tutorials

Adaptive Sampling and Clipping for Private Worst-Case Group Optimization

arXiv:2602.10820v2 Announce Type: replace Abstract: A central requirement for the acceptance of machine learning methods for human-centric tasks is that they should be fair, in the sense that they sho

Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting

DGX agent

arXiv:2605.27668v1 Announce Type: cross Abstract: Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM forecasting, existing methods typically learn from binar

tutorialsarxiv-cs-ai

28 May 2026

Automatic Pruning Discovery for Large Language Models

arXiv:2511.15390v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive siz

Banger paper from Harvard. AutoScientists drops the central planner entirely. Agents interpret shared experimental data, self-organize aroun…

Banger paper from Harvard. AutoScientists drops the central planner entirely. Agents interpret shared experimental data, self-organize around promising directions, evaluate proposals before resource a

tutorialsdair-ai--x

Build a custom portal with embedded Amazon SageMaker AI MLflow Apps

In this post, you learn how to build a custom portal with embedded SageMaker AI MLflow Apps UI. You walk through the architecture pattern behind a React front end paired with a Flask reverse proxy tha

tutorialsaws-ml-blog

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

arXiv:2605.27860v1 Announce Type: new Abstract: Retrieval-augmented generation combined with reinforcement learning has shown promise for grounding large language models in trustworthy medical evidenc

Canvas updates include: - Improved canvas interactions & more powerful tools - Better mobile experience - Image generation with GPT-Image 2,…

Canvas updates include: - Improved canvas interactions & more powerful tools - Better mobile experience - Image generation with GPT-Image 2, videos with Seedance, and animated SVGs - Updated visual ed

tutorialsreplit--x

Checking Fact with Better Retrieval: Dynamic Contrastive Learning for Evidence Retrieval

arXiv:2605.27449v1 Announce Type: cross Abstract: In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream cla

CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes

arXiv:2605.28125v1 Announce Type: new Abstract: Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and im

Continuous Diffusion Models Can Obey Formal Syntax

arXiv:2602.12468v2 Announce Type: replace Abstract: Diffusion language models offer a promising alternative to autoregressive models due to their global, non-causal generation process, but their conti

D^2Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation

arXiv:2605.27460v1 Announce Type: new Abstract: Single-frame atmospheric turbulence mitigation is inherently ill-posed due to spatially varying blur coupled with non-rigid geometric distortion. Existi

Data Residency with Vultr: Privacy, Security & Compliance

Vultr's data residency solution enables organizations to store and process data within specific geographic regions to meet regulatory compliance requirements such as GDPR, HIPAA, and local data protec

tutorialsvultr

DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation

arXiv:2605.27931v1 Announce Type: new Abstract: Scientific diagrams are essential for communicating complex methodologies in academic papers. A natural way for researchers to specify such diagrams is

Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study

arXiv:2512.15791v2 Announce Type: replace-cross Abstract: In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simul

Fascinating results + Anthropic running away with it right now + So many people want to start their own company + Google over OpenAI + Verce…

tutorialsjeremy-howard--x

Fascinating results + Anthropic running away with it right now + So many people want to start their own company + Google over OpenAI + Vercel, Linear, Every, PostHog overperforming A great list if you

Formula-One Prompting: A Composable Equation-First Prefix for Applied Mathematics

arXiv:2601.19302v3 Announce Type: replace Abstract: This paper introduces Formula Prompting (FP) and Formula-One Prompting (F-1), two single-call methods that elicit governing equations before solving

From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

arXiv:2605.27944v1 Announce Type: new Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepf

Fun fact: Australia is basically Scandinavia with the Sahara Desert bolted on.

tutorialsjeremy-howard--x

Fun fact: Australia is basically Scandinavia with the Sahara Desert bolted on. I LOVE this visualisation. Everyone imagines nature and the outback, but they don't realise just how urbanised we are. Cr

Go from resource-level to business-level maintenance in Google Cloud

Managing planned maintenance is a critical part of running a reliable business. But as your cloud footprint grows into hundreds or even thousands of projects, keeping track of every individual update

tutorialsgoogle-cloud-ai

[Guide] How to securely run ComfyUI on Windows (Docker>WSL2) [RTX 3090, logic can be applied to other hardware]

tutorialsr-stablediffusion

ComfyUI is a node-based interface for Stable Diffusion that can be run on Windows using Docker and WSL2 (Windows Subsystem for Linux 2) for improved security and performance. This guide provides instr

Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognition

arXiv:2504.10079v4 Announce Type: replace Abstract: Few-shot action recognition (FSAR) aims to recognize novel action categories with few exemplars. Existing methods typically learn frame-level repres

How to secure your vibecoded app in 4 steps 🔒 Speed without security is a liability. Here's how to ship without leaving the back door open …

This post from Replit outlines a 4-step security framework for protecting vibecoded applications in production environments. It emphasizes that application speed must not come at the expense of securi

tutorialsreplit--x

Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization

arXiv:2605.28802v1 Announce Type: new Abstract: Free-text explanations extend human label variation (HLV) beyond label disagreement by revealing the reasoning and preferences behind annotators' decisi

