Knowledge catalogue
This Neo-Noir Cyberpunk world made with @ideogram_ai is quality! → 9.3B parameters → Native 2K resolution → Open weights - download, fine-tune, run local Flawless typography in complex scenes. Native
(To be clear, *I* don't think we should try to slow down recursive AI self improvement - I think we should open it up and democratize it as much as possible. My point is: if *you* claim we should slow
arXiv:2606.10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence ope
arXiv:2606.10431v1 Announce Type: cross Abstract: Multi-task vehicle routing problems play a critical role in enhancing efficiency across various industries and service sectors. These problems consist
1. Pausing until we had a much firmer idea of how to make AI safe—and well-aligned with human values—might well be a good idea. but 2. I trust neither of these companies, but fear that both will say “
Jeremy Howard argues that Anthropic's leadership should recognize that ensuring AI safety and positive outcomes requires collaborative effort across the industry rather than positioning any single org
arXiv:2606.07568v1 Announce Type: cross Abstract: Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the 'last mile' problem:
arXiv:2606.09327v1 Announce Type: cross Abstract: Football event data constitute a rich spatiotemporal source for quantitative analysis of player actions in team sports. These datasets contain heterog
arXiv:2606.09104v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) frameworks for portfolio optimization have shown promise for their ability to learn allocation rules dynamically fro
arXiv:2606.09536v1 Announce Type: new Abstract: Conventional one-hot encodings often yield poorly calibrated models, being overconfident under attack, and letting entropy-based detection algorithms fa
arXiv:2606.09777v1 Announce Type: new Abstract: Force and tactile sensing are indispensable in contact-rich manipulation. However, force-aware robot learning faces critical challenges due to the incom
arXiv:2601.03093v2 Announce Type: replace Abstract: Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (
arXiv:2606.08962v1 Announce Type: cross Abstract: World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-mo
Degrading performance on ML research *without telling the user* is shockingly hostile and a terrible look. That could silently damage all sorts of work, including some of my own. Also the type of thin
arXiv:2606.08694v1 Announce Type: cross Abstract: Generative models are increasingly used to capture correlations in many-body systems, but the representations they learn remain largely opaque to phys
arXiv:2606.07915v1 Announce Type: new Abstract: Neural symbolic regression models improve inference efficiency by shifting structural search to pretraining, but their one-pass autoregressive decoding
arXiv:2606.08107v1 Announce Type: cross Abstract: Robotics faces a fundamental challenge of data scarcity. Unlike language or vision research, there is no internet-scale dataset for robotic manipulati
arXiv:2606.09525v1 Announce Type: cross Abstract: During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While
arXiv:2606.08013v1 Announce Type: new Abstract: Catastrophic forgetting, the abrupt loss of previously acquired knowledge upon learning new information, remains the central challenge in Continual Lear
arXiv:2606.08167v1 Announce Type: cross Abstract: Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures. However, a theoretical understandin
At SXSW London last week I gave a talk called “Five things you need to know about AI,” in which I shared what I think are the biggest themes in AI right now. I pulled a few things from our first AI10
arXiv:2606.08956v1 Announce Type: new Abstract: Scientists have historically relied on mathematical models based on differential equations to relate system inputs -- forces, fluxes, or heat sources --
Custom agents let GitHub Copilot CLI understand your stack and team workflows, turning one-off terminal prompts into repeatable, reviewable processes. The post From one-off prompts to workflows: How t
arXiv:2606.07619v1 Announce Type: new Abstract: We present a Graph Neural Network (GNN) framework for the classification of finite groups according to their solvability. Using graph representations as
How do you prove the business value of generative AI to your teams? Technology and finance leaders need to show the clear business value of AI projects to secure ongoing funding. While measuring retur
Row-Bot is a local-first desktop AI assistant that can check emails and integrate multiple tools in a single conversation turn . The application includes integrated tools, a personal knowledge graph,
I don't really want to have to go to bat against Anthropic, but they've just been unnecessarily antagonistic to all of China, then not so subtly to open weight models, and now more broadly open AI res
This post critiques opaque AI moderation systems that penalize users without clear explanation, drawing parallels to how some companies might arbitrarily restrict customer access based on undisclosed
arXiv:2606.08438v1 Announce Type: cross Abstract: Bayesian optimization (BO) is a widely used approach for black-box optimization that uses a Gaussian process (GP) as a surrogate and guides sequential
It's confusing that Trump constantly warns about the security of our elections & foreign interference, yet his administration has taken several steps to dismantle or divert resources away from key saf
June 9th Researcher Reciprocity License 'if you train on it, you let us generate - reverse terms of use void' Status quo 1. We teach frontier devs with ICLR/NeurIPS papers, OSS Github contributions 2.
arXiv:2606.08993v1 Announce Type: new Abstract: We propose LEAF, a learning-enabled ADMM framework for accelerated convex optimization. The key idea is to approximate the Moreau envelope of the object
arXiv:2606.08641v1 Announce Type: new Abstract: The processing of gigapixel whole slide images within vision language models faces a major difficulty due to an excessive number of visual tokens. Exist
arXiv:2208.00859v2 Announce Type: replace Abstract: We propose a novel method enabling autocompletion of chemical flowsheets. This idea is inspired by the autocompletion of text. We represent flowshee
arXiv:2606.09446v1 Announce Type: new Abstract: Advances in handwritten text recognition have enabled large-scale transcription of historical documents, but still provide limited access to interpretab
LLMs are useful but we still have a long way to go. See my 2020 article The Next Decade in Arxiv, which remains a good guide to the future and offers a road map that the companies are increasingly fol
arXiv:2606.08460v1 Announce Type: cross Abstract: Data-adaptive two-sample testing assesses if two samples come from the same distribution, using a discrepancy learned from the data (e.g., via kernel-
arXiv:2510.06052v2 Announce Type: replace Abstract: Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of
arXiv:2601.21149v3 Announce Type: replace-cross Abstract: Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations
arXiv:2606.08204v1 Announce Type: cross Abstract: Neural fields parameterize data as functions from coordinates to values, providing a unified framework for representation learning across modalities.
arXiv:2606.09077v1 Announce Type: new Abstract: The Legendre-Fenchel (LF) transform is a fundamental tool in convex analysis and machine learning that maps lower semi-continuous functions to their con
arXiv:2606.08447v1 Announce Type: cross Abstract: One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to inte
arXiv:2506.04480v2 Announce Type: replace-cross Abstract: This paper focuses on Geodesic Principal Component Analysis (GPCA) on a collection of probability distributions using the Otto-Wasserstein geo
One of my personal favorite features announced at WWDC will I suspect be a sleeper hit: container machines, allowing your Mac to run a lightweight, persistent Linux environment with your home director
Open Source is the only way... First they came for the model builders... I feel we're getting a glimpse of a future where AI is only provided to a privileged few, and that's not a future I want to liv
arXiv:2606.09239v1 Announce Type: new Abstract: While visual programming of data analysis workflows has become an important vehicle for the democratization of data science, such systems remain largely
arXiv:2602.04402v3 Announce Type: replace-cross Abstract: Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only
arXiv:2606.07527v1 Announce Type: cross Abstract: The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL. In this position paper, we ar
arXiv:2606.09301v1 Announce Type: new Abstract: Multimodal federated graph learning (MM-FGL) aims to collaboratively learn from decentralized graphs with text and images. However, real-world clients m
arXiv:2606.08186v1 Announce Type: new Abstract: Monopedal hopping robots are conceptually simple but highly dynamic and inherently unstable. Achieving robust 3D hopping is still difficult because grou
arXiv:2606.08212v1 Announce Type: new Abstract: Solving machine learning problems is complex and typically reserved for experts. Over the past two decades, systems have emerged to support non-experts.
arXiv:2404.01948v3 Announce Type: replace Abstract: Dynamic visual sensors (DVS) are characterized by a large amount of background activity (BA) noise, which it is mixed with the original (cleaned) se
arXiv:2603.10823v2 Announce Type: replace-cross Abstract: Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced
arXiv:2606.08765v1 Announce Type: cross Abstract: Effective visuo-tactile integration is critical for robotic dexterous manipulation, especially when visual observations are unreliable or occluded. Ho
arXiv:2606.08649v1 Announce Type: cross Abstract: Forensic analysis of web server logs demands both accurate detection and human-readable explanations that can satisfy legal requirements. We present C
arXiv:2606.07596v1 Announce Type: new Abstract: Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigation
Small: 30 billion parameters, 3B active. Efficient: Benchmarks to 33.4 on the Artificial Analysis Coding Index, competitive among similar sized models. Open Source: Apache 2.0 license so developers ca
arXiv:2510.22450v3 Announce Type: replace-cross Abstract: The choice of activation function plays a critical role in neural networks, yet most architectures still rely on fixed, uniform activation fun
arXiv:2505.17868v2 Announce Type: replace Abstract: We present the first provable method for identifying symmetric linear dynamical systems (LDS) with accuracy guarantees that are independent of the s
arXiv:2606.07605v1 Announce Type: cross Abstract: Fine-grained time series data with high temporal resolution is critical for accurate analytics across a wide range of applications. However, the acqui