Knowledge catalogue
> Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. We do this for you in Deep Agents - see
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose
If you use LLM-as-judge, this one is worth reading. (bookmark it) It's actually one of the most effective ways to use LLM-as-a-Judge for evals. Holistic judge scores hide both their reasoning and thei
This is very interesting. Coinbase seems to have lowered their token spend ($$) to about half, by 1) routing to cheap inference like GLM 5.2 and Kimi 2.7 that are still pretty performant 2) Smart rout
This post by Filip Hric explains how to interpret AI code review benchmarks, specifically breaking down key evaluation metrics like precision and recall that are commonly used to assess code review to
arXiv:2606.13042v2 Announce Type: replace Abstract: In intelligent video surveillance, cameras record image sequences during day and night. Commonly, this demands different sensors. To achieve a bette
Autonomy isn't the ability to act without human supervision. It's the ability to *learn* without human bottlenecks in the process. A system that is fully dependent on human training data and RL enviro
Financial Times: Binance tells EU customers that it will stop providing services for them from July 1, after Greece rejected its application for a bloc-wide license last week — World's biggest crypto
arXiv:2508.02753v5 Announce Type: replace-cross Abstract: Time Series Forecasting (TSF) faces persistent challenges in modeling intricate temporal dependencies across different scales. Despite recent
arXiv:2606.16203v3 Announce Type: replace Abstract: Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI). Yet, early identification remains challenging due to the com
arXiv:2606.26273v1 Announce Type: new Abstract: Symmetries are important for many deep learning tasks, ranging from applications in the sciences to medical imaging. However, there is an ongoing debate
arXiv:2606.26481v1 Announce Type: new Abstract: Billions of scientific papers lead to the need to identify essential parts from the massive text. Scientific research is an activity from putting forwar
arXiv:2606.26515v1 Announce Type: new Abstract: Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating it
Forward Deployed Engineering is the most critical ingredient for Enterprise AI adoption. It’s why the most important companies on the planet are investing so heavily into it. That’s why we put togethe
from Write & Learn (thx @MilksandMatcha @philipkiely @swyx), my most important takeaway, 𝐛𝐮𝐢𝐥𝐝 𝐚 𝐝𝐞𝐧𝐬𝐞 𝐫𝐞𝐰𝐚𝐫𝐝 𝐟𝐨𝐫 𝐲𝐨𝐮𝐫 𝐰𝐫𝐢𝐭𝐢𝐧𝐠. fun fact. most people know @swyx as the famous podcaster, the AIE godfat
arXiv:2602.00813v5 Announce Type: replace Abstract: Composed Image Retrieval (CIR) is the task of retrieving a target image from a database using a multimodal query, which consists of a reference imag
arXiv:2606.27061v1 Announce Type: new Abstract: External indexes can be used for cluster evaluation when ground truth is available. We review the most common external validity indexes focusing on set-
arXiv:2606.26894v1 Announce Type: new Abstract: Brain MRI poses a fundamental challenge for machine learning: models must learn from high-dimensional 3D data spanning multiple co-registered modalities
arXiv:2606.26169v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has emerged as a pivotal technique in optimizing the design of Generative Adversarial Networks (GANs), automating the
arXiv:2606.26913v1 Announce Type: cross Abstract: Recent work on neural texture compression has demonstrated that it is possible to learn small, per-material texture representations (composed of laten
arXiv:2606.26410v1 Announce Type: new Abstract: We present a self-supervised framework for learning implicit 3D physical dynamics directly from video-derived supervisory signals. While current generat
Thomas Claburn / The Register: OpenAI says 97.9% of its employees are now using Codex, up from ~40% in August 2025; non-developer usage of Codex has risen 137x for individual users — Codex, it's not j
arXiv:2606.26128v1 Announce Type: new Abstract: The spatiotemporal evolution of many physical, chemical, and biological systems is described by nonlinear partial differential equations (PDEs). Recentl
arXiv:2606.26428v1 Announce Type: cross Abstract: Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. Th
arXiv:2603.26678v2 Announce Type: replace-cross Abstract: AI and renewable energy are increasingly framed as a 'power couple,' on the premise that surging AI demand will accelerate clean-energy invest
arXiv:2606.27223v1 Announce Type: new Abstract: Gaussian Splatting has been recently explored for satellite 3D reconstruction, demonstrating flexibility and efficiency in representing radiometrically
arXiv:2606.27375v1 Announce Type: new Abstract: We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation datas
Simple Blender animation → Seedance 2.0 → stylized AI video. This workflow uses basic 3D motion as a guide, then applies the look and detail from a reference image. To try this workflow, link below 👇
arXiv:2606.26749v1 Announce Type: cross Abstract: Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuratio
arXiv:1906.09235v3 Announce Type: replace Abstract: Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal
this is too late for AIE worlds fair but heres the how to book talks in the first place https://x.com/swyx/status/2069985832166154339?s=46 @ianand i think we have linked to this https://swyx.io/cfp-ad
Transformers are better at copying, while RNNs are better at modeling 'meaning-bearing words—the nouns, verbs, & adjectives that say what a sentence is about' Hybrid (transformer–RNN) models are fast
arXiv:2606.25068v1 Announce Type: new Abstract: Online time-series forecasters receive labels only after horizon-dependent delays, while every adaptation step spends limited compute. We study when an
arXiv:2606.25277v1 Announce Type: cross Abstract: To address data overload and inefficient shape-level annotation in robotic visual inspection, this paper proposes a hardware-software integrated optoe
arXiv:2604.00316v2 Announce Type: replace-cross Abstract: Grokking occurs when a model achieves high training accuracy but generalization to unseen test points happens long after that. This phenomenon
arXiv:2606.25357v1 Announce Type: new Abstract: State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavi
arXiv:2606.25255v1 Announce Type: new Abstract: High-resolution (HR) MRI acquisition is often hampered by scan time constraints, resulting in anisotropic or low-resolution scans (e.g., thick-slice FLA
arXiv:2511.12100v2 Announce Type: replace Abstract: In current visual model training, models often rely on only limited sufficient causes for their predictions, which makes them sensitive to distribut
arXiv:2606.25444v1 Announce Type: cross Abstract: Connecting a pre-trained speech encoder to a Large Language Model (LLM) is the standard architecture for building Speech LLMs. However, a structural m
arXiv:2606.25317v1 Announce Type: new Abstract: An efficient and accurate system for detecting errors in procedural tasks is crucial for supporting human needs in daily life, as it can provide instant
Meta is bringing back the Facebook Creator Studio page manager, now 'reimagined' as a standalone AI companion app. The new app aims to make it easier for creators to connect with their audiences and s
arXiv:2606.25578v1 Announce Type: new Abstract: Hairstyle transfer has practical applications such as virtual try-on, yet remains challenging when the source and reference exhibit large head-pose disc
arXiv:2606.24953v1 Announce Type: new Abstract: Machine learning (ML) algorithms are known to be opaque. We do not know the reasons for their predictions. The learning process leading to the predictio
I think part of what makes this account’s work so satisfying is they are doing a form of pattern recognition that is computerlike in many ways but actually requires a soul to pull off. Proof humans ar
In this post, we demonstrate how to implement video upscaling using SeedVR2 on SageMaker AI. We cover the solution architecture, walk through the deployment steps, and show performance comparisons tha
🚨 In a surprise to NOBODY, a study shows that generative AI use raises homework scores, but substantially reduces learning. My takeaways for AI ethicists and educators: The study analyzed data from 26
arXiv:2606.25434v1 Announce Type: new Abstract: Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are co
arXiv:2606.25927v1 Announce Type: cross Abstract: As machine learning models and datasets continue to grow, developing complex models has become increasingly computationally demanding. Knowledge disti
arXiv:2606.17967v2 Announce Type: replace Abstract: Speech foundation models, pre-trained on large corpora of unlabelled speech data, produce general-purpose representations which are useful across ta
arXiv:2606.25342v1 Announce Type: new Abstract: Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context
arXiv:2501.18916v2 Announce Type: replace Abstract: Recent work has demonstrated the potential of large language models (LLMs) for program optimization, a key challenge in programming languages. We pr
lots of folks prepping talks next week (congrats!). Some thoughts from RLing on thousands of hours of engineer- and researcher- focused talks: - AI generated svgs > AI generated imgs. MAXIMUM 4 ai slo
arXiv:2606.25225v1 Announce Type: new Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual strea
arXiv:2603.22050v2 Announce Type: replace-cross Abstract: Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning
Jeremy Howard discusses the existence of a black market for AI tokens, expressing surprise at learning about this market dynamic. The post likely covers unauthorized trading, resale, or acquisition of
Or people could learn their lesson? Naah 🙈 @GaryMarcus The reason he’s going down, is because the market can only handle one all encompassing scam at a time. So the AI scam will probably get a boost w
arXiv:2606.25269v1 Announce Type: cross Abstract: As black-box models become foundational to modern research, ensuring their stability is paramount for the realization of trustworthy artificial intell
arXiv:2606.25645v1 Announce Type: cross Abstract: In recent years, the posting of fake news including disinformation and misinformation on social networking services (SNS) has become a social problem.
We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a s
What happens when you shift more of the context layer into the model weights themselves? Engram is building a neolab focused on memory and continual learning. Let’s go @dan_biderman @realJessyLin! Fun