All entries

MeGAS: Thermomechanical Dynamic Gaussian Splatting for Thermophysical Scene Editing

arXiv:2606.23455v1 Announce Type: new Abstract: Recent advances integrate physically grounded Newtonian dynamics with neural rendering frameworks, narrowing the gap between photorealistic scene recons

Membrane-based Acoustic Microrobots

DGX agent

arXiv:2606.21047v1 Announce Type: new Abstract: Acoustic microrobots have emerged as a promising frontier for targeted drug delivery and minimally invasive medicine due to their high-power density and

researcharxiv-cs-ro

23 Jun 2026

Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory

arXiv:2606.23195v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade dur

Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering

arXiv:2606.21540v1 Announce Type: new Abstract: Graph convolutional networks (GCNs) have demonstrated significant success in capturing complex user-item relationships for collaborative filtering (CF).

MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation

arXiv:2606.20679v1 Announce Type: cross Abstract: Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observatio

safetyarxiv-cs-cv

Menlo raised 3B for funds dedicated to backing AI startups, its largest fundraising to date; sources say Menlo's Anthropic stake is currently worth nearly 14B (Natasha Mascarenhas/Bloomberg)

Natasha Mascarenhas / Bloomberg: Menlo raised 3B for funds dedicated to backing AI startups, its largest fundraising to date; sources say Menlo's Anthropic stake is currently worth nearly 14B — In 202

industrytechmeme

Mesh2GS: White-Box 3DGS Construction via Plenoptic Sampling

arXiv:2606.21898v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representati

MeshFlow: Mesh Generation with Equivariant Flow Matching

arXiv:2606.23489v1 Announce Type: cross Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important

Meta copied slot machines to addict kids to Instagram. Now Zuckerberg is turning his company into a prediction market. Meta’s business model…

Meta copied slot machines to addict kids to Instagram. Now Zuckerberg is turning his company into a prediction market. Meta’s business model is profiting from addiction—kids, gamblers, & more. Stop it

safetygary-marcus--x

Meta launches cheaper smart glasses without Ray-Ban

model-releasesthe-verge-ai

For the past three years, 'Meta' and 'Ray-Ban' have been synonymous in the smart glasses space. Not anymore. Yesterday, I slipped on several pairs of Meta Glasses - no Ray-Bans - in three different st

Meta-Reinforcement Learning via Evolution for Multi-Objective Combinatorial Supply Chain Optimisation

arXiv:2606.22146v1 Announce Type: new Abstract: Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environme

Meta ships first smart glasses powered by its Superintelligence Labs’ Muse Spark model

Meta Platforms Inc. today announced a partnership with EssilorLuxottica to launch a new lineup of artificial intelligence-powered smart glasses that can “see” the world and talk to users about it. Bui

industrysiliconangle

Meta's Starfire glasses with Kylie Jenner include a tiny gemstone on the lens, a metal nose pad to prevent absorbing makeup, and an AI version of Kylie's voice (Julian Chokkattu/Wired)

Julian Chokkattu / Wired: Meta's Starfire glasses with Kylie Jenner include a tiny gemstone on the lens, a metal nose pad to prevent absorbing makeup, and an AI version of Kylie's voice — The new Meta

industrytechmeme

Metric-Dependent Annotation Saturation for Learning from Label Distributions

researchapple-ml-research

When annotators disagree on a label, the disagreement itself carries signal—and the number of annotators needed to capture it depends on the evaluation metric. We fine-tune NLI models on label distrib

Micron and Sandisk led a tech selloff on Tuesday, falling more than 13%; Western Digital fell 8%, Marvell 9%, Seagate 5%, Qualcomm 8%, and Applied Materials 8% (Britney Nguyen/MarketWatch)

Britney Nguyen / MarketWatch: Micron and Sandisk led a tech selloff on Tuesday, falling more than 13%; Western Digital fell 8%, Marvell 9%, Seagate 5%, Qualcomm 8%, and Applied Materials 8% — One anal

industrytechmeme

MILE: A Mechanically Isomorphic Exoskeleton Data Collection System with Fingertip Visuotactile Sensing for Dexterous Manipulation

arXiv:2512.00324v3 Announce Type: replace-cross Abstract: Imitation learning provides a promising approach to dexterous hand manipulation, but its effectiveness is limited by the lack of large-scale,

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding

arXiv:2601.07298v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image r

Mind the Noise: Sensitivity of Transformer-based Interaction-Aware Trajectory Prediction Models to Noisy Data

arXiv:2606.21344v1 Announce Type: cross Abstract: Trajectory prediction allows autonomous vehicles to anticipate the future behavior of surrounding objects (or agents) and, accordingly, maximize the s

local-aiarxiv-cs-lg

Mind the Privileged-to-Camera Gap: Actor-Centric Sidecar Supervision for Camera-First Open-Loop Waypoint Prediction

arXiv:2606.20772v1 Announce Type: new Abstract: Camera-first autonomous-driving models predict future ego waypoints from images, ego-state features, and route commands, but waypoint supervision alone

safetyarxiv-cs-ro

Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy

arXiv:2606.23096v1 Announce Type: new Abstract: Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a elta-ex

Minimus opens its entire secure container image catalog to developers for free

Container image startup Minimus Inc. today announced that it’s removing the registration wall on its entire catalog of secure container images, making the full library free to any developer. The compa

industrysiliconangle

Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection

arXiv:2606.20752v1 Announce Type: new Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent stu

MIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents

arXiv:2606.20717v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inheren

local-aiarxiv-cs-cv

Tutorials

MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions for Fine-Grained Vision-Language Learning

arXiv:2606.21419v1 Announce Type: new Abstract: Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance

tutorialsarxiv-cs-cv

Misleading branding works well

Misleading branding works well Naming it USAID was brilliant honestly because most people are too dumb to even ask what it really does It’s like naming something “Save the Orphan Puppies Org” - what d

industryelon-musk--x

Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages (Mistral AI Blog)

Mistral AI Blog: Mistral debuts OCR 4, a model featuring structured document extraction with bounding boxes, block classification, and inline confidence scores, in 170 languages — Today, we're releasi

model-releasestechmeme

Mitigating Cross-Image Information Leakage in Multi-Image Understanding with Large Vision-Language Models

arXiv:2508.13744v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) exhibit strong performance on single-image tasks. However, their performance degrades significantly when handli

Mitigating Measurement-Induced Training Instability in Hybrid Quantum Neural Networks for Protein Classification

arXiv:2606.22551v1 Announce Type: cross Abstract: Hybrid Quantum Neural Network (QNN) classifiers produce logits as expectation values of quantum measurement operators. For standard Pauli measurements

Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection

arXiv:2501.03432v3 Announce Type: replace Abstract: The Large Hadron Collider at CERN produces immense volumes of complex data from high-energy particle collisions, demanding sophisticated analytical

mlx-vis: GPU-Native Dimensionality Reduction on Apple Silicon

arXiv:2603.04035v4 Announce Type: replace Abstract: Dimensionality reduction is a foundational tool for visualizing high-dimensional data, yet its reference implementations span a fragmented stack of

local-aiarxiv-cs-lg

MMGist: A Comprehensive Multimodal Benchmark for 2027

arXiv:2606.22437v1 Announce Type: new Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and

MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction

arXiv:2606.20906v1 Announce Type: new Abstract: Molecular message-passing neural networks commonly propagate chemically diverse interactions through a single graph, which may mix interaction-specific

MMOU: A Massive Multi-Task Omni Understanding and Reasoning Benchmark for Long and Complex Real-World Videos

arXiv:2603.14145v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However,

Agents

Model council as a tool to push performance definitely works, I think the interesting next frontier is trying to scale this at the agent lev…

Model council as a tool to push performance definitely works, I think the interesting next frontier is trying to scale this at the agent level have been thinking a bunch about model routing and relate

agentsharrison-chase--x

Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

arXiv:2505.12462v3 Announce Type: replace Abstract: Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment

Model Inversion meets Cryptographic Fuzzy Extractors

arXiv:2510.25687v3 Announce Type: replace-cross Abstract: Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models. For example, face auth

Model Merging in the Essential Subspace

model-releasesarxiv-cs-lg

arXiv:2602.20208v2 Announce Type: replace Abstract: Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model

Modular Diffusion Models for Structured Visual Recognition

arXiv:2606.22702v1 Announce Type: new Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often pr

local-aiarxiv-cs-cv

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

arXiv:2606.21943v1 Announce Type: new Abstract: Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a nar

MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts

arXiv:2606.21033v1 Announce Type: cross Abstract: Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific

MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis

arXiv:2212.04495v3 Announce Type: replace Abstract: Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality.

Agents

Momentic raises the bar for software testing with agentic quality platform

Artificial intelligence-powered software testing and quality assurance platform Momentic Inc. today announced a major update to its service focused on verification in the AI coding era, enabling teams

agentssiliconangle

MOOZY: A Patient-First Foundation Model for Computational Pathology

arXiv:2603.27048v3 Announce Type: replace Abstract: Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain l

Applications

More on Leadership, Lab, and Crowd: https://www.oneusefulthing.org/p/making-ai-work-leadership-lab-and

applicationsethan-mollick--x

This post from Ethan Mollick likely explores how organizations can effectively implement AI through three key dimensions: leadership approaches to AI adoption, lab-based experimentation and testing, a

Agents

More on the /learn command: https://hermes-agent.nousresearch.com/docs/user-guide/features/skills#learning-a-skill-from-sources-learn

The /learn command in Hermes Agent enables users to teach the system new skills by providing source materials or documentation, allowing the agent to acquire and integrate custom knowledge for improve

agentsnous-research--x

More riddles for @RoKhanna. The President of El Salvador came to the same conclusion as DOGE and celebrated the shutdown of USAID. Are you a…

More riddles for @RoKhanna. The President of El Salvador came to the same conclusion as DOGE and celebrated the shutdown of USAID. Are you accusing the President who reduced his country’s murder rate

industryelon-musk--x

MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS

model-releasesarxiv-cs-lg

arXiv:2606.23603v1 Announce Type: new Abstract: Unhealthy dietary behavior continues to be a persistent public health issue in the United States, exacerbated by recommendation systems that prioritize

Morphology-Aware Multimodal Representation Learning for Insect Phylogenetic Reconstruction

arXiv:2606.22077v1 Announce Type: new Abstract: Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches ha