video understanding, i.e., autonomously deciding when to speak and what to say from continuous audio-visual streams, is an emer
arXiv:2605.18041v1 Announce Type: new Abstract: Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long mul
arXiv:2605.16962v1 Announce Type: cross Abstract: Existing vision-language forgery detection and grounding methods operate under a closed-world paradigm, assuming verification can be completed by the
arXiv:2605.16998v1 Announce Type: cross Abstract: The Quantum Fourier Transform (QFT) is required by hidden subgroup problem (HSP) algorithms, including Shor's algorithm for factoring. The circuit dep
arXiv:2605.17483v1 Announce Type: new Abstract: Facial Expression Recognition faces two core challenges. The first is class imbalance in public datasets, which skews the learning process and weakens g
Kate Clark / Wall Street Journal: On-demand manufacturing startup SendCutSend raised 110M co-led by Sequoia, Paradigm, and Stripe co-founders Patrick and John Collison, valuing it at 1B — Custom sheet
arXiv:2605.16707v1 Announce Type: cross Abstract: The rapid evolution of digital health technologies is redefining healthcare services worldwide. The integration of wireless communication and Internet
arXiv:2605.17678v1 Announce Type: cross Abstract: In this paper, we derive rates of convergence in the high-dimensional central limit theorem for Polyak--Ruppert averaged iterates generated by entropy
arXiv:2605.18262v1 Announce Type: new Abstract: Accurate pedestrian trajectory prediction is crucial for autonomous systems operating in complex environments, such as modular buses and delivery robots
arXiv:2601.23154v2 Announce Type: replace-cross Abstract: Pain management in intensive care usually involves complex trade-offs, since both inadequate and excessive treatment can compromise patient sa
arXiv:2605.18370v1 Announce Type: cross Abstract: We study sample quantiles of distributions indexed by estimated parameters, with a on Value-at-Risk related to linear projections of financial returns
arXiv:2512.12572v2 Announce Type: replace Abstract: Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wid
arXiv:2601.21531v2 Announce Type: replace-cross Abstract: Visual token compression is widely used to accelerate large vision-language models (LVLMs) by pruning or merging visual tokens, yet its advers
arXiv:2602.16712v2 Announce Type: replace Abstract: Dexterous manipulation policies today largely assume fixed hand designs, severely restricting their generalization to new embodiments with varied ki
arXiv:2605.17907v1 Announce Type: cross Abstract: By sharing intermediate features, collaborative perception extends each agent's sensing beyond standalone limits, but real-world feature modality hete
arXiv:2605.17811v1 Announce Type: cross Abstract: Can a shared-weight recurrent Transformer develop distinct internal roles without being partitioned into separate modules? We study this in Asymmetric
One of the loudest applauses in the entire Google keynote: Nishtha put on the new Gentle Monster + Gemini glasses, tapped the side to summon Gemini, and ALL in one prompt said “take a photo and put a
'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding
One trend that I think you might start to see at big companies is insourcing via hiring: why pay so many outside vendors (legal, marketing, software vendors) when you can hire in-house and harness AI
arXiv:2602.20706v2 Announce Type: replace Abstract: This paper introduces online algorithms with unreliable guidance (OAG), a model for ML-augmented online decision-making that cleanly separates the p
arXiv:2605.17705v1 Announce Type: cross Abstract: Panel data, in which multiple units are repeatedly observed over time, arise throughout science and engineering. Quantifying predictive uncertainty in
arXiv:2603.03538v3 Announce Type: replace Abstract: Large Language Models (LLMs) with chain-of-thought generation have demonstrated great potential for solving complex reasoning and planning tasks. Ho
arXiv:2306.12282v2 Announce Type: replace-cross Abstract: Decision-makers often have access to machine-learned predictions about future demand that can help guide online resource allocation decisions.
arXiv:2512.04331v2 Announce Type: replace Abstract: The surge in face forgeries has increasingly undermined confidence in the authenticity of online content. As generation algorithms rapidly evolve, n
open sourcing Marlin-2B 🐟 a tiny VLM to extract structured information from videos Marlin is finetuned for two questions devs want to ask in their videos: what is happening, and when? Best open model
OpenAI: OpenAI introduces Guaranteed Capacity, a new offering that lets customers guarantee access to OpenAI's compute through one- to three-year commitments — Guarantee long-term access to OpenAI com
New York Times: OpenAI's win against Elon Musk leaves it free to continue its IPO plans, but it still faces many issues, like rising competition and dozens of other lawsuits — A jury's rejection of El
arXiv:2605.06088v2 Announce Type: replace Abstract: Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semanti
arXiv:2605.17172v1 Announce Type: cross Abstract: Personal AI stacks, like OpenClaw and Hermes Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local
arXiv:2508.16438v4 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG).