All entries

From the description: 'Reasoning-Medical-27B is designed for universal advanced medical reasoning in professional medicine, medical genetics, college biology/medicine, and clinical knowledge. The mode

tutorialsr-localllama

MedLoCoMo: A Long-Context Multi-Session Medical Dialogue Benchmark for Large Language Models

DGX agent

arXiv:2607.22566v1 Announce Type: new Abstract: MedLoCoMo is a Medical Long-Context Memory benchmark for patient-specific clinical reasoning over multi-admission medical dialogue. Existing medical QA

model-releasesarxiv-cs-ai

28 Jul 2026

MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning

model-releasesarxiv-cs-lg

arXiv:2607.24314v1 Announce Type: new Abstract: Predicting the absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of small molecules remains a major challenge in drug disc

MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion

arXiv:2607.22696v1 Announce Type: cross Abstract: High-resolution video diffusion models built on Diffusion Transformers (DiTs) deliver strong fidelity but quickly exhaust the memory budget of a singl

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi

MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution

arXiv:2607.22832v1 Announce Type: new Abstract: Long-horizon embodied tasks require policies that execute many dependent actions before task success can be observed. Representing policies as executabl

safetyarxiv-cs-lg

MEMOIR: Temporal Behavioral Memory for Recommendation Across the Preference-Drift Spectrum

arXiv:2607.23986v1 Announce Type: cross Abstract: We propose MEMOIR, a framework that segments user interaction histories into temporal windows, generates semantic behavioral memory for each period us

researcharxiv-cs-cl

Local Ai

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

local-aiapple-ml-research

Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s most powerful on-device foundation model. This work presents th

Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers

model-releasesarxiv-cs-cl

arXiv:2607.23811v1 Announce Type: cross Abstract: Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple's most powerful

Tutorials

Memory for Attention: Language-Conditioned Re-Perception with a Vision--Language--Motion Map

arXiv:2607.23797v1 Announce Type: new Abstract: A robot carrying a persistent, behavior-annotated map faces two planning questions, and its memory answers only one well. The spatial-navigation questio

tutorialsarxiv-cs-ro

MemTX: Transactional Belief Commit for Stateful Agent Memory

arXiv:2607.23929v1 Announce Type: new Abstract: LLM agents increasingly coordinate through persistent shared memory: one agent's write becomes another agent's premise, and eventually a tool call with

MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation

arXiv:2607.23504v1 Announce Type: new Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to maintain long-horizon visual history for trajectory consistency wh

researcharxiv-cs-cv

Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting

model-releasesarxiv-cs-cv

arXiv:2607.22890v1 Announce Type: cross Abstract: Domain Randomization (DR) is a standard technique for closing the Sim-to-Real gap, yet traditional DR pipelines rely on classical computer graphics re

Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study

arXiv:2607.22984v1 Announce Type: cross Abstract: Machine learning models for clinical prediction tasks, such as in-hospital mortality and sepsis onset, routinely achieve high AUROC scores. However, A

researcharxiv-cs-lg

Metric Surface Reconstruction of Neurosurgical Scenes from Monocular Operating Microscope Images and Microscope Pose

arXiv:2607.22773v1 Announce Type: cross Abstract: Objective: We evaluated whether metric 3D geometry of neurosurgical operative exposure can be recovered from standard monocular operating-microscope i

researcharxiv-cs-cv

microsoft/Mage-VL · Hugging Face - An Efficient Codec-Native Streaming Multimodal Foundation Model

model-releasesr-localllama

Mage-VL is a codec-native, proactive-streaming multimodal foundation model for image and video understanding, whose visual encoder is trained entirely from scratch at a compact 4B scale. It targets a

Local Ai

microsoft/VibeVoice-ASR-BitNet

VibeVoice-ASR-BitNet is a compressed variant of VibeVoice-ASR optimized for real-time inference on edge CPUs — no GPU required. Through heterogeneous quantization, the model is compressed from 4.62 GB

local-air-localllama

Tutorials

MicroZoom: Structure-Preserving Detail Synthesis at Extreme Scale

arXiv:2607.24729v1 Announce Type: new Abstract: We introduce MicroZoom, a generative framework for gigapixel image synthesis at the microscopic scale. Given a standard photograph and a sparse set of c

tutorialsarxiv-cs-cv

Might need math+code benchmark for frontier model(LLMs Silently Replace Math)[D]

model-releasesr-machinelearning

Hello guys. I found some problems in current frontier models. And want to share. # math_code_hallucination > Record of a failure caused by combining mathematics and code in a single prompt. --- ## Cas

MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models

arXiv:2607.22556v1 Announce Type: new Abstract: Continual learning (CL) is essential for small language models (SLMs) to adapt to evolving real-world needs in resource-constrained deployments. However

MIME: Multimodal Interactive Motion Encoder

arXiv:2607.22702v1 Announce Type: new Abstract: Text-motion representation learning has advanced rapidly, with growing interest in multi person interactions for animation, AR/VR, and embodied AI. Thes

safetyarxiv-cs-cv

Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations

arXiv:2607.23012v1 Announce Type: new Abstract: During SGD training, the gradients often align strongly with the dominant subspace spanned by the top-k eigenvectors of the Hessian of the loss. While t

researcharxiv-cs-lg

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD

arXiv:2607.24235v1 Announce Type: cross Abstract: Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with num

researcharxiv-cs-lg

Applications

MINT-V2X: A Mobility-Integrated Network Trajectory Dataset for Predictive Resource Management

arXiv:2607.22654v1 Announce Type: new Abstract: Vehicle-to-Everything (V2X) communication systems are based on datasets that not only contain vehicle trajectory data but also wireless network paramete

applicationsarxiv-cs-ai

MioFFAn: an Annotation Software for Formula Formalization with LLM Automation Capabilities

arXiv:2607.22552v1 Announce Type: new Abstract: The automatic translation of mathematical expressions in scientific literature into executable symbolic code (a process we refer to as Formula Formaliza

researcharxiv-cs-cl

MiSS: A Logic-Driven Explanation of Minimal Sufficient Coalitions for Point Cloud Classifiers

arXiv:2607.24074v1 Announce Type: new Abstract: We present MiSS, a black-box, query-based framework for explaining 3D point cloud classifiers through perturbation-relative sufficiency reasoning. MiSS

Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric

arXiv:2607.23532v1 Announce Type: cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested e

Agents

@mitsuhiko Turns out the 'third-party provider' with the sandbox that was used for the attack was Modal, though they blame one of their cust…

@mitsuhiko Turns out the 'third-party provider' with the sandbox that was used for the attack was Modal, though they blame one of their customers for deploying an endpoint without authentication: http

agentssimon-willison--x

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models

arXiv:2607.23047v1 Announce Type: cross Abstract: Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing meth

Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

model-releasesarxiv-cs-cv

arXiv:2607.24407v1 Announce Type: new Abstract: Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and comp

ML-based Predictive Models for Power Consumption in Virtualised O-RANs

arXiv:2607.24256v1 Announce Type: cross Abstract: As communication networks adopt virtualized and disaggregated architectures, achieving energy efficiency has become increasingly important for both ec

MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models

arXiv:2607.22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with co

MMOE: Modernizing Diffusion Transformers with Efficient Expert Design

model-releasesarxiv-cs-cv

arXiv:2607.24665v1 Announce Type: new Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capa

Applications

mmSimPrior: Learning Simulation Priors for Data-Efficient Real-World Generalizable Radar-Based Human Motion Reconstruction

arXiv:2607.22973v1 Announce Type: new Abstract: Millimeter-wave (mmWave) radar offers privacy-preserving and lighting-robust sensing for human motion reconstruction, but learning models that generaliz

applicationsarxiv-cs-cv

MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing

arXiv:2607.24365v1 Announce Type: new Abstract: Autonomous fleets enable mobility platforms to coordinate idle vehicles directly, making fleet-wide rebalancing possible. However, two obstacles limit r

safetyarxiv-cs-lg

Model Predictive Planner for UAV Navigation in Non-Convex Air Corridors

arXiv:2607.24369v1 Announce Type: new Abstract: This work presents a motion planning framework for UAV navigation in non-convex urban air corridors. The planner is based on a mixed-integer tracking mo

researcharxiv-cs-ro

Modeling Memory-Dependent Reliability of LLMs: A Hidden Markov Model

arXiv:2607.22951v1 Announce Type: cross Abstract: Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified ope

MoE-Based Learned Inertial Odometry for Bicycle Localization

model-releasesarxiv-cs-ro

arXiv:2510.17604v2 Announce Type: replace Abstract: GNSS suffers from multipath errors in urban canyons, making reliable bicycle localization difficult. Hand-crafted inertial alternatives, such as cyc

Agents

MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

arXiv:2607.23511v1 Announce Type: new Abstract: End-to-end autonomous driving systems commonly follow a cascaded two-stage pipeline where a perception stage compresses multi-modal sensor inputs into a

agentsarxiv-cs-cv

MoLGE: Mixture of Language Group Experts for Efficient Scaling of Massively Multilingual Speech Recognition

model-releasesarxiv-cs-cl

arXiv:2607.24030v1 Announce Type: new Abstