One town’s scheme to get rid of its geese
“Pull over!” I order my brother one sunny February afternoon. Our target is in sight: a gaggle of Canada geese, pecking at grass near the dog park. As I approach, tiptoeing over their grayish-white po
Knowledge catalogue
“Pull over!” I order my brother one sunny February afternoon. Our target is in sight: a gaggle of Canada geese, pecking at grass near the dog park. As I approach, tiptoeing over their grayish-white po
arXiv:2506.18186v3 Announce Type: replace Abstract: The restless multi-armed bandit (RMAB) framework is a popular approach to solving resource allocation problems in networked systems. In this paper,
arXiv:2604.00555v2 Announce Type: replace Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory complianc
OpenAI: OpenAI announces workspace agents in ChatGPT, letting teams create Codex-powered shared agents for complex tasks, and says they are “an evolution of GPTs” — Codex-powered agents for teams. — C
OpenAI released a new model that was made available on Hugging Face, as announced by Hugging Face CEO Clem Delangue on X (formerly Twitter). The specific details about which model was released are not
OpenAI is shutting down text-embedding-3-small?!? I strongly believe that if you shut down a closed-source embedding model that you should open-source. Imaging the trillions of tokens that will no lon
OpenAI just open sourced a new 1.5B (50m active) model on HuggingFace with Apache 2.0 license! It's not a new LLM, this one is called Privacy Filter, and it's a PII detection model (checking if text h
OpenAI just released a new open-source model it's 'a bidirectional token-classification model for personally identifiable information (PII) detection and masking in text' https://github.com/openai/pri
OpenAI is giving users of its Business, Enterprise, Edu, and Teachers plans access to cloud-based 'workspace' agents available in ChatGPT that can perform business tasks. In its blog post, OpenAI give
OpenAI: OpenAI releases ChatGPT for Clinicians, a tool for medical tasks like documentation and research, free for verified physicians, pharmacists, and more in the US — Built for clinical work, ChatG
OpenAI: OpenAI releases Privacy Filter, an open-weight model for masking personally identifiable information in text, with 1.5B total and 50M active parameters — Our state of the art model for masking
arXiv:2412.09404v3 Announce Type: replace-cross Abstract: Nowadays, social media is the ground for political debate and exchange of opinions. There is a significant amount of research that suggests th
arXiv:2604.18800v1 Announce Type: cross Abstract: We study online learning for new products on a platform that makes capacity-constrained assortment decisions on which products to offer. For a newly l
arXiv:2604.19399v1 Announce Type: new Abstract: Federated learning (FL) is a key paradigm for distributed model learning across decentralized data sources. Communication in each FL round typically con
arXiv:2512.12448v2 Announce Type: replace Abstract: Efforts to improve Kolmogorov--Arnold networks (KANs) with architectural enhancements have been stymied by the complexity those enhancements bring,
Oracle Corp. is extending its partnership with Google LLC’s Cloud to simplify how enterprise users interact with data, introducing a new natural-language interface for queries directly against Oracle
arXiv:2509.15435v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) exhibit strong multimodal capabilities but remain vulnerable to hallucinations from intrinsic errors and
Ars Technica's newsroom AI policy forbids unlabeled AI material in reported stories and requires human confirmation of every quotation's accuracy. The publication does not permit the publication of AI
Perplexity's reward design system prioritizes correctness as a foundational requirement, then evaluates user preference and efficiency only when answers meet correctness standards. This hierarchical a
Outrageous! SPLC executives who did this need to go to prison for a long time. This evening: @DAGToddBlanche and I are announcing an 11 count indictment against the Southen Poverty Law Center. Charges
arXiv:2604.18658v1 Announce Type: cross Abstract: Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a d
arXiv:2604.19379v1 Announce Type: new Abstract: This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve general
arXiv:2604.19556v1 Announce Type: new Abstract: Current 3D mapping pipelines generally assume static environments, which limits their ability to accurately capture and reconstruct moving objects. To a
arXiv:2604.18864v1 Announce Type: new Abstract: Generalized Additive Models (GAMs) can be used to create non-linear glass-box (i.e. explicitly interpretable) models, where the predictive function is f
arXiv:2604.19656v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are
Pay attention to this one, AI devs. This is particularly interesting if you work with long-horizon terminal agents that often drown in their own observations. TACO is a self-evolving framework that au
arXiv:2604.19596v1 Announce Type: new Abstract: Point cloud registration involves aligning one point cloud with another or with a three-dimensional (3D) model, enabling the integration of multimodal d
This post from Hugging Face CEO Clem Delangue discusses the value of persistence in machine learning work, using an anecdote about observing an intern working through problems. The tweet emphasizes th
arXiv:2604.18943v1 Announce Type: new Abstract: With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences
arXiv:2403.09905v5 Announce Type: replace-cross Abstract: Embodied navigation methods commonly operate in static environments with stationary objects. In this work, we present approaches for tackling
arXiv:2411.06837v2 Announce Type: replace Abstract: The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, enabling fully-automated, pers
arXiv:2602.09370v2 Announce Type: replace Abstract: Skateboards offer a compact and efficient means of transportation as a type of personal mobility device. However, controlling them with legged robot
arXiv:2604.19738v1 Announce Type: cross Abstract: We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on
arXiv:2512.00993v2 Announce Type: replace Abstract: Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance,
The 2026 Breakthrough Prize in Fundamental Physics was awarded to researchers who measured the magnetic 'wobble' of the muon subatomic particle with exceptional precision over more than 60 years of ex
arXiv:2511.08418v2 Announce Type: replace Abstract: Accurately simulating systems governed by PDEs, such as voltage fields in cardiac electrophysiology (EP) modelling, remains a significant modelling
arXiv:2602.20323v5 Announce Type: replace-cross Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM)
arXiv:2511.12606v3 Announce Type: replace Abstract: Group Activity Recognition (GAR) is well studied on the video modality for surveillance and indoor team sports (e.g., volleyball, basketball). Yet,
arXiv:2604.19324v1 Announce Type: cross Abstract: We introduce PLaMo 2.1-VL, a lightweight Vision Language Model (VLM) for autonomous devices, available in 8B and 2B variants and designed for local an
arXiv:2604.19695v1 Announce Type: new Abstract: We propose SmoothCruiser, a new planning algorithm for estimating the value function in entropy-regularized Markov decision processes and two-player gam
arXiv:2604.19036v1 Announce Type: new Abstract: Defeasible statements are statements that are likely, or probable, or usually true, but may occasionally be false. Plausible reasoning makes conclusions
arXiv:2603.29078v2 Announce Type: replace Abstract: We present PolarQuant, a post-training weight quantization method for large language models (LLMs) that exploits the distributional structure of neu
arXiv:2604.19024v1 Announce Type: new Abstract: Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language mo
Tanaya Macheel / CNBC: Polymarket says perpetuals are coming to the platform and lets users sign up for early access; it hasn't specified whether crypto perpetual futures are included — Prediction mar
arXiv:2604.19129v1 Announce Type: new Abstract: Existing facial reenactment methods struggle with a trade-off between expressiveness and fine-grained controllability. Holistic facial reenactment model
arXiv:2510.18333v2 Announce Type: replace-cross Abstract: Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap st
arXiv:2604.18649v1 Announce Type: cross Abstract: As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on post-hoc mitigation -- especially mach
arXiv:2604.19684v1 Announce Type: new Abstract: Explainable artificial intelligence (XAI) has predominantly focused on generating model-centric explanations that approximate the behavior of black-box
arXiv:2601.15349v2 Announce Type: replace Abstract: In narrow, unstructured underwater environments such as environmental monitoring and minimally invasive medical procedures, micro soft robots exhibi
arXiv:2604.18801v1 Announce Type: new Abstract: Lossy compression is widely used to reduce storage and I/O costs for large-scale particle datasets in scientific applications such as cosmology, molecul
Presumably GPT-imagegen-2 (aka ChatGPT Images 2.0 aka gpt-image-2) works as a tool which the models generate prompts for? I wish we could see those prompts, like back in the DALL-E 3 days https://simo
Principal Platform Engineer at Sakana AI https://sakana.ai/careers/#principal-platform-engineer At Sakana AI, we are building a sovereign, unified data platform for Japan's defense sector and largest
arXiv:2510.13763v2 Announce Type: replace-cross Abstract: Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or
arXiv:2604.18892v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectori
arXiv:2604.18712v1 Announce Type: new Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive sig
arXiv:2604.19069v1 Announce Type: cross Abstract: Neural NLI models overfit dataset artifacts instead of truly reasoning. A hypothesis-only model gets 57.7% in SNLI, showing strong spurious correlatio
arXiv:2604.19083v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threate
arXiv:2508.01371v3 Announce Type: replace-cross Abstract: Smart contracts are important for digital finance, yet they are hard to patch once deployed. Prior work has mainly explored LLMs for smart con
arXiv:2604.18919v1 Announce Type: new Abstract: Analyzing topics extracted from text data in relation to external outcomes is important across fields such as computational social science and organizat
Props to @augmentcode for being one of the first to ship Kimi K2.6 to their users. Open models are now the frontier. Support for Kimi K2.6 is now here in Augment Code! We teamed up with @Kimi_Moonshot