tutorials

Knowledge Cascade: Reverse Knowledge Distillation on Nonparametric Multivariate Functional Estimation

arXiv:2606.25927v1 Announce Type: cross Abstract: As machine learning models and datasets continue to grow, developing complex models has become increasingly computationally demanding. Knowledge disti

Tutorials

Learning task-specific subspaces via interventional post-training of speech foundation models

DGX agent

arXiv:2606.17967v2 Announce Type: replace Abstract: Speech foundation models, pre-trained on large corpora of unlabelled speech data, produce general-purpose representations which are useful across ta

tutorialsarxiv-cs-cl

25 Jun 2026

Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention

arXiv:2606.25342v1 Announce Type: new Abstract: Lifelong continual learning remains an obstacle on the path to human-like intelligence. Modern transformers show sparks of intelligence with in-context

LLM Program Optimization via Retrieval Augmented Search

arXiv:2501.18916v2 Announce Type: replace Abstract: Recent work has demonstrated the potential of large language models (LLMs) for program optimization, a key challenge in programming languages. We pr

lots of folks prepping talks next week (congrats!). Some thoughts from RLing on thousands of hours of engineer- and researcher- focused talk…

lots of folks prepping talks next week (congrats!). Some thoughts from RLing on thousands of hours of engineer- and researcher- focused talks: - AI generated svgs > AI generated imgs. MAXIMUM 4 ai slo

tutorialsswyx--x

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

arXiv:2606.25225v1 Announce Type: new Abstract: Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual strea

Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data

arXiv:2603.22050v2 Announce Type: replace-cross Abstract: Supervised machine learning describes the practice of fitting a parameterized model to labeled input-output data. Supervised machine learning

obvious in retrospect but I had no idea there was a black market for tokens

tutorialsjeremy-howard--x

Jeremy Howard discusses the existence of a black market for AI tokens, expressing surprise at learning about this market dynamic. The post likely covers unauthorized trading, resale, or acquisition of

Or people could learn their lesson? Naah 🙈

Or people could learn their lesson? Naah 🙈 @GaryMarcus The reason he’s going down, is because the market can only handle one all encompassing scam at a time. So the AI scam will probably get a boost w

tutorialsgary-marcus--x

Stabilizing black-box algorithms through task-oriented randomization

arXiv:2606.25269v1 Announce Type: cross Abstract: As black-box models become foundational to modern research, ensuring their stability is paramount for the realization of trustworthy artificial intell

Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation

arXiv:2606.25645v1 Announce Type: cross Abstract: In recent years, the posting of fake news including disinformation and misinformation on social networking services (SNS) has become a social problem.

We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve s…

We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a s

tutorialscursor--x

What happens when you shift more of the context layer into the model weights themselves? Engram is building a neolab focused on memory and c…

What happens when you shift more of the context layer into the model weights themselves? Engram is building a neolab focused on memory and continual learning. Let’s go @dan_biderman @realJessyLin! Fun

tutorialssonya-huang--x

What's in an Earth Embedding? An Explainability Analysis of Location Encoders

arXiv:2606.24997v1 Announce Type: new Abstract: Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into

While everyone’s displacing jobs, we’re creating them. A Hero for every family. @hellotohera’s favorite friend 83 year old Stanley Zareff dr…

While everyone’s displacing jobs, we’re creating them. A Hero for every family. @hellotohera’s favorite friend 83 year old Stanley Zareff dropped by our office to learn what being a Hero means and ann

tutorialslinus-lee--x

you may have heard that glm-5.2 at 280 token/s is cool, how about 318 and we still have room to go

tutorialsjeremy-howard--x

GLM-5.2 achieved token generation speeds of 318 tokens per second, surpassing the previously reported 280 tokens per second benchmark, with indications that further performance improvements are possib

A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input

arXiv:2505.14251v2 Announce Type: replace Abstract: We study the problem of differentially private second moment estimation and present a new algorithm that achieve strong privacy-utility trade-offs e

AI-powered BI with Snowflake and Amazon Quick

In this post, you will learn how to build an end-to-end integration between Snowflake semantic views and Amazon Quick. The sample data is user review data for a media company. You start by loading mov

tutorialsaws-ml-blog

Coordinate-Queryable Neural Field Reconstruction for EEG Spatial Super-Resolution with Unseen-Electrode Generation

arXiv:2606.23707v1 Announce Type: cross Abstract: EEG spatial super-resolution (EEGSR) in real deployments is challenged by random channel missingness, unstable electrode quality, and changing visible

Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation

arXiv:2606.18478v2 Announce Type: replace Abstract: Recent progress has shown promise in distilling multi-step video diffusion models into efficient few-step students. Among them, Distribution Matchin

Devin tests its work before you review the PR. You review and approve the test plan. Then get back a screen recording with a visual checklis…

Devin, an AI coding assistant, incorporates a testing workflow where it automatically tests its code changes before submitting pull requests for human review. The process involves the AI presenting it

tutorialscognition-ai--x

Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition

arXiv:2603.29578v2 Announce Type: replace Abstract: Facial Expression Recognition (FER) is essential for human-machine interaction, as it enables machines to interpret human emotions and internal stat

Entity Resolution via Batched Oracle Queries

arXiv:2606.24407v1 Announce Type: cross Abstract: We consider an oracle that processes a limited batch of records at a time and clusters those that refer to the same real-world entity. We study how to

Fast and Slow Variational Continual Learning

arXiv:2606.24007v1 Announce Type: cross Abstract: Continual learning remains a major challenge for modern deep networks, partly because commonly used optimizers lack inherent mechanisms for continual

Gartner® Reviews Specialty Cloud Providers, Recognizing Vultr

Gartner published a market guide analyzing specialty cloud providers, with Vultr receiving recognition in the assessment. The guide likely evaluates providers offering specialized cloud services beyon

tutorialsvultr

I (and a bunch of my colleagues) donated to this. I think it is a really excellent initiative. TLDR: - Equity investments in broad spectrum …

tutorialsjeremy-howard--x

I (and a bunch of my colleagues) donated to this. I think it is a really excellent initiative. TLDR: - Equity investments in broad spectrum preventatives that are ready to get to phase 2 within 4 year

I’m reading an old collection of interconnected science fiction stories by Jerry Pournelle, written in the early 70s. His best books were la…

I’m reading an old collection of interconnected science fiction stories by Jerry Pournelle, written in the early 70s. His best books were later co-authored with Larry Niven, but it is still solid work

tutorialselon-musk--x

Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation

arXiv:2606.24206v1 Announce Type: cross Abstract: Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain tw

Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts

arXiv:2405.19062v2 Announce Type: replace-cross Abstract: Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation

It was great to talk about the threat from superintelligence and its geopolitical implications with @FukuyamaFrancis. Thanks for hosting my …

It was great to talk about the threat from superintelligence and its geopolitical implications with @FukuyamaFrancis. Thanks for hosting my piece on how to prevent it and build a future where humanity

tutorialsconnor-leahy--x

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation

arXiv:2606.24849v1 Announce Type: cross Abstract: Unified multi-modal large language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware promp

Learn more about Computer for Counsel: https://www.perplexity.ai/enterprise/use-cases/legal

Computer for Counsel is an enterprise offering from Perplexity AI designed specifically for legal professionals and law firms to leverage AI-powered research and analysis capabilities. The solution li

tutorialsperplexity--x

MVG-KAN: Multi-View Geo-Wind Guided KAN for PM_{2.5} Forecasting

arXiv:2606.24347v1 Announce Type: new Abstract: Accurate short-term PM_{2.5} forecasting is important for public health protection, air-quality early warning, and urban environmental management. Howev

NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation

arXiv:2606.24450v1 Announce Type: cross Abstract: Perceiving physical contact is fundamental to dexterous manipulation. While robots often rely on dedicated hardware tactile sensors, humans exhibit a

PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought

arXiv:2606.24539v1 Announce Type: new Abstract: Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene

Predictive variational inference: Learn the predictively optimal posterior distribution

arXiv:2410.14843v4 Announce Type: replace-cross Abstract: Vanilla variational inference finds an optimal approximation to the Bayesian posterior distribution, but even the exact Bayesian posterior is

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

arXiv:2512.10244v2 Announce Type: replace Abstract: Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled

Task Decomposition for Efficient Annotation

arXiv:2606.24734v1 Announce Type: cross Abstract: High-quality annotations of structured representations are expensive to collect over large corpora. Manual annotation of structure is laborious, and m

Underpromise, overdeliver? Hands-on with the $24,950 Slate auto.

Slate Auto's Blank Slate is a stripped-down, two-seat electric pickup truck starting at $24,950, featuring a 65 kWh LFP battery pack with 205 miles of range and 181 horsepower. The vehicle achieves it

tutorialsars-technica

Watching Kyra and her family fight brain cancer — glioblastoma — over the last year has been inspiring, and heartrending, beyond belief. Now…

Watching Kyra and her family fight brain cancer — glioblastoma — over the last year has been inspiring, and heartrending, beyond belief. Now her endlessly proud father, @DavidPSamson, will continue th

tutorialsanthropic--x

Zero-Day Exploitation of Vulnerability (CVE-2026-20245) in Cisco Catalyst SD-WAN Manager

Written by: Chester Sng, Pete Boonyakarn, Logeswaran Nadarajan Introduction In early 2026, Mandiant identified a threat actor targeting SD-WAN infrastructure at a service provider. After gaining initi

tutorialsgoogle-cloud-ai

A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

arXiv:2602.14239v2 Announce Type: replace-cross Abstract: Predicting links in sparse, continuously evolving networks is a central challenge in network science. Conventional heuristic methods and deep

A large-scale foundation model enables simulation-to-real adaptation for nuclear magnetic resonance-based molecular structure analysis

arXiv:2606.20756v1 Announce Type: cross Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is a powerful tool for molecular structure analysis, and spectral artificial intelligence offers great p

Adaptive Recurrent Message Passing for Test Time Computing on Graphs

arXiv:2606.22462v1 Announce Type: new Abstract: Pre-trained foundation models have demonstrated remarkable success in many domains, enabling a unified backbone to generalize across diverse downstream

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

arXiv:2606.21736v1 Announce Type: new Abstract: Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain a

Asymmetric physics enables efficient learning in quadrupedal robot swarms

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

tutorialsarxiv-cs-ro

BASIL: Bayesian Application for Scientific Iteration and Learning

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

Bayesian Model Averaging under Predictor Redundancy via Density-Ratio Posterior Compression

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