tutorials

L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting

arXiv:2605.17730v1 Announce Type: cross Abstract: Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to t

Learning from Historical Activations in Graph Neural Networks

DGX agent

arXiv:2601.01123v2 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A

tutorialsarxiv-cs-ai

19 May 2026

Learning What Evaluators Value: A Reliable Approach to Modeling Evaluator Preferences

arXiv:2605.16615v1 Announce Type: new Abstract: In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For examp

Leveraging Latent Visual Reasoning in Silence

arXiv:2605.18641v1 Announce Type: new Abstract: Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation.

LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messaging

arXiv:2605.16264v1 Announce Type: cross Abstract: Push notifications remain among the most direct channels through which digital platforms engage users, yet existing approaches have invested heavily i

tutorialsarxiv-cs-cl

llms.txt validation will be supported in Chrome devtools :)

tutorialsjeremy-howard--x

Chrome DevTools will add support for validating llms.txt files, enabling developers to check the validity and correctness of their llms.txt configurations directly within the browser's developer tools

Machine Learning Enabled Graph Analysis of Particulate Composites: Application to Solid-state Battery Cathodes

arXiv:2512.16085v2 Announce Type: replace-cross Abstract: Particulate composites underpin many solid-state chemical and electrochemical systems, where microstructural features such as multiphase bound

Machines Learn Number Fields, But How? The Case of Galois Groups

arXiv:2508.06670v2 Announce Type: replace-cross Abstract: By applying interpretable machine learning methods such as decision trees, we study how simple models can classify the Galois groups of Galois

Maximum Likelihood Decoding of Quantum Error Correction Codes

arXiv:2605.17230v1 Announce Type: cross Abstract: Quantum error correction (QEC) is indispensable for realizing fault-tolerant quantum computation, yet its effectiveness hinges critically on the class

Meta-Learning Guided Pruning for Few-Shot Plant Pathology on Edge Devices

arXiv:2601.02353v3 Announce Type: replace Abstract: Farmers in remote areas need quick and reliable methods for identifying plant diseases, yet they often lack access to laboratories or high-performan

Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet

arXiv:2605.16887v1 Announce Type: new Abstract: Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap inc

Multiscale Supervised Unbalanced Optimal Transport Flow Matching

arXiv:2605.16529v1 Announce Type: new Abstract: Unbalanced optimal transport (UOT) provides a principled framework for modeling single-cell transitions and birth-death dynamics, but its high computati

MusicSynth: An Automated Pipeline for Generating Violin Fingerboard Animations from Sheet Music Using Optical Music Recognition

arXiv:2605.17181v1 Announce Type: cross Abstract: Learning the violin is harder than it looks. Unlike piano keys or guitar frets, the violin neck has no markings at all, so a beginner cannot tell by l

Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions

arXiv:2605.16818v1 Announce Type: cross Abstract: Learning physical dynamics directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and oft

Online Algorithms with Unreliable Guidance

arXiv:2602.20706v2 Announce Type: replace Abstract: This paper introduces online algorithms with unreliable guidance (OAG), a model for ML-augmented online decision-making that cleanly separates the p

PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning

arXiv:2601.08679v3 Announce Type: replace Abstract: As users increasingly expect LLMs to align with their preferences, personalized information becomes valuable. However, personalized information can

PhysSkin: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural Skinning

arXiv:2603.23194v2 Announce Type: replace-cross Abstract: Achieving real-time physics-based animation that generalizes across diverse 3D shapes and discretizations remains a fundamental challenge. We

PLATO Hand: Shaping Contact Behavior with Fingernails for Precise Manipulation

arXiv:2602.05156v2 Announce Type: replace Abstract: We present the PLATO Hand, a dexterous robotic hand with a hybrid fingertip that combines a rigid fingernail, embedded distal phalanx, and compliant

tutorialsarxiv-cs-ro

PromptDecipher: Supporting AI Tutor Authoring Through Editable Simulated Interactions

arXiv:2605.16605v1 Announce Type: cross Abstract: Chatbots have long been explored as tools to support learning, and recent advances in large language models have significantly expanded the availabili

RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs

arXiv:2602.05367v2 Announce Type: replace Abstract: Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and perf

RadJEPA: Radiology Encoder for Chest X-Rays via Joint Embedding Predictive Architecture

arXiv:2601.15891v2 Announce Type: replace Abstract: Recent advances in medical vision language models guide the learning of visual representations; however, this form of supervision is constrained by

Reasoning Can Be Restored by Correcting a Few Decision Tokens

arXiv:2605.16874v1 Announce Type: new Abstract: Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood

RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation

arXiv:2605.17522v1 Announce Type: new Abstract: Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predicti

tutorialsarxiv-cs-ro

Rover: Context-aware Conflict Resolution with LLM

arXiv:2605.17279v1 Announce Type: cross Abstract: Code merging is a significant challenge, particularly in large-scale projects. Existing solutions, including program analysis and machine learning, sh

scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement

arXiv:2605.18576v1 Announce Type: new Abstract: A critical challenge in single-cell RNA sequencing (scRNA-seq) integration is resolving the tension between eliminating batch effects and maintaining bi

Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data

arXiv:2605.18557v1 Announce Type: new Abstract: The brain learns abstract representations of high-dimensional sensory input, but the plasticity rules that enable such learning are unknown. We study bi

SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

arXiv:2512.04746v2 Announce Type: replace-cross Abstract: Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance de

Single Image Reflection Removal with Patch Reflectance Prior

arXiv:2312.03798v2 Announce Type: replace Abstract: Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface d

Sparse Autoencoders are Topic Models

arXiv:2511.16309v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by d

Sparse Deep Additive Model with Interactions: Enhancing Interpretability and Predictability

arXiv:2509.23068v2 Announce Type: replace-cross Abstract: Recent advances in deep learning highlight the need for personalized models that can learn from small samples, handle high-dimensional feature

SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation

arXiv:2605.18267v1 Announce Type: new Abstract: Normalizing flows (NFs) provide exact likelihoods and deterministic invertible sampling, but have historically lagged behind diffusion models for large-

StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow

arXiv:2605.16486v1 Announce Type: cross Abstract: Diffusion and flow-based models are ubiquitously used for generative modelling and density estimation. They admit a deterministic probability flow ord

Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth

arXiv:2605.18603v1 Announce Type: new Abstract: Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically

Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search

arXiv:2605.17762v1 Announce Type: new Abstract: Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositi

Tensor Cookbook: Mastering Tensors through Diagrams

arXiv:2605.16610v1 Announce Type: new Abstract: High-dimensional data arise naturally in many areas of science and engineering, including machine learning, signal processing, computational physics, an

The Diffusion Duality, Chapter II: Psi-Samplers

arXiv:2602.21185v2 Announce Type: replace Abstract: Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over a

The Learnability Gap in Medical Latent Diffusion

arXiv:2605.17087v1 Announce Type: new Abstract: Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approac

The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation

arXiv:2605.17500v1 Announce Type: cross Abstract: Generative text-to-image models are typically trained on large-scale web-scraped datasets that include diverse visual content such as copyrighted and

Therapist-Exoskeleton-Patient Interaction for Gait Therapy

arXiv:2507.16059v2 Announce Type: replace Abstract: Following a stroke, individuals often experience mobility and balance impairments due to lower-limb weakness and loss of independent joint control.

tutorialsarxiv-cs-ro

TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration

arXiv:2601.20306v2 Announce Type: replace Abstract: All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation

Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty

arXiv:2602.12687v2 Announce Type: replace-cross Abstract: The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how clas

Venom: A PyTorch Generative Modeling Toolkit

arXiv:2605.17605v1 Announce Type: new Abstract: Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

arXiv:2509.17680v2 Announce Type: replace Abstract: Table question answering (TableQA) is a fundamental task in natural language processing (NLP). The strong reasoning capabilities of large language m

tutorialsarxiv-cs-cl

You can ask Cursor to fix bugs, add features, update tests, or investigate a task described in the work item. Learn more: http://cursor.com/…

Cursor is an AI tool that can assist with software development tasks including bug fixes, feature additions, test updates, and task investigation based on work item descriptions. The platform enables

tutorialscursor--x

A Unified View of Score-Based and Drifting Models

arXiv:2603.07514v3 Announce Type: replace-cross Abstract: Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with

Anthropic last week began letting Mythos users share cybersecurity threats with others who may face similar vulnerabilities, modifying its previous stance (Amrith Ramkumar/Wall Street Journal)

Amrith Ramkumar / Wall Street Journal: Anthropic last week began letting Mythos users share cybersecurity threats with others who may face similar vulnerabilities, modifying its previous stance — How

tutorialstechmeme

Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis

arXiv:2605.15551v1 Announce Type: new Abstract: Training large-scale deep neural networks (DNNs) is resource-intensive, making model compression a practical necessity. The widely accepted ''learning a

CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage

arXiv:2605.15597v1 Announce Type: new Abstract: Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructio