Search: “tutorials”

It is refreshing to have some new arguments pointing at specific distributions (Gaussian) our embeddings must follow! Especially now that we…

It is refreshing to have some new arguments pointing at specific distributions (Gaussian) our embeddings must follow! Especially now that we know how to do scalable distribution matching in high dimen

tutorialsyann-lecun--x

Tutorials

it's boston tech week! come join @masondrxy and i with the @blitzyai team to learn about building deep agents! https://luma.com/9ob847de

DGX agent

Boston Tech Week featured a session hosted by Mason Dry and Sydney Runkle with the Blitzy AI team focused on building deep agents. The event was promoted via Luma Events and appears to be an education

tutorialsharrison-chase--x

27 May 2026

Joint 2D-3D Segmentation and Association in Street-level Imaging

arXiv:2605.26725v1 Announce Type: new Abstract: Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments.

Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences

arXiv:2605.26850v1 Announce Type: new Abstract: Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matc

Learning to Diagnose and Correct Errors: Towards Moral Sensitivity Acquisition in Large Language Models

arXiv:2601.03079v4 Announce Type: replace Abstract: Moral sensitivity is the most fundamental capability underlying human moral competence. Although many approaches aim to align large language models

Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking

arXiv:2605.26933v1 Announce Type: new Abstract: Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotatio

Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models

arXiv:2506.11253v2 Announce Type: replace Abstract: Machine unlearning removes certain training data points and their influence from AI models (e.g., when a data owner revokes their consent to allow m

MatFormBench: A Benchmarking Evaluation Framework for Target-Driven Materials Formulation

arXiv:2605.26741v1 Announce Type: cross Abstract: Inverse design of materials has significantly advanced target-driven formulation optimization, yet existing materials machine learning benchmarks rema

Model Unlearning Objectives Vary for Distinct Language Functions

arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai

Normal Guidance is what Attention Needs

arXiv:2605.27306v1 Announce Type: new Abstract: We consider training classifiers for 3D medical images using only one binary label for the entire volume rather than a label for each 2D slice. In such

On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning

arXiv:2605.26649v1 Announce Type: new Abstract: RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representatio

tutorialsarxiv-cs-ro

Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics

arXiv:2605.26840v1 Announce Type: new Abstract: Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as

ORCA: An End-to-End Interactive Copilot for Optimized Root Cause Analysis

arXiv:2605.27022v1 Announce Type: new Abstract: Causal analysis is a crucial task in many domains, including manufacturing, social science, and medicine. However, despite recent progress, the conceptu

Personalized Generative Models for Contextual Debiasing

arXiv:2605.26353v1 Announce Type: cross Abstract: Different visual patterns appear with different frequencies in the world: e.g., beach balls appear on sand more often than they do on a road. These st

PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance

arXiv:2605.27128v1 Announce Type: new Abstract: Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real

Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning

arXiv:2605.26167v1 Announce Type: cross Abstract: We propose Lie group embedded dynamical neural networks (LieEDNN) and the corresponding learning algorithms based on gradient descent and metric proje

Proper Calibeating

arXiv:2605.26703v1 Announce Type: cross Abstract: The classic concept of 'calibrated forecasts' and its more recent refinement, 'calibeating,' are defined with respect to the standard quadratic scorin

RAGEAR: Retrieval-Augmented Graph-Enhanced Academic Recommender

arXiv:2605.26819v1 Announce Type: cross Abstract: We present RAGEAR (Retrieval-Augmented Graph-Enhanced Academic Recommender), a neurosymbolic recommender system for academic course recommendation. RA

Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning

arXiv:2605.27080v1 Announce Type: new Abstract: Appearance-based gaze estimation always suffers from poor generalization due to limited annotated samples and insufficient dataset diversity. Leading ap

Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

arXiv:2605.27030v1 Announce Type: new Abstract: Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution

SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising

arXiv:2605.26894v1 Announce Type: new Abstract: In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction

The entire event yesterday, launching missions, landers, rovers, tech demos building a Moon Base, and sci-fi capabilities like MoonFall, bro…

The entire event yesterday, launching missions, landers, rovers, tech demos building a Moon Base, and sci-fi capabilities like MoonFall, brought to you by those who Dare Mighty Things. Just the very b

tutorialselon-musk--x

The fact that tokens went from something no one even put in a budget line a year ago to an absolute requirement for coding now is the cause …

tutorialsethan-mollick--x

The fact that tokens went from something no one even put in a budget line a year ago to an absolute requirement for coding now is the cause of handwringing, not that AI is not turning out to be useful

This Ebola outbreak has been a slow motion disaster - 900 cases and and now threatening the U.S.. We know how to stop outbreaks like this. B…

This Ebola outbreak has been a slow motion disaster - 900 cases and and now threatening the U.S.. We know how to stop outbreaks like this. But Trump chose not to stop it. He destroyed our global healt

tutorialsyann-lecun--x

Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning via Knowledge-Grounded LLM

arXiv:2605.26405v1 Announce Type: new Abstract: Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback

Transformers Can Learn Posterior Predictive Distributions In-Context

arXiv:2605.26713v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive d

Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently

arXiv:2511.17852v2 Announce Type: replace Abstract: Transformers can acquire Chain-of-Thought (CoT) capabilities to solve complex reasoning tasks through fine-tuning. Reinforcement learning (RL) and s

We're on a dangerous trajectory toward superintelligent AI that nobody controls. ControlAI's Adam Shimi (@epist_vigilance) and Connor Leahy …

We're on a dangerous trajectory toward superintelligent AI that nobody controls. ControlAI's Adam Shimi (@epist_vigilance) and Connor Leahy (@NPCollapse) lay out the problem and how to tackle it, in a

tutorialsconnor-leahy--x

What does JEPA actually learn? We can finally prove it 🌍 So excited to share our theory of identifiable World Models: LeJEPA recovers the l…

What does JEPA actually learn? We can finally prove it 🌍 So excited to share our theory of identifiable World Models: LeJEPA recovers the latent variables of the world. Plan in the learned World Model

tutorialsyann-lecun--x

Wow. It looks like the @XiaomiMiMo v2.5 model is insanely good value :O (Price for each prompt shown after each answer. Context includes >40…

tutorialsjeremy-howard--x

Jeremy Howard comments on the Xiaomi MiMo v2.5 model, highlighting its exceptional value proposition and cost-effectiveness for prompt processing. The post appears to include comparative pricing data

A Context Augmented Multi-Play Multi-Armed Bandit Algorithm for Fast Channel Allocation in Opportunistic Spectrum Access

arXiv:2605.25391v1 Announce Type: new Abstract: We study the restless contextual multi-play multi-armed bandit (MP-MAB) problem for channel allocation in the opportunity spectrum access (OSA) scenario

A perspective on fluid mechanical environments for challenges in reinforcement learning

arXiv:2605.25011v1 Announce Type: new Abstract: We consider the challenge of developing agents that efficiently interact with high-dimensional, evolving environments, towards a view of practical reinf

An Empirical Evaluation of LLM-Generated Code Security Across Prompting Methods

arXiv:2605.24298v1 Announce Type: cross Abstract: The growing use of Large Language Models (LLMs) for automated code generation has enhanced software development efficiency, but often at the cost of s

Asymmetric Adaptation-based Real-time Fault Diagnosis Under Transitional Operating Conditions

arXiv:2605.24457v1 Announce Type: cross Abstract: Data streams in real-world industrial scenarios often contain transitional operating conditions that are uncovered during offline training, leading to

BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization

arXiv:2605.23937v1 Announce Type: new Abstract: Knowledge base (KB) embeddings aim at combining the capability of classical knowledge graph embeddings to generalize the information present in facts, t

Demystifying the Mythos or Disrupting Bugonomics? From Zero-Day Asymmetry to Defender Remediation Throughput

arXiv:2605.24632v1 Announce Type: cross Abstract: Recent demonstrations of large language models producing candidate and confirmed vulnerabilities in production software have renewed the narrative tha

Designing Singing Syllabi with Virtual Avatars: AI-Assisted Syllabus Reauthoring

arXiv:2508.11872v3 Announce Type: replace-cross Abstract: Traditional syllabi often function as static reference documents rather than engaging introductions to a course. In practical teaching, we obs

everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my mind, it's a system that obser…

tutorialsharrison-chase--x

everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my mind, it's a system that observes it's own outputs, evaluates them, and uses that signal t

EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models

arXiv:2605.25477v1 Announce Type: cross Abstract: The ability to efficiently and reliably learn new tasks has been a foundational challenge in robotics. Vision-Language-Action (VLA) models have demons

Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting

arXiv:2605.24911v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-au

Fermi-Dirac machines as quantizations of neurons

arXiv:2605.24386v1 Announce Type: cross Abstract: Fermi-Dirac machines were proposed recently as an approach to solving semidefinite optimization problems on quantum computers. Here, we reinterpret th

Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification

arXiv:2605.24367v1 Announce Type: cross Abstract: The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural

How Should LLMs Consume High-Quality Data? Optimal Data Scheduling via Quality-Aware Functional Scaling Laws

arXiv:2605.25698v1 Announce Type: cross Abstract: High-quality data is scarce in large language model (LLM) training, yet how to schedule its use jointly with training dynamics lacks theoretical guida

How to use Grok Build

How to use Grok Build Beginner video: How to install & use Grok Build (made for non-technical SuperGrok and X Premium+ users) I got so many questions from friends, so I made this simple step-by-step g

tutorialselon-musk--x

HyperGuide: Hyperbolic Guidance for Efficient Multi-Step Reasoning in Large Language Models

arXiv:2605.24140v1 Announce Type: new Abstract: Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods

// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from lon…

// Language Models Need Sleep // Let your agents 'sleep', folks. On a serious note, this is a fascinating paper on getting the most from long-horizon agents. Here is the problem with agents today: Att

tutorialsdair-ai--x

Learning, locomotion, and navigation of soft synthetic snakes in three-dimensional, heterogeneous environments

arXiv:2605.24985v1 Announce Type: cross Abstract: Limbless terrestrial animals exhibit exceptional locomotor versatility and control, currently unmatched by engineered counterparts. Here, we introduce

Learning to Search and Searching to Learn for Generalization in Planning

arXiv:2605.25720v1 Announce Type: new Abstract: Combinatorial generalization remains a central challenge in Deep Reinforcement Learning (DRL). Classical planning provides a simple yet challenging sett