tutorials

Direct Simultaneous Translation Activation for Large Audio-Language Models

arXiv:2509.15692v2 Announce Type: replace-cross Abstract: Simultaneous speech-to-text translation (Simul-S2TT) aims to translate speech into target text in real time, outputting translations while rec

Tutorials

Enhance the after-discharge mortality rate prediction via learning from the medical notes

DGX agent

arXiv:2605.03560v1 Announce Type: new Abstract: With the increase of the Electronic Health Records (EHR) data, more and more researchers are developing machine learning models to learn from the medica

tutorialsarxiv-cs-lg

6 May 2026

Enhancing Visual Question Answering with Multimodal LLMs via Chain-of-Question Guided Retrieval-Augmented Generation

arXiv:2605.03790v1 Announce Type: new Abstract: With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of

Every month for the last 6 years, I’ve gotten a $0.50 charge to my debit card from AWS for an account I don’t use or remember how to access.…

tutorialscristobal-valenzuela--x

Every month for the last 6 years, I’ve gotten a 0.50 charge to my debit card from AWS for an account I don’t use or remember how to access. I have no idea why. I am willing to pay 0.6

Flow Sampling: Learning to Sample from Unnormalized Densities via Denoising Conditional Processes

arXiv:2605.03984v1 Announce Type: new Abstract: Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function

Give LLMs 1. A latent space diffusion-like reasoning. 2. A real recurrent state. 3. A world-model pre-pre-training. And we are done.

tutorialsjeremy-howard--x

Jeremy Howard proposes three key enhancements for large language models: incorporating latent space diffusion-like reasoning processes, adding a persistent recurrent state mechanism, and implementing

Graph Neural Network based Hierarchy-Aware Embeddings of Knowledge Graphs: Applications to Yeast Phenotype Prediction

arXiv:2605.03690v1 Announce Type: new Abstract: We present a method for finding hierarchy-aware embeddings of knowledge graphs (KGs) using graph neural networks (GNNs) enriched with a semantic loss de

How ChatGPT learns about the world while protecting privacy

ChatGPT learns about the world through training on diverse text data while implementing privacy protections that prevent it from storing personal information from individual conversations or retaining

tutorialsopenai

I ❤️ NYC We're hosting two in-person events next Wednesday: 1️⃣ FinParse workshop: Build AI agents to extract and act over the most complex …

I ❤️ NYC We're hosting two in-person events next Wednesday: 1️⃣ FinParse workshop: Build AI agents to extract and act over the most complex financial documents 2️⃣ AI Happy Hour with Tabs: drinks, con

tutorialsjerry-liu--x

I'm disappointed by repeatedly hearing that my colleagues at Anthropic believe they are the only ones who should be trusted with building AI…

tutorialsjeremy-howard--x

I'm disappointed by repeatedly hearing that my colleagues at Anthropic believe they are the only ones who should be trusted with building AI. It is *very good* there are a diversity of people building

Learning Discriminative Signed Distance Functions from Multi-scale Level-of-detail Features for 3D Anomaly Detection

arXiv:2605.03437v1 Announce Type: new Abstract: Detecting anomalies from 3D point clouds has received increasing attention in the field of computer vision, with some group-based or point-based methods

Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding

arXiv:2605.03620v1 Announce Type: cross Abstract: Syndrome-based neural decoding (SBND) has emerged as a promising deep learning approach for soft-decision decoding of high-rate, short-length codes. H

LlamaIndex NYC takeover, 5/13 🗽 Our CEO Jerry Liu is in town. Two events, open to every NYC builder: 🛠️ FinParse Workshop — laptops out, h…

LlamaIndex NYC takeover, 5/13 🗽 Our CEO Jerry Liu is in town. Two events, open to every NYC builder: 🛠️ FinParse Workshop — laptops out, hands-on with @jerryjliu0 → https://luma.com/updli8i6 🍕 AI Engi

tutorialsjerry-liu--x

LLM-Assisted Repository-Level Generation with Structured Spec-Driven Engineering

arXiv:2605.02455v1 Announce Type: cross Abstract: State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when

Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

arXiv:2507.22268v3 Announce Type: replace-cross Abstract: We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purcha

Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF

arXiv:2605.03799v1 Announce Type: new Abstract: This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline: from tokenisation and ve

Neural Decision-Propagation for Answer Set Programming

arXiv:2605.01797v1 Announce Type: new Abstract: Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend

Parametrization of subgrid scales in long-term simulations of the shallow-water equations using machine learning and convex limiting

arXiv:2602.00378v2 Announce Type: replace-cross Abstract: We present a method for parametrizing sub-grid processes in the Shallow Water equations. We define coarse variables and local spatial averages

Physically Guided Visual Mass Estimation from a Single RGB Image

arXiv:2601.20303v2 Announce Type: replace Abstract: Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of

Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines

arXiv:2507.05561v2 Announce Type: replace Abstract: Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans levera

PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL

arXiv:2605.02917v1 Announce Type: new Abstract: Supervised deep learning models for automated CTG analysis are typically constrained by narrowly curated labelled datasets and limited patient cohorts,

Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News

arXiv:2605.03450v1 Announce Type: new Abstract: In studies of media coverage of extreme climate events, NLP methods have become indispensable for identifying relevant texts in large news databases. St

SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering

arXiv:2605.02819v1 Announce Type: new Abstract: Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide st

Text-Conditional JEPA for Learning Semantically Rich Visual Representations

arXiv:2605.03245v1 Announce Type: cross Abstract: Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature pre

Using Echo-State Networks to Reproduce Rare Events in Chaotic Systems

arXiv:2505.16208v2 Announce Type: replace-cross Abstract: We apply Echo-State Networks to predict time series and statistical properties of the competitive Lotka-Volterra model in the chaotic regime.

ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable

arXiv:2604.25224v2 Announce Type: replace Abstract: LLM-based financial agents increasingly produce investment rationales before the outcomes needed to evaluate them are observable. This creates a del

A Survey of Reasoning-Intensive Retrieval: Progress and Challenges

arXiv:2605.00063v1 Announce Type: cross Abstract: Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting

A tutorial on learning from preferences and choices with Gaussian Processes

arXiv:2403.11782v5 Announce Type: replace Abstract: Preference modelling lies at the intersection of economics, decision theory, machine learning and statistics. By understanding individuals' preferen

Adaptation of AI-accelerated CFD Simulations to the IPU platform

arXiv:2605.00462v1 Announce Type: cross Abstract: Intelligence Processing Units (IPU) have proven useful for many AI applications. In this paper, we evaluate them within the emerging field of AI for s

AlbumFill: Album-Guided Reasoning and Retrieval for Personalized Image Completion

arXiv:2605.02892v1 Announce Type: new Abstract: Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely

An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection

arXiv:2605.02259v1 Announce Type: new Abstract: Incomplete propagation data significantly hinders robust fake news detection. Recent approaches leverage large language models to simulate missing user

Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition

arXiv:2605.01217v1 Announce Type: new Abstract: Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse

CCNETS: A Modular Causal Learning Framework for Pattern Recognition in Imbalanced Datasets

arXiv:2401.04139v4 Announce Type: replace Abstract: Handling class imbalance remains a central challenge in machine learning, particularly in pattern recognition tasks where identifying rare but criti

Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models

arXiv:2601.08517v2 Announce Type: replace Abstract: Channel-configuration search, the optimization of layer specifications such as channel widths in deep neural networks, presents a combinatorial chal

Coding agents are accelerating different types of software work to different degrees. When we architect teams, understanding these distincti…

Coding agents are accelerating different types of software work to different degrees. When we architect teams, understanding these distinctions helps us to have realistic expectations. Listing functio

tutorialsandrew-ng--x

Continual Learning of Feedback-based Molecular Communication

arXiv:2605.01020v1 Announce Type: new Abstract: This paper proposes and evaluates a new performance estimation method that leverages continual learning (CL) algorithms to carry out sequential simulati

Cross-Scale Pretraining: Enhancing Self-Supervised Learning for Low-Resolution Satellite Imagery for Semantic Segmentation

arXiv:2601.12964v2 Announce Type: replace Abstract: Self-supervised pretraining in remote sensing is mostly done using mid-spatial resolution (MR) image datasets due to their high availability. Given

Data-Driven, Geometry-Aware Optimal-Transport Calibration of Flavor Tagger

arXiv:2605.01363v1 Announce Type: cross Abstract: Flavor-tagging calibrations are often provided either as scale factors measured at a finite set of working points or as binned corrections to a chosen

Decouple and Cache: KV Cache Construction for Streaming Video Understanding

arXiv:2605.01858v1 Announce Type: new Abstract: Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continu

Degradation-Aware Adaptive Context Gating for Unified Image Restoration

arXiv:2605.01236v1 Announce Type: new Abstract: Unified image restoration using a single model often faces task interference due to diverse degradations. To address this, we propose DACG-IR (Degradati

Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting

arXiv:2605.00850v1 Announce Type: cross Abstract: Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile do

EGAD: Entropy-Guided Adaptive Distillation for Token-Level Knowledge Transfer

arXiv:2605.01732v1 Announce Type: new Abstract: Large language models (LLMs) have achieved remarkable performance across diverse domains, yet their enormous computational and memory requirements hinde

Exploring Accuracy Law for Deep Time Series Forecasters: An Empirical Study

arXiv:2510.02729v2 Announce Type: replace Abstract: Deep time series forecasting has emerged as a rapidly growing field in recent years. Despite the exponential growth of community interests, progress

Forager: a lightweight testbed for continual learning with partial observability in RL

arXiv:2605.01131v1 Announce Type: new Abstract: In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world

Foundations of Riemannian Geometry for Riemannian Optimization: A Monograph with Detailed Derivations

arXiv:2605.02279v1 Announce Type: cross Abstract: Riemannian geometry provides the fundamental framework for optimization on nonlinear spaces such as matrix manifolds, which arise in machine learning,

Generative Modeling with Orbit-Space Particle Flow Matching

arXiv:2605.02222v1 Announce Type: cross Abstract: We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP

GenRecEdit: Adapting Model Editing for Generative Recommendation with Cold-Start Items

arXiv:2603.14259v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) has shown strong potential for sequential recommendation in an end-to-end generation paradigm. However, existin

Geometry-Aware Scene Configurations for Novel View Synthesis

arXiv:2510.09880v2 Announce Type: replace Abstract: We propose scene-adaptive strategies to efficiently allocate representation capacity for generating immersive experiences of indoor environments fro