All entries

GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation

arXiv:2606.07526v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong potential for recommendation (LLMRec) due to their powerful reasoning and generalization abilities. How

Research

GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priors

DGX agent

arXiv:2606.08440v1 Announce Type: cross Abstract: Robotic grasping is a fundamental capability in robotic manipulation. Yet grasping remains challenging under partial observations. Reliable grasping d

researcharxiv-cs-cv

9 Jun 2026

Gravity-guided Contact Dynamics Estimation from 3D Human Motions

arXiv:2606.08133v1 Announce Type: new Abstract: Ground contact forces acting on the human body, are crucial for biomechanics studies or sport performance analysis. Prior methods rely on force plates o

researcharxiv-cs-cv

GRPO Does Not Close the Multi-Agent Coordination Gap

model-releasesarxiv-cs-lg

arXiv:2606.07845v1 Announce Type: cross Abstract: We measure how well current large language models coordinate as multiple agents sharing a common resource, using the dining philosophers problem as a

Guided Discovery of New Behaviors using Diffusion Policies

arXiv:2606.08743v1 Announce Type: new Abstract: Diffusion models have become a powerful tool for generative modeling in robotics, with diffusion policies excelling at modeling multimodal action-trajec

safetyarxiv-cs-ro

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

arXiv:2606.08014v1 Announce Type: cross Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications. Recent advancements leverage multiple pre-trained f

HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions

arXiv:2503.14229v4 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded envi

HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling

arXiv:2606.08302v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. How

researcharxiv-cs-cv

Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics

arXiv:2606.08417v1 Announce Type: cross Abstract: Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling. Progress in both

Hands-free first notice of loss: Using Strands Agents and Amazon Bedrock AgentCore Browser Tool for intelligent claims intake

In this post, we demonstrate how a hands-free FNOL intake system combines agents built with the Strands Agents SDK for domain reasoning with Amazon Bedrock AgentCore Browser Tool for live portal inter

industryaws-ml-blog

Agents

Happy to present that terminal tool calls will be in prettified markdown codeblocks now if you have display tool calls enabled in Hermes Age…

Nous Research announced an enhancement to their Hermes AI model where terminal tool calls will now be displayed in formatted markdown codeblocks when the display tool calls feature is enabled. This im

agentsnous-research--x

HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning

arXiv:2606.08610v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

arXiv:2606.08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1

Hardware

Hardware-aware Low-latency Quantum Compilation with Data-driven Lightweight Error Detection for Early Fault-Tolerant Systems

arXiv:2606.07666v1 Announce Type: cross Abstract: Noisy intermediate-scale quantum (NISQ) processors are entering an early fault-tolerance regime where full quantum error correction carries prohibitiv

hardwarearxiv-cs-lg

Harmonia: End-to-End RAG Serving Optimization

arXiv:2505.07833v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) improves the reliability of large language models by integrating external knowledge, but serving RAG pipe

Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer

arXiv:2606.09416v1 Announce Type: cross Abstract: Robot middleware faces a new role in the era of Physical AI. Learned policies, planners, and vision-language-action (VLA) models now enter deployed ro

Harnessing Streaming Video in the Wild

model-releasesarxiv-cs-cv

arXiv:2606.08615v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentar

HARP: Efficient Data Selection for Finetuning Large Language Models

arXiv:2606.07690v1 Announce Type: cross Abstract: Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repea

HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning

arXiv:2606.07621v1 Announce Type: cross Abstract: Edge services increasingly use federated learning to personalize on-device models while keeping sensitive data local. In practice, deployments must ha

Applications

Have I Solved This Before? Retrieving Similar Segmentation Problems for Evolutionary Learning

arXiv:2606.08155v1 Announce Type: new Abstract: Reliable integration and solid configuration of monitoring systems constitute a fundamental prerequisites for achieving high efficiency and productivity

applicationsarxiv-cs-lg

Hardware

Haven't seen much about the Nvidia Cosmos 3 video model that dropped, what's up with that?

hardwarer-stablediffusion

Nvidia Cosmos 3 is an open physical AI foundation model built on a mixture-of-transformers architecture that combines vision reasoning, world generation, and action prediction for reasoning, simulatio

HDRAgent: An Agentic Framework for Multi-Exposure HDR Imaging

arXiv:2606.09110v1 Announce Type: new Abstract: Most existing multi-exposure HDR methods follow a fixed feed-forward reconstruction paradigm, making them prone to ghosting artifacts in complex dynamic

safetyarxiv-cs-cv

HDSL: A Hierarchical Domain-Specific Language for Structured 3D Indoor Scene Generation and Localized Editing with LLM Agents

model-releasesarxiv-cs-cv

arXiv:2606.09738v1 Announce Type: new Abstract: Text-driven indoor scene generation and editing require an intermediate representation that language models can both produce and revise. Existing LLM-ba

