All entries

MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios

arXiv:2606.07669v1 Announce Type: cross Abstract: Deploying Video Anomaly Detection (VAD) in real-world surveillance faces a fundamental tension between the demand for high-level semantics to ensure e

local-aiarxiv-cs-ai

Agents

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory

DGX agent

arXiv:2606.07909v1 Announce Type: new Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long

agentsarxiv-cs-ai

9 Jun 2026

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

arXiv:2601.22859v3 Announce Type: replace-cross Abstract: The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bot

Mesh Graph Neural Network Framework for Accelerating Finite Element Simulation for Arbitrary Geometries

arXiv:2606.08287v1 Announce Type: new Abstract: Finite element analysis (FEA) is essential for structural design but remains computationally expensive, particularly when evaluating multiple design ite

researcharxiv-cs-lg

MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution

arXiv:2606.07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through ta

agentsarxiv-cs-ai

Industry

Microsoft AI chief walks back comments about AI taking over white-collar work

Microsoft AI head Mustafa Suleyman is walking back his statement about AI automating jobs done by white-collar workers, including lawyers, accountants, and project managers. During an episode of Decod

industrythe-verge-ai

Microsoft AI head calls out Anthropic for acting like Claude is conscious

model-releasesthe-verge-ai

Microsoft AI CEO Mustafa Suleyman says it's 'really, really dangerous' for Anthropic to speculate about Claude's consciousness inside its 'constitution,' or the instructions that tell the model how to

Tools

Migrating Your GitHub CI to Hugging Face Jobs

This article explains how to migrate continuous integration workflows from GitHub Actions to Hugging Face Jobs, likely covering the setup process, configuration differences, and benefits of using Hugg

toolshugging-face

MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation

arXiv:2606.09056v1 Announce Type: new Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames req

Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking

arXiv:2606.08253v1 Announce Type: cross Abstract: Enabling humanoid robots to operate in complex, dynamic environments remains a critical challenge, fundamentally limited by the ability to navigate ro

safetyarxiv-cs-lg

Minibatch Selection via Partition Matroid Constrained Gradient Matching

arXiv:2606.07954v1 Announce Type: cross Abstract: Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains

Applications

Minimal Solvers for Full-DoF Motion Estimation from Asynchronous Differential SfM

arXiv:2606.09218v1 Announce Type: new Abstract: As a bio-inspired intelligent sensor, event cameras have introduced a new paradigm in the intelligent perception of spatiotemporal information and visua

applicationsarxiv-cs-cv

MinNav: Minimalist Navigation Using Optical Flow For Active Tiny Aerial Robots

arXiv:2606.07813v1 Announce Type: cross Abstract: Navigation using a monocular camera is pivotal for autonomous operation on tiny aerial robots due to their perfect balance of versatility, cost and ac

agentsarxiv-cs-cv

MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets

arXiv:2606.07611v1 Announce Type: cross Abstract: This paper proposes an improved approach to the analysis of Mining Software Repositories (MSR) datasets via metadata enrichment, FAIRness assessment,

safetyarxiv-cs-ai

Mitigating Diffusion Model Hallucinations with Dynamic Guidance

arXiv:2510.05356v2 Announce Type: replace Abstract: Hallucinations in diffusion models are samples with structural inconsistencies that can emerge due to the excessive smoothing of the learned score f

Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization

arXiv:2606.07835v1 Announce Type: new Abstract: A fundamental tension exists in the large-step inference of diffusion models via their deterministic probability flow ordinary differential equation (PF

local-aiarxiv-cs-lg

Tutorials

MixReasoning: Switching Modes to Think

arXiv:2510.06052v2 Announce Type: replace Abstract: Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of

tutorialsarxiv-cs-ai

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

arXiv:2606.07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge. Whi

mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models

arXiv:2606.07531v1 Announce Type: cross Abstract: We introduce mllm-shap, an open-source Python framework designed to extend Shapley Value (SV) explainability from text-only Large Language Models to M

safetyarxiv-cs-ai

MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matryoshka Training Framework

arXiv:2606.07654v1 Announce Type: cross Abstract: Multi-vector visual document retrievers achieve strong fine-grained matching by representing each page with multiple vectors from deep Vision-Language

MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting

arXiv:2601.09085v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on

Tutorials

Mobility-Embedded POIs: Learning What A Place Is and How It Is Used from Human Movement

arXiv:2601.21149v3 Announce Type: replace-cross Abstract: Recent progress in geospatial foundation models highlights the importance of learning general-purpose representations for real-world locations

tutorialsarxiv-cs-ai

Model-Based Learning of Whittle indices

model-releasesarxiv-cs-lg

arXiv:2511.20397v2 Announce Type: replace Abstract: We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (M

Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices

arXiv:2606.07857v1 Announce Type: cross Abstract: The rise of edge-based machine learning has enabled distributed adaptation of language models across mobile and IoT devices, offering privacy preserva

Model Poisoning Against Federated Model Adaptation with Chain of Bit-Flips

arXiv:2606.09548v1 Announce Type: cross Abstract: Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility of

local-aiarxiv-cs-ai

Modeling Components and Connections in Cyber-Physical Systems

arXiv:2606.09645v1 Announce Type: new Abstract: Text based configuration files for cyber-physical systems show the hierarchy of component modules well but often hide the details of connections and int

researcharxiv-cs-ro

Applications

Modeling Stochastic Conditional Dynamics from Sparse Observations via Kernel-Stabilized Flow Matching

arXiv:2411.08314v5 Announce Type: replace Abstract: Learning to transform conditional probability densities over time is a fundamental challenge spanning probabilistic modeling and the natural science

applicationsarxiv-cs-lg

Applications

Modeling the Diachronic Evolution of Legal Norms: An LRMoo-Based, Component-Level, Event-Centric Approach to Legal Knowledge Graphs

arXiv:2506.07853v5 Announce Type: replace Abstract: Representing the temporal evolution of legal norms is a critical challenge for automated processing. While foundational frameworks exist, they lack

applicationsarxiv-cs-ai

MOLOT System Card: Malicious Operational Logic Observation Transformer

model-releasesarxiv-cs-lg

arXiv:2606.07792v1 Announce Type: cross Abstract: MOLOT (Malicious Operational Logic Observation Transformer) is a static malicious-code detection system designed for SAST setup where package metadata

Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization

arXiv:2606.08815v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for eliciting long-chain reasoning in large language models. Ho

safetyarxiv-cs-ai

Monday’s gains are Tuesday’s losses?

This post likely discusses the volatility and unpredictability of financial markets, examining whether gains achieved on one trading day are frequently reversed or lost the following day. Gary Marcus

safetygary-marcus--x

More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budget using Reset and Discard (ReD)

arXiv:2601.21522v2 Announce Type: replace-cross Abstract: The performance of large language models (LLMs) on verifiable tasks is usually measured by pass@k, the probability of answering a question cor

Tools

more charts of other tiers where its less stark including the vibe shift chart from https://x.com/swyx/status/2064081945567580323 here

more charts of other tiers where its less stark including the vibe shift chart from https://x.com/swyx/status/2064081945567580323 here It's finally out!!! @METR_Evals found that more than half of SWEB

toolsswyx--x

Industry

More details here: https://huggingface.co/blog/clem/arcee-hf

Arcee is a model or project shared through Hugging Face, likely involving machine learning or AI development. The blog post from Clem Delangue (Hugging Face CEO) provides detailed information about Ar

industryclem-delangue--x

More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs

arXiv:2606.08471v1 Announce Type: cross Abstract: Recently, language models have made rapid progress across various domains and applications. However, their capability for self-improvement, i.e., whet

MosaicIMU: Composing Carrier Experts for Generalizable Neural Inertial Odometry

arXiv:2606.09355v1 Announce Type: new Abstract: Robust inertial odometry is essential for various carriers when external sensing is unreliable. Learning-based methods reduce integration drift by captu

local-aiarxiv-cs-ro

MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

arXiv:2606.07639v1 Announce Type: cross Abstract: Video understanding is shifting from the offline paradigm -- taking a fully recorded video as input and producing a single answer after it ends -- tow

Motion planning for hundreds of floating robots

arXiv:2606.09620v1 Announce Type: new Abstract: Planning collision-free motion for large robot fleets is difficult because collision avoidance induces strong inter-agent coupling that grows rapidly wi

agentsarxiv-cs-ro

MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding

arXiv:2410.21747v2 Announce Type: replace Abstract: Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging re

MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model

arXiv:2606.08288v1 Announce Type: new Abstract: Vision-language-action (VLA) models increasingly condition robot policies on history, depth, or 4D features to resolve ambiguity in long-horizon manipul

researcharxiv-cs-ro

MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation

arXiv:2606.09215v1 Announce Type: new Abstract: World Action Models (WAMs) couple a video dynamics prior to the policy and have shown encouraging results on tabletop manipulation, but iterative denois

safetyarxiv-cs-ro

MS-COOT: Comparing Morse-Smale Complexes with Co-Optimal Transport

arXiv:2606.08258v1 Announce Type: cross Abstract: Understanding and comparing structures in scalar fields is a central challenge in scientific visualization, with applications ranging from feature ana

MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport

arXiv:2606.07578v1 Announce Type: new Abstract: This paper extends MST-Direct, a Matching-via-Sinkhorn-Transport approach for multivariate geostatistical simulation, from the original bivariate, uncon

researcharxiv-cs-lg

Hardware

MuJoCo-Drones-Gym: A GPU-Accelerated Multi-Drone Simulator for Control and Reinforcement Learning

arXiv:2606.08039v1 Announce Type: new Abstract: Robotic simulators are a cornerstone of modern research in aerial robotics, serving both as a vehicle for the development of new control algorithms and

hardwarearxiv-cs-ro

Multi-Armed Bandits with Arriving Arms: Sequential Screening, Dynamic Regret, and Sublinear Guarantees

model-releasesarxiv-cs-lg

arXiv:2606.09002v1 Announce Type: cross Abstract: We study a stochastic multi-armed bandit problem in which the set of available arms expands over time. This setting arises in sequential experimentati

Multi-planar 2D-U-Net Segmentation of 3D-CT Abdominal Organs augmented by Spatial Occurrence Maps

arXiv:2606.07717v1 Announce Type: cross Abstract: This work proposes a lightweight 2D-U-Net-based framework for segmenting five abdominal organs in large field-of-view 3D CT scans. The method combines

Multi-resolution Enhancement for Full Spectrum Neural Representations

arXiv:2509.15494v2 Announce Type: replace Abstract: Scientific data acquisition continues to outpace storage and analysis capabilities, making voxel-based representations increasingly intractable. Imp

researcharxiv-cs-lg

Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback

arXiv:2606.09748v1 Announce Type: new Abstract: Existing benchmarks for deep research agents (DRAs) assess only single-shot outputs, ignoring a key question: can DRAs improve their reports when guided

agentsarxiv-cs-ai