Knowledge catalogue
arXiv:2606.23153v1 Announce Type: new Abstract: Animal collectives navigate cluttered environments through local coordination, yet robot swarms still struggle to reproduce this capability in the physi
arXiv:2606.21092v1 Announce Type: new Abstract: We introduce BASIL, a user-friendly desktop application for process optimization. BASIL employs a Bayesian approach, incorporating special acquisition f
arXiv:2606.21080v1 Announce Type: cross Abstract: Bayesian model averaging in support-indexed regression induces a posterior distribution over active predictor supports. Under predictor redundancy, po
arXiv:2606.20702v1 Announce Type: new Abstract: Vision-language models (VLMs) have sparked growing interest in zero-shot Earth Observation (EO) downstream tasks, with further gains enabled by remote-s
arXiv:2606.23270v1 Announce Type: new Abstract: As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving p
arXiv:2505.11129v2 Announce Type: replace Abstract: Representation learning is one of the key research topics in machine learning, and the framework of self-supervised learning (SSL) has revolutionize
This post shows you how to build a conversational protein research assistant that combines three capabilities: Natural language query parsing to extract structured search parameters, vector similarity
arXiv:2603.20520v2 Announce Type: replace-cross Abstract: Simulation-based inference (SBI) with neural networks has accelerated and transformed cognitive modeling workflows. SBI enables modelers to fi
arXiv:2606.21156v1 Announce Type: new Abstract: The high cost of spatial transcriptomics (ST) has driven extensive studies into predicting gene expression directly from H&E histology images. However,
arXiv:2606.21608v1 Announce Type: new Abstract: Accurate segmentation of curvilinear structures remains challenging in biomedical imaging due to their thin geometry, complex topology, and sensitivity
arXiv:2603.11909v2 Announce Type: replace Abstract: Reliable uncertainty quantification is paramount for forecasting multivariate time series and spatiotemporal data. While Transformer architectures e
arXiv:2606.21602v1 Announce Type: cross Abstract: Deep unrolled networks (DUNs) integrate physical forward models with learned regularization in cascaded network architectures, achieving exceptional p
arXiv:2606.21036v1 Announce Type: cross Abstract: In many domains, practitioners seek models that produce accurate forecasts while faithfully capturing latent system dynamics. Existing approaches typi
arXiv:2606.22314v1 Announce Type: cross Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attribu
arXiv:2606.22994v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have become an important tool for unsupervised concept discovery in large models. To make the resulting feature spaces more i
arXiv:2606.20858v1 Announce Type: new Abstract: The temporal structure of reward composition in reinforcement learning (RL) is typically hand-designed and held fixed throughout training, leaving the p
arXiv:2606.22838v1 Announce Type: new Abstract: In this work, we propose Frontier-based Path Planning with Adaptive Sampling (FPAS), a novel framework designed for efficient goal-reaching in large-sca
arXiv:2606.20842v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising technique for novel view synthesis. However, 3DGS requires dense input views to achieve high-qua
arXiv:2606.22876v1 Announce Type: new Abstract: Quantitative measurement of the golf swing is critical for evaluating technique and enabling individualized feedback. However, existing methods are impr
arXiv:2510.10759v2 Announce Type: replace Abstract: Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint
arXiv:2606.22416v1 Announce Type: new Abstract: We address the problem of training on long-tailed data for video action recognition. We propose to augment the training set using a text-to-video genera
Companies are asking how to build specialized AI that fits with the way their workflows actually run. The first wave of enterprise AI was about access. Companies experimented with new frontier and ope
Explore how my day as a senior leader looks now that I use 40 automations to help, and learn more about some of my favorites. The post I automated my job (and it made me a better leader) appeared firs
arXiv:2606.23682v1 Announce Type: new Abstract: Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis.
arXiv:2606.20937v1 Announce Type: new Abstract: We study internalization processes, by which neural-network-based systems absorb an explicit computational procedure into their own weights, and how the
arXiv:2606.23208v1 Announce Type: new Abstract: Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose
arXiv:2606.21358v1 Announce Type: new Abstract: Supervised video pretraining is a common transfer learning practice for improving downstream action recognition performance. However, it requires large-
arXiv:2606.23688v1 Announce Type: new Abstract: Reconstructing dynamic non-rigid objects from monocular video requires integrating visual cues from direct observations with data-driven priors over geo
arXiv:2412.05976v2 Announce Type: replace Abstract: Occupancy prediction has garnered increasing attention in recent years for its comprehensive fine-grained environmental representation and strong ge
arXiv:2606.23136v1 Announce Type: cross Abstract: Finding the shortest path in non-geometric network graphs, where edge weights encode arbitrary metrics such as latency or monetary cost rather than sp
arXiv:2606.22565v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thi
arXiv:2602.15206v2 Announce Type: replace Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it rem
arXiv:2606.21419v1 Announce Type: new Abstract: Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance
arXiv:2606.21463v1 Announce Type: new Abstract: Accurate segmentation of subcortical regions is critical for neurosurgical planning and functional research. Most automated methods rely on template spa
arXiv:2606.22946v1 Announce Type: new Abstract: Neural operators learn mappings between function spaces, but are typically developed with dense input-output training fields and fully observed inputs a
arXiv:2601.17207v2 Announce Type: replace Abstract: We introduce NewPINNs, a physics-informing learning framework that couples neural networks with conventional numerical solvers for solving different
arXiv:2606.23200v1 Announce Type: cross Abstract: Neighboring-slice self-supervised denoising is attractive for volumetric medical imaging, yet inter-slice misalignment breaks anatomical correspondenc
Nice to see the Drivetrain Approach getting some love again! :D https://x.com/ForBo7_/status/2069337722821673174 Did a close read of @jeremyphoward et al's Drivetrain Approach Define goal → Consider l
arXiv:2603.22713v2 Announce Type: replace Abstract: Adversarial imitation learning (AIL) achieves high-quality imitation by mitigating compounding errors inherent to behavioral cloning (BC), yet its a
arXiv:2606.22696v1 Announce Type: new Abstract: We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measuremen
arXiv:2606.17276v3 Announce Type: replace-cross Abstract: Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been
arXiv:2602.24121v2 Announce Type: replace Abstract: Current methods in robot learning are fundamentally bottlenecked by one or more of: hand-designed rewards, simulation modeling, or action supervisio
arXiv:2512.24551v4 Announce Type: replace Abstract: Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws re
arXiv:2606.23098v1 Announce Type: new Abstract: The quantum nature of light determines the inherent Poisson stochasticity of photon detection, which is ubiquitous in photography, microscopy, and astro
arXiv:2606.21920v1 Announce Type: new Abstract: Goal-directed eye movements are a fundamental component of visuomotor control, enabling humans to anticipate and guide their actions. Whether this antic
arXiv:2606.22938v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains
arXiv:2601.19756v2 Announce Type: replace Abstract: The empirical success of deep learning is often attributed to deep networks' ability to exploit hierarchical structure in data, constructing increas
The Drivetrain Approach is a framework for building effective data products, developed by Jeremy Howard and published by O'Reilly Media, that focuses on defining business objectives, identifying lever
arXiv:2606.23069v1 Announce Type: new Abstract: Few-shot object detection aims to detect novel object categories from only a few labeled examples, avoiding costly large-scale annotation. Recent protot
arXiv:2606.22601v1 Announce Type: cross Abstract: Gaussian Processes (GPs) are a powerful tool for Bayesian time-series modeling, yet their cubic computational cost remains a severe barrier for applic
arXiv:2606.20477v2 Announce Type: replace Abstract: We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a lar
arXiv:2606.21929v1 Announce Type: new Abstract: Selective ensemble for modern machine learning systems requires choosing promising model candidates under limited evaluation budgets, while downstream t
In this post, you will learn patterns for implementing production-ready multi-tenant systems using Amazon Bedrock AgentCore. You will see these patterns demonstrated through healthcare AI agents that
arXiv:2606.21026v1 Announce Type: new Abstract: The ocean plays a critical role in sustainable development, particularly in climate change mitigation. Among marine ecosystems, blue carbon ecosystems a
arXiv:2606.21258v1 Announce Type: cross Abstract: Recent 3DGS-SLAM systems enable real-time operation by leveraging conventional feature matching or ICP-based tracking, thereby avoiding the heavy dens
arXiv:2606.21705v1 Announce Type: new Abstract: Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset mor
arXiv:2606.20600v1 Announce Type: cross Abstract: What can the success of modern AI tell us about how humans learn? This paper argues that taking AI seriously as a model of human learning supports a m
This year @WecoAI will be at the @aiDotEngineer World's Fair. We'll host a hands-on autoresearch workshop on June 29. And I'll give a talk on July 1. Looking forward to chatting with old and new frien
arXiv:2606.21700v1 Announce Type: new Abstract: Unsupervised domain adaptation (UDA) aims to learn a target-domain classifier from labeled source data and unlabeled target data under distribution shif
arXiv:2606.21790v1 Announce Type: new Abstract: We study what Lorentz-equivariant jet taggers learn internally, using equivariance tests, linear probes and grade ablations across five models including