Here's Audi's next Q7 SUV and US-only SQ7, now with an RS V8

Audi introduced a redesigned Q7 SUV lineup for 2026, with the SQ7 performance variant powered by a 4.0-liter biturbo V8 engine producing up to 500 HP. The SQ7 features S-specific exterior styling and

industryars-technica

Applications

Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks

arXiv:2606.08978v1 Announce Type: new Abstract: Hypergraph knowledge distillation aims to retain the predictive performance of a hypergraph neural network (HNN) teacher while reducing inference costs

applicationsarxiv-cs-lg

Hey Siri, meet AI

This article likely discusses Apple's integration of AI capabilities into Siri, its virtual assistant, covering updates to Siri's functionality, intelligence, or how it compares to other AI assistants

industryben-s-bites

HF has been an amazing partner since day one, so this was easy. As we’ve grown from a post-training shop into a full model lab, @huggingface…

HF has been an amazing partner since day one, so this was easy. As we’ve grown from a post-training shop into a full model lab, @huggingface is the obvious partner to scale the infra open models deman

industryclem-delangue--x

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

arXiv:2606.08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-

Hierarchical Projection for Adaptive Knowledge Transfer

arXiv:2606.08691v1 Announce Type: new Abstract: Modern data-driven applications increasingly involve learning from multiple heterogeneous sources, where a target dataset is limited but related informa

safetyarxiv-cs-lg

High Effort handles your most complex builds with ease on Replit. Now powered by Claude Fable 5. 25% off for the next 7 days.

Replit's High Effort feature is designed to handle complex software builds and projects, and is now powered by Claude Fable 5 for improved performance. The announcement includes a promotional offer of

model-releasesreplit--x

High-severity vulnerability in Linux caused by a single faulty character

CVE-2026-23111 is a use-after-free vulnerability in Linux's nf_tables packet-filtering subsystem caused by a single inverted character that allows unprivileged local users to escalate privileges to ro

industryars-technica

HiMat: DiT-based Ultra-High Resolution SVBRDF Generation

arXiv:2508.07011v5 Announce Type: replace Abstract: Creating ultra-high-resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, t

safetyarxiv-cs-cv

Agents

How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces

This article describes how an AI agent was used to create a 3D virtual gallery of Paris by chaining together two Hugging Face Spaces applications. It demonstrates a practical example of using agents t

agentshugging-face

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs

arXiv:2601.06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also kn

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs

arXiv:2606.08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are

How engineers at Nextdoor use Codex to build without limits

Nextdoor engineers leverage OpenAI's Codex to accelerate software development and reduce coding constraints, enabling faster feature implementation and improved developer productivity. The case study

model-releasesopenai

How Hyper-Datafication Impacts the Sustainability Costs in Frontier AI

arXiv:2602.00056v4 Announce Type: replace-cross Abstract: Large-scale data has fuelled the success of frontier artificial intelligence (AI) models over the past decade. This expansion has relied on su

How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects

arXiv:2606.08777v1 Announce Type: cross Abstract: Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a p

How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap

model-releasesarxiv-cs-lg

arXiv:2606.08594v1 Announce Type: new Abstract: Deep learning EEG denoising architectures have scaled from tens of thousands to tens of millions of parameters, yet no prior study has isolated model ca

How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers in Hybrid Long-Context Models

arXiv:2606.07703v1 Announce Type: cross Abstract: Long-context prefill remains expensive because full/GQA layers still score the historical sequence, even in hybrid models with local, sparse, linear,

How Much MRI Preprocessing Is Enough? A Cost-Utility Study for Brain MRI Foundation Models

arXiv:2606.08164v1 Announce Type: new Abstract: MRI preprocessing defines the input distribution seen by brain MRI foundation models, yet it is usually treated as routine data cleaning rather than a m

researcharxiv-cs-cv

How Reliable are Fairness Audits with Unreliable Data?

arXiv:2506.23033v2 Announce Type: replace Abstract: Fairness audits are a key component of responsible machine-learning deployment. Yet, the reliability of audit recommendations under incomplete prote

safetyarxiv-cs-lg

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

arXiv:2606.08051v1 Announce Type: new Abstract: Financial transaction processing requires extracting structured merchant information from noisy, abbreviated bank transaction strings at scale. Our curr

Agents

How to detect credential theft in AI agent harness traces

In May 2026, a malicious version of a popular VS Code extension spent 18 minutes in the marketplace before anyone caught it. In that time it ran on roughly 6,000... The post How to detect credential t

agentsarize-ai

Tutorials

How to unlock true ROI in software development – a deep dive into the latest DORA research

How do you prove the business value of generative AI to your teams? Technology and finance leaders need to show the clear business value of AI projects to secure ongoing funding. While measuring retur

tutorialsgoogle-cloud-ai

Tutorials

How to use Row-Bot to turn unread emails into a daily action plan

Row-Bot is a local-first desktop AI assistant that can check emails and integrate multiple tools in a single conversation turn . The application includes integrated tools, a personal knowledge graph,

tutorialsr-ollama

How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing

arXiv:2603.13259v2 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two path

How Well Do Latent World Models Understand Partially Observable Safety Constraints?

arXiv:2510.06492v2 Announce Type: replace Abstract: Latent world models are a promising approach for learning state representations and dynamics directly from high-dimensional observations, enabling r

safetyarxiv-cs-ro