Identifiable Bayesian Deep Generative Copulas with Unknown Layer Widths for Data with Arbitrary Marginal Distributions

arXiv:2605.27523v1 Announce Type: cross Abstract: Deep generative models offer powerful tools for multivariate data analysis, but their black-box architectures are often unidentified and difficult to

Inversely Learning Transferable Rewards via Abstracted States

arXiv:2501.01669v4 Announce Type: replace Abstract: Inverse reinforcement learning (IRL) has progressed significantly toward accurately learning the underlying rewards in both discrete and continuous

Keyphrase Generative Representation of Youth Crisis Conversations Beyond Static Taxonomies

arXiv:2605.27546v1 Announce Type: new Abstract: Crisis Responders (CRs) rapidly assess thousands of youth SMS conversations each year to identify mental health concerns and guide support. Yet youth di

Learn from your own latents and not from tokens: A sample-complexity theory

arXiv:2605.27734v1 Announce Type: new Abstract: Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude lar

Learning a Kinodynamic Trajectory Manifold for Impact-Aware Compliant Catching of Fast-Moving Objects

arXiv:2605.28462v1 Announce Type: new Abstract: Fast catching of free-flying objects is difficult because of short reaction time, impact uncertainty, and kinodynamic constraints. We use reinforcement

tutorialsarxiv-cs-ro

Learning Correlated Reward Models: Statistical Barriers and Opportunities

arXiv:2510.15839v2 Announce Type: replace Abstract: Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learni

Learning the Error Patterns of Language Models

arXiv:2605.28328v1 Announce Type: cross Abstract: When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused

Learning to Assess the Reliability of Number-of-Runs Estimation in Stochastic Optimization

arXiv:2605.28309v1 Announce Type: new Abstract: In large-scale benchmarking of stochastic optimization algorithms, the key challenge is no longer whether repeated runs are needed for reliability, but

Majorization-Minimization Networks for Inverse Problems: An Application to EEG Imaging

arXiv:2602.03855v2 Announce Type: replace-cross Abstract: Inverse problems are often ill-posed and require optimization schemes with strong stability and convergence guarantees. While learning-based a

Measure-to-measure Regression with Transformers

arXiv:2605.28075v1 Announce Type: new Abstract: Many learning problems require predicting how populations evolve under an unknown transformation. A natural representation for such populations is a pro

Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images

arXiv:2605.28693v1 Announce Type: cross Abstract: Backpropagation is the core learning mechanism underlying deep learning. However, whether and how this algorithm is implemented in the brain remains h

Neural Image Space Tessellation efect

arXiv:2602.23754v2 Announce Type: replace-cross Abstract: We present Neural Image Space Tessellation effect (NIST), a lightweight screen-space post-processing approach for reducing the faceted silhoue

New Classroom Accounts expand quantum access for educators

IBM has introduced new classroom accounts that provide educators with expanded access to quantum computing resources for teaching and research purposes. These accounts are designed to make quantum tec

tutorialsibm-research

PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation

arXiv:2605.28634v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models offer a promising paradigm for generalist robotic policies, yet their adaptation is hindered by data inefficiency an

tutorialsarxiv-cs-ro

Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields

arXiv:2605.28625v1 Announce Type: new Abstract: Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussi

Revealing Algorithmic Deductive Circuits for Logical Reasoning

arXiv:2605.27824v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representation

SAFEVPR: Patch-Based Conformal Verification for Safe Cross-Condition Sequence Visual Place Recognition

arXiv:2605.28048v1 Announce Type: new Abstract: Sequence-based visual place recognition (VPR) for SLAM and robot relocalization must decide whether the retrieved top-1 candidate is safe to accept. Con

tutorialsarxiv-cs-ro

Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization

arXiv:2605.28394v1 Announce Type: new Abstract: Animation of 2D hand-drawn sketches provides an effective medium for visual communication. However, these sketches pose challenges, particularly in hand

Streamline external access to Amazon SageMaker MLflow using a REST API proxy

In this post, we demonstrate how to build a secure Flask-based MLflow proxy service that provides HTTPS access to Amazon SageMaker MLflow without requiring the MLflow SDK. This solution is for organiz

tutorialsaws-ml-blog

“The mechanism is always the same in every story I've been covering. The demo works in a controlled environment with clean inputs. The deplo…

“The mechanism is always the same in every story I've been covering. The demo works in a controlled environment with clean inputs. The deployment fails because real kitchens, real intersections, and r

tutorialsgary-marcus--x

The Principles of Diffusion Models

arXiv:2510.21890v2 Announce Type: replace-cross Abstract: This book presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse for

Transformers Provably Learn to Internalize Chain-of-Thought

arXiv:2605.28600v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning fro

Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models

arXiv:2605.28132v1 Announce Type: new Abstract: Spatial intelligence requires visual representations that capture both semantic objects and geometric structure in the physical world. To support this,

Why Gaussian Diffusion Models Fail on Discrete Data and How to Prevent It?

arXiv:2604.02028v2 Announce Type: replace Abstract: Diffusion models have become a standard approach for generative modeling in continuous domains, yet their application to discrete data remains chall

Adversarial Water-Filling: Theory, Algorithms and Foundation Model

arXiv:2605.26163v1 Announce Type: cross Abstract: Competitive resource allocation problems over frequency and space can be formulated as minimax interaction between transmit power and worst-case inter