All entries

HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks

arXiv:2606.30516v1 Announce Type: new Abstract: Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic

Model Releases

Have your agent record video demos of its work with shot-scraper video

DGX agent

shot-scraper video is a new command introduced in today's shot-scraper 1.10 release which accepts a storyboard.yml file defining a routine to run against a web application and uses Playwright to recor

model-releasessimon-willison

30 Jun 2026

Local Ai

HDDPM: Heteroscedastic Denoising Diffusion Probabilistic Model for Quantitative Low-Count Brain PET Recovery

arXiv:2606.28513v1 Announce Type: cross Abstract: Positron emission tomography (PET) seeks to balance diagnostic quality with ra-diation dose. Low-count PET noise is non-Gaussian, non-stationary, and

local-aiarxiv-cs-ai

He3-Seeker: Robotic Information Planning for Lunar Helium-3 Distribution Mapping

arXiv:2606.28746v1 Announce Type: new Abstract: Lunar helium-3 is a highly valuable strategic resource, pivotal to the advancement of both deep-space exploration and space mining. Existing lunar heliu

agentsarxiv-cs-ro

Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns

arXiv:2606.30037v1 Announce Type: new Abstract: In a deep forecasting pipeline for fat-tailed financial returns at short horizons, which matters more - the backbone architecture or the output head? We

researcharxiv-cs-lg

HEARTS: Benchmarking LLM Reasoning on Health Time Series

arXiv:2603.06638v3 Announce Type: replace-cross Abstract: The rise of large language models (LLMs) has shifted time series analysis from narrow analytics to general-purpose reasoning. Yet, existing be

Hermes Agent now reads the web up to 60x faster and 49x cheaper. Scraping backends pass clean content straight to the agent without redundan…

Hermes Agent now reads the web up to 60x faster and 49x cheaper. Scraping backends pass clean content straight to the agent without redundant processing steps; large pages are saved locally and paged

agentsnous-research--x

HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data

arXiv:2606.29784v1 Announce Type: cross Abstract: Reliable generative AI models critically rely on expert human annotations to evaluate output quality, yet these 'gold' labels are expensive to collect

He's an adjudicated rapist, and SCOTUS knows it. He fomented an insurrection, and Jack Smith knows it. He botched a pandemic, and Dr Fauci k…

He's an adjudicated rapist, and SCOTUS knows it. He fomented an insurrection, and Jack Smith knows it. He botched a pandemic, and Dr Fauci knows it. He has committed every type of fraud known to man,

researchyann-lecun--x

Heterogeneous Tactile Transformer

model-releasesarxiv-cs-ro

arXiv:2606.29948v1 Announce Type: new Abstract: Tactile sensors are inherently heterogeneous: a model trained on one sensor cannot be directly used on another, which limits learning contact-rich manip

HiAP: A Multi-Granular Stochastic Auto-Pruning Framework for Vision Transformers

arXiv:2603.12222v2 Announce Type: replace Abstract: Vision Transformers require significant computational resources and memory bandwidth, severely limiting their deployment on resource-constraint hard

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

arXiv:2606.29126v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat

Applications

HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting

arXiv:2512.07854v2 Announce Type: replace Abstract: Traffic forecasting task is significant to modern urban management. Recently, there is growing attention on large-scale forecasting, as it better re

applicationsarxiv-cs-lg

Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization

arXiv:2606.28764v1 Announce Type: new Abstract: Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageabl

safetyarxiv-cs-lg

Hierarchical Experimentalist Agents

arXiv:2606.29315v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on parametr

Hierarchical Policy Learning via Spectral Decomposition

arXiv:2606.29570v1 Announce Type: new Abstract: In this paper, we identify a semantic decomposition in robot action sequences, separating task-level motion intent from execution-level refinements. By

safetyarxiv-cs-ro

Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts

arXiv:2606.30092v1 Announce Type: new Abstract: Real-time strategy (RTS) games present significant AI challenges, characterized by expansive state-action spaces arising from multi-unit coordination in

researcharxiv-cs-ai

High-Dimensional Concentration and Retrieval Instability in Embedding Spaces: Implications for Retrieval-Augmented Generation

arXiv:2606.28330v1 Announce Type: cross Abstract: Embedding-based retrieval systems rely on the assumption that geometric proximity in highdimensional representation spaces reflects semantic relevance

High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator

arXiv:2602.13416v2 Announce Type: replace Abstract: The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating

researcharxiv-cs-lg

High-Resolution Flood Mapping With Sentinel-1 and Sentinel-2 via Misalignment-Robust Cross-Sensor Learning and Generative Despeckling

arXiv:2606.30511v1 Announce Type: new Abstract: Reliable high-resolution flood extent mapping from satellite imagery remains constrained by limited data fidelity and sensor-specific artifacts. Multisp

Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions

arXiv:2606.30310v1 Announce Type: cross Abstract: The Sliced Wasserstein (SW) distance has emerged as a computationally attractive alternative to the Wasserstein distance by leveraging one-dimensional

researcharxiv-cs-lg

HippoSpark: An On-Demand Experience System for LLM Reasoning

arXiv:2606.29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research. However,

researcharxiv-cs-ai

HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

arXiv:2606.29333v1 Announce Type: new Abstract: Uncalibrated volumetric video streaming for human reconstruction is essential for holographic communication and AR/VR, yet remains challenging due to th

Applications

HiRes: A Hierarchical Cascaded Method for Resistor Value Identification

arXiv:2606.30179v1 Announce Type: new Abstract: Accurate identification of resistor values from unconstrained images remains a challenging computer vision task due to variations in lighting, orientati

applicationsarxiv-cs-cv

HJ-SafeDMP: Hamilton-Jacobi Reachability-Guided Dynamic Movement Primitives for Provably Safe Robot Motion

arXiv:2606.28995v1 Announce Type: new Abstract: Robots deployed in safety-critical environments must execute motions that are simultaneously robust to disturbances and provably safe from collisions. D

safetyarxiv-cs-ro

Local Ai

HKVLM: Faithful Reasoning Grounding by Binding Language Queries to a Frozen Detector

arXiv:2606.28862v1 Announce Type: new Abstract: Many visual requests -- ``the object to open this bottle'', ``the person not wearing a helmet'' -- require reasoning, not just category matching. Pure o

local-aiarxiv-cs-cv

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

arXiv:2606.28349v1 Announce Type: cross Abstract: Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction

agentsarxiv-cs-ai

HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor Scenes

arXiv:2606.29828v1 Announce Type: new Abstract: Recently, zero-shot object customization generation methods have rapidly developed and shown tremendous potential for applications. For instance, in the

HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformers

arXiv:2606.29095v1 Announce Type: new Abstract: Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short cl

Industry

Hotels, tour operators, and travel agencies rush to launch proprietary online tools and loyalty schemes to fend off future competition from AI travel agents (Stephanie Stacey/Financial Times)

Stephanie Stacey / Financial Times: Hotels, tour operators, and travel agencies rush to launch proprietary online tools and loyalty schemes to fend off future competition from AI travel agents — Chatb

industrytechmeme

How AI settled the complexity of the oldest SGD algorithm

arXiv:2606.29593v1 Announce Type: cross Abstract: In 1937, Stefan Kaczmarz proposed a simple algorithm for solving systems of linear equations. This algorithm turned out to be the earliest known examp

How Anthropomorphic Language Impacts Public Perceptions of AI

arXiv:2606.29121v1 Announce Type: cross Abstract: Public discourse about artificial intelligence (AI) often uses anthropomorphic language: language that attributes human capabilities and characteristi

How ChatGPT adoption has expanded

ChatGPT adoption has grown significantly since its launch, expanding across diverse user demographics, industries, and use cases globally. OpenAI's analysis likely covers metrics such as user growth,

model-releasesopenai

How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation

arXiv:2606.28358v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external docume

how do you run agent code without a full blown sandbox? we did a lot of work to harden the code interpreter runtime we use

Harrison Chase discusses techniques for executing agent code safely without requiring a complete sandbox environment, highlighting hardening measures implemented in their code interpreter runtime. The

agentsharrison-chase--x

How Far Can Sharpness and Complexity Jointly Explain Generalization?

model-releasesarxiv-cs-lg

arXiv:2606.29043v1 Announce Type: new Abstract: Sharpness and complexity are two central factors in the generalization analysis of deep neural networks. Existing quantitative evaluations of generaliza

How Far Can You Get Without a GPU? A Systematic Benchmark of Lightweight Hallucination Detection Across Question Answering, Dialogue, and Summarisation

arXiv:2606.29809v1 Announce Type: cross Abstract: Hallucination detection has become a pressing requirement for trustworthy AI deployment at scale. The most accurate detection methods depend on GPU-in

How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD

model-releasesarxiv-cs-cl

arXiv:2606.29733v1 Announce Type: new Abstract: Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and whic

Hardware

How Jaiveer Singh Is Helping Robots — and Developers — Move Faster

When Jaiveer Singh talks about robots, he doesn’t begin with spectacle. He begins with infrastructure: the boards inside machines, the software that lets developers see through a robot’s cameras and t

hardwarenvidia-blog

How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning

model-releasesarxiv-cs-cl

arXiv:2606.29672v1 Announce Type: new Abstract: Evaluating the originality of visual images poses enduring challenges for creativity assessment. Automated scoring using AI models has proven effective

How Much Due Diligence Before You Bid? Learning in Intractable Takeover Auctions

arXiv:2606.29457v1 Announce Type: new Abstract: When two companies bid to buy the same target, no one knows exactly what the target is worth. Each bidder pays for due diligence: costly, imperfect home

researcharxiv-cs-ai

How much of an LLM-generated clinical corpus is actually new? A production-scale measurement of content redundancy for provenance classification

model-releasesarxiv-cs-cl

arXiv:2606.29605v1 Announce Type: new Abstract: Clinical machine learning increasingly relies on training corpora generated by large language models (LLMs) rather than annotated by clinicians, and suc

Hardware

How NVIDIA’s Inference Software Stack Powers the Lowest Token Cost

As organizations move from AI pilots to production AI factories, infrastructure decisions have shifted from peak chip specifications to cost per token: how many useful tokens they can deliver per doll

hardwarenvidia-blog

Hardware

How Outpost VFX Uses AWS to Accelerate AI Model Training for Visual Effects

In this post, we explore how Outpost VFX achieved 8x faster training speeds using AWS infrastructure to transform their face replacement workflow, the technical architecture they implemented to overco

hardwareaws-ml-blog

How Schrödinger sped up molecular discovery by 4x with Alphaevolve

model-releasesgoogle-cloud-ai

Computational chemistry researchers have traditionally faced a frustrating trade-off when simulating molecular interactions: use fast classical force fields that sacrifice precision or rely on accurat

How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position

arXiv:2606.15032v2 Announce Type: replace Abstract: World models have become a central abstraction in modern AI. The term now refers to several different objects: action-conditioned environment models

safetyarxiv-cs-lg

Industry

How Spain's LaLiga uses nationwide IP blocking to combat illegal sports streams, impacting an estimated 550K+ domains, putting it in conflict with Cloudflare (Bloomberg)

Bloomberg: How Spain's LaLiga uses nationwide IP blocking to combat illegal sports streams, impacting an estimated 550K+ domains, putting it in conflict with Cloudflare — From small businesses to gove

industrytechmeme

Local Ai

How to Leverage Synthetic Speech for LLM-Based ASR Systems?

arXiv:2606.29031v1 Announce Type: cross Abstract: In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from mo

local-aiarxiv-cs-ai