Knowledge catalogue
arXiv:2503.10954v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents can solve *any* computational problem *without* an algorithm in a runtime *independent* of the computational
arXiv:2607.04276v1 Announce Type: new Abstract: Diffusion models achieve impressive image-generation quality but remain expensive at inference time. Diffusion distillation reduces sampling steps, yet
In this post, we walk through what Dataset Enrichment is, how it differs from legacy Topics, and provide three migration scenarios with step-by-step guidance so you can move your business context into
If you're struggling to get started with evals, you're not alone. This post explains how to write LLM evals as ordinary tests in CI with Phoenix, pytest, and Vitest/Jest. The post Evals in CI: How to
arXiv:2607.02854v1 Announce Type: cross Abstract: Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT). However, generating a BRT is itself a challeng
arXiv:2503.10496v2 Announce Type: replace-cross Abstract: Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from
arXiv:2508.16771v3 Announce Type: replace-cross Abstract: Code Language Models (CodeLLMs) learn token importance from data correlations, whereas human developers attend selectively to semantically sal
arXiv:2512.16357v3 Announce Type: replace Abstract: Pre-trained Latent Diffusion Models (LDMs) have recently shown strong perceptual priors for low-level vision tasks, making them a promising directio
arXiv:2607.03330v1 Announce Type: new Abstract: Quantifying plant growth dynamics from sparse longitudinal 3D observations is fundamental for agriculture and plant sciences. Yet, plants pose unique ch
Hello, my dear friends, we have some breaking news today! Our rentosertib (novel target that has never been in clinical trials before we picked it using AI, novel molecule designed using true generati
ComfyUI shared a blog post link via their @hellorob account offering additional learning resources about their platform or features. The tweet directs users to their blog through a shortened URL for m
arXiv:2607.02038v2 Announce Type: replace Abstract: The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious
arXiv:2607.04709v1 Announce Type: cross Abstract: Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data li
arXiv:2607.05329v1 Announce Type: new Abstract: Siamese verification networks are widely used to compare items such as faces, cars, or signatures. In these scenarios, the network is trained to learn a
arXiv:2607.05316v1 Announce Type: new Abstract: Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in
arXiv:2607.04341v1 Announce Type: cross Abstract: This state-of-the-art report provides an overview of controllable 3D human avatar creation. We describe current 3D avatar systems, which typically con
arXiv:2603.24025v2 Announce Type: replace Abstract: Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It's common that
arXiv:2602.19143v2 Announce Type: replace Abstract: This paper studies simple transformers trained on a high-order Markov chain, where the model must incorporate information from multiple past positio
arXiv:2607.02800v1 Announce Type: new Abstract: Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they i
arXiv:2506.21887v2 Announce Type: replace Abstract: High-stakes decision-making involves navigating multiple competing objectives with expensive evaluations. For instance, in brachytherapy, clinicians
arXiv:2607.04156v1 Announce Type: new Abstract: Scientific equation discovery must combine broad domain priors with strict numerical testing. Symbolic regression supplies numerical grounding but faces
arXiv:2607.05263v1 Announce Type: new Abstract: This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint rep
arXiv:2607.04711v1 Announce Type: new Abstract: Continual learning aims to progressively learn from a sequence of tasks, each containing a disjoint subset of classes, while preserving previously learn
arXiv:2401.10805v4 Announce Type: replace-cross Abstract: We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in a
arXiv:2503.18509v2 Announce Type: replace Abstract: Weak supervision enables machine learning models to learn from limited or noisy labels, but it introduces challenges in reliability and semantic cla
🎓 New course launch from LangChain Academy: Introduction to Deep Agents ✅ Learn what a harness is, and why agents need one ✅ Understand the 4 core capabilities of a harness ✅ Start building with Deep
Now I'm regretting having carefully blasted through 100% of my Fable allotment in time for being cut off at the end of today! (Presumably 'Wed 12:00 PM' means I get it back at noon on Wednesday, not a
arXiv:2603.19954v2 Announce Type: replace Abstract: Transformers have shown inconsistent success in AI planning tasks, and theoretical understanding of when generalization should be expected has been
arXiv:2607.04118v1 Announce Type: cross Abstract: With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often
arXiv:2607.05127v1 Announce Type: cross Abstract: Understanding the physics of many-body complex dynamical systems is typically non-trivial. High-dimensional analysis approaches are often deemed neces
arXiv:2607.04587v1 Announce Type: new Abstract: Robust 3D object detection in adverse weather conditions is challenging due to sensor limitations. Although combining complementary modalities such as L
arXiv:2607.03303v1 Announce Type: new Abstract: While Large Language Models (LLMs) can provide personalized support in learning, several studies have raised concerns regarding their use in education.
arXiv:2607.03640v1 Announce Type: cross Abstract: Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt
arXiv:2510.19698v3 Announce Type: replace Abstract: Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learn
arXiv:2607.03196v1 Announce Type: new Abstract: WiFi-based human pose estimation (HPE) enables the detection and interpretation of human body positions and movements without the need for wearable devi
arXiv:2607.02402v2 Announce Type: replace Abstract: Vision-language models (VLMs) can follow complex textual instructions, yet they struggle to reason from purely visual context. In particular, curren
arXiv:2607.04064v1 Announce Type: cross Abstract: Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Re
tldr of thariq's AIEWF keynote https://latent.space/p/ainews-the-field-guide-to-fable (more in today's ainews issue) my keynote at AI Engineer World Fair: “A Field Guide to Fable” is live on YouTube!
arXiv:2502.12096v5 Announce Type: replace-cross Abstract: In this paper, we introduce token communications (TokCom), a large model-driven framework to leverage cross-modal context information in gener
arXiv:2607.02864v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful approach in financial trading, enabling agents to learn optimal strategies through direct market i
arXiv:2607.04969v1 Announce Type: cross Abstract: The training paradigm of large language models has shifted from traditional one-pass training to multi-epoch training, as reasonable reuse of limited
arXiv:2603.07606v2 Announce Type: replace Abstract: Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rul
arXiv:2510.05681v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in
arXiv:2603.18797v2 Announce Type: replace Abstract: Spatial graphs provide a lightweight and elegant representation of curvilinear anatomical structures such as blood vessels, lung airways, and neuron
arXiv:2607.03551v1 Announce Type: new Abstract: Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promis
What actually makes an AI application good or not? Thanks to @StackOverflow for hosting @the_bunny_chen on the Stack Overflow Podcast (even though he is giving away all of our secrets!) Listen here: h
arXiv:2607.05381v1 Announce Type: cross Abstract: What does a discrete diffusion model learn: a denoiser, a score ratio, or a bridge plug-in predictor? At the level of jump rates, these are one object
Absolutely. And protect your expertise as much as you can in this new era of AI. Learn to package it as a product or experience using AI. I find that content creation is one of the highest ROI activit
Today, we’re excited to announce a deep-link integration between Hugging Face and Amazon SageMaker AI. Developers can now go from model discovery to hands-on experimentation in SageMaker Studio with a
This article from Modal explains the pricing models and cost considerations for serverless GPU services, likely covering how providers like Modal calculate charges based on GPU usage, execution time,
If you want to start a startup, don't learn 'entrepreneurship.' Learn how to build things. The hard part of startups is not 'entrepreneurship' but product: to know what to build, and to be able to bui
// In-context Retrieval at Million-token Scale // Great study providing better understanding of retrieval at million-token scale. They run the first systematic study of in-context retrieval at the sca
Making sure Cybercab meets the needs of the blind Cybercab at the National Federation of the Blind's Annual Convention in Austin for a hands-on experience of its accessibility features for blind or vi
A keynote presentation titled 'A Field Guide to Fable' was delivered at AI Engineer World Fair and is available on YouTube. The talk, given by Thariq, likely covers practical guidance or best practice
// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harnes
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form acoustic encodings. AED models trained on segmented utterances learn to encode absolute frame
The glorification of insider trading is a disturbing new trend that I’ll never understand Be leopold > wife is chief of staff at Anthropic > get insider info at the dinner table > learn that Anthropic
Was this deadpan? As if we hadn’t experienced the internet era. Let me re-up: plausible that LLMs will slow down science *today* while *also* destroying the very processes that would eventually lead t
Check out all the amazing work from our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation (https://www.physicsoflearning.org/) presented at the main meeting of @ICMLconf #ICML
Great overview of always-on agents. (bookmark it) It's a new 130+ pages survey on always-on agents. Simply put it, always-on agents are systems whose future behavior depends on durable state built up