When Can Attention Heads Be Statically Defined?
arXiv:2609.34650v1 Announce Type: new Abstract: Some attention heads learn similar patterns across inputs. Reusing these patterns could reduce training cost by avoiding repeated query-key score comput
Knowledge catalogue
arXiv:2609.34650v1 Announce Type: new Abstract: Some attention heads learn similar patterns across inputs. Reusing these patterns could reduce training cost by avoiding repeated query-key score comput
arXiv:2606.16694v2 Announce Type: replace Abstract: Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a la
arXiv:2609.34939v1 Announce Type: new Abstract: Future exogenous variables provide valuable information for forecasting endogenous time series. Existing covariate-aware methods primarily learn the dir
arXiv:2609.30414v1 Announce Type: cross Abstract: Cognitive psychology has studied how people encode, use, and learn concepts that describe categories, and how they represent, recognize, and acquire c
arXiv:2609.31038v1 Announce Type: new Abstract: Time series foundation models (TSFMs) enable cross-domain forecasting, but their development as general-purpose forecasters remains constrained by under
Learn how to operationalize Amazon Textract Custom Queries adapters for production: infrastructure as code with AWS CloudFormation and Terraform, a cross-account adapter promotion process, a pre-class
arXiv:2609.30708v1 Announce Type: cross Abstract: A key challenge in medical image analysis is the scarcity of large annotated datasets for specific populations and diseases. As deep learning models r
arXiv:2312.16730v2 Announce Type: replace Abstract: Interactive decision making is the problem of learning to act well in an unknown environment, using the data that one's own actions generate to cont
arXiv:2609.30487v1 Announce Type: new Abstract: We here develop a functional neural network, termed MatFAE, for learning trajectories on the Riemannian manifold of symmetric positive definite (SPD) ma
arXiv:2609.31161v1 Announce Type: new Abstract: Recent empirical and theoretical advances suggest that joint-embedding predictive architectures (JEPAs) may learn meaningful representations for action-
arXiv:2609.31225v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to balance accurate motion tracking with compliant interaction, yet most visual-action policies leave complian
arXiv:2609.30433v1 Announce Type: new Abstract: Recent advancements in image-based profiling techniques have enabled the collection of high-volume cell morphology data, allowing new molecular embeddin
arXiv:2609.30758v1 Announce Type: new Abstract: Raindrops can cause occlusion and distortion in the background scenes due to their adherence to windows or camera lenses. Existing raindrop removal meth
OpenAI, loosely paraphrased: sure my poorly trained pit bull has been biting all the neighbor kids, and, yeah, i unleashed it before finishing the fence, and i actually don’t know how to train pit bul
arXiv:2609.30605v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) enables adaptive intrusion detection in dynamic network environments but also exposes intrusion detection systems (IDS
arXiv:2609.31518v1 Announce Type: cross Abstract: Sintering is widely used to manufacture ceramics, but coupled densification and grain growth, material-dependent kinetics, and sparse measurements com
arXiv:2609.30560v1 Announce Type: new Abstract: Beyond collision avoidance, socially competent robot navigation requires adherence to implicit social conventions that vary across contexts, cultures, a
arXiv:2511.09239v2 Announce Type: replace Abstract: Deep neural networks typically learn spatially entangled representations that conflate discriminative foreground features with spurious background c
arXiv:2609.30633v1 Announce Type: new Abstract: Successful training of deep neural networks is highly dependent on the distribution of the initial weights. If the weights are too large, network traini
arXiv:2609.30682v1 Announce Type: new Abstract: Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random
arXiv:2609.30276v1 Announce Type: new Abstract: We analyze the original same-step coordinate-wise AdaGrad under generalized smoothness and heavy-tailed noise with bounded variance. In this setting, lo
arXiv:2609.31162v1 Announce Type: new Abstract: Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, seque
Distributed Training and Inference both involves having a fundamental understanding of how distributed systems work in general Distributed Parallelism Tensor Parallelism Pipeline Parallelism Model Par
Open-source RL envs for the win. On Hugging Face of course! was looking for a quiet weekend but xiaomi dropped their rl envs repo last night to put in perspective, if you have to buy some tasks like t
Hi everyone, I built an educational tool that shows what happens inside a small MLP while it trains, and I'd like some feedback from people who teach ML. Everything is plain NumPy, no autograd: manual
Yann LeCun's lab borrowed a trick from the human brain and more than doubled how often an AI found its way to a goal. The paper is called Temporal Straightening for Latent Planning, from NYU with Brow
arXiv:2609.29334v1 Announce Type: new Abstract: Image denoising remains a fundamental problem in image restoration, with applications in photography, biomedical, and scientific imaging. Modern deep ne
Learn how to run SkyRL, an open-source reinforcement learning framework, on Amazon SageMaker HyperPod to post-train a Qwen3-VL-8B vision-language model with GRPO. This walkthrough covers building the
arXiv:2408.10349v2 Announce Type: replace-cross Abstract: Continual learning (CL) agents incrementally learn from sequentially arriving data and adapt to the dynamic, ever-changing nature of real-worl
arXiv:2404.06022v3 Announce Type: replace-cross Abstract: Face forgery detection faces critical challenges in generalizing to unseen manipulation techniques and remaining robust under image compressio
Can an LM, starting from random init (!!), learn to generate all of its pretraining data? Introducing Self-Play Pretraining with Zero Data. Two models start from random initialization: a generator pro
arXiv:2609.30080v1 Announce Type: new Abstract: Foundation segmenters such as SAM return several plausible masks for an unlabeled image, and a student trained on the wrong one inherits its errors. Cho
arXiv:2609.28558v1 Announce Type: new Abstract: CFD predictions of open tip clearance flow in compressor cascades are subject to discrepancies relative to experiments, while experimental observations
arXiv:2609.29680v1 Announce Type: new Abstract: Automatic Post-Editing (APE) for low-resource languages (LRLs) often fails to improve Machine Translation (MT), and the score alone cannot say why: whet
arXiv:2609.29807v1 Announce Type: new Abstract: A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compres
arXiv:2609.29466v1 Announce Type: cross Abstract: Approximate message passing on factor graphs underlies two dominant families of probabilistic inference algorithms: expectation propagation (EP) and v
arXiv:2609.29310v1 Announce Type: cross Abstract: Robot manipulation policies trained through imitation learning inherit not only the demonstrated behavior but also the conservative execution tempo of
arXiv:2609.29064v1 Announce Type: cross Abstract: The proliferation of photorealistic AI-generated images demands robust detection methods that generalize across diverse generative models. While exist
arXiv:2402.16763v3 Announce Type: replace-cross Abstract: Behavior can be described as a temporal sequence of actions driven by neural activity. To learn complex sequential patterns in neural networks
arXiv:2409.18486v5 Announce Type: replace Abstract: This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, sp
arXiv:2609.29159v1 Announce Type: cross Abstract: Dynamic mode decomposition (DMD) is a data-driven method that computes the best linear approximation of the underlying dynamical system and decomposes
arXiv:2609.29027v1 Announce Type: new Abstract: Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regula
arXiv:2609.29995v1 Announce Type: cross Abstract: AI teaching assistants (AI TAs) backed by large language models (LLMs) and pedagogical guardrails are increasingly being integrated into programming c
Learn how Datacor built a self-service rental analytics experience for gas and welding distributors by embedding Amazon Quick Sight dashboards and natural language querying into its TrackAbout platfor
arXiv:2609.29657v1 Announce Type: new Abstract: When users address large language models, they produce directive speech acts whose pragmatic features differ from those of both everyday conversation an
arXiv:2609.28877v1 Announce Type: cross Abstract: New words are invented every day. A human listener can learn a new word by hearing it clearly once and inferring its usage from sentence context. This
arXiv:2609.29988v1 Announce Type: new Abstract: Synthetic data can scale training supervision when real-world data are limited, but noise and distribution mismatch can reduce its value. Existing synth
arXiv:2609.29908v1 Announce Type: cross Abstract: Neural models can learn to generate various solutions to the inverse kinematics problem from data, but are usually limited to a single robot. We prese
arXiv:2609.29947v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolat
Nope. It's still true. Where is your domestic robot? Where is your Level-5 self-driving car? Where is your robot car that can learn to drive in a few hours of practice like any 17 year old? Where is y
arXiv:2609.28645v1 Announce Type: new Abstract: Recent advancements in 3D Gaussian Splatting (3DGS) have extended its capabilities to multi-scale segmentation. Existing methods reconstruct a scene wit
arXiv:2609.29037v1 Announce Type: cross Abstract: Federated learning (FL) lets EEG decoders learn from recordings of several subjects without pooling them. We consider two light EEG decoders, the Riem
arXiv:2609.29714v1 Announce Type: cross Abstract: The complexity of time-domain simulation of modern power systems has increased significantly because converter-based resources introduce control dynam
arXiv:2609.29181v1 Announce Type: new Abstract: There are many complex issues in the world of artificial intelligence. Some of these problems are solved using other artificial intelligence methods, wh
arXiv:2609.28625v1 Announce Type: new Abstract: Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new reasoning capabilities remains deb
Learn how to scale Mixture-of-Experts (MoE) reinforcement learning on Amazon EKS using Elastic Fabric Adapter (EFA) and DeepEP. This post presents an architecture that combines Amazon EKS, EFA, and Am
arXiv:2609.30063v1 Announce Type: new Abstract: Advances in language modeling have been driven by scaling pretraining on ever more data. Yet, the training data is still largely curated on the model's
arXiv:2609.29836v1 Announce Type: new Abstract: While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typi
arXiv:2609.28927v1 Announce Type: new Abstract: World action models (WAMs) that use future visual prediction at inference time incur substantial generation costs. Asynchronous execution reduces waitin
arXiv:2609.29792v1 Announce Type: cross Abstract: We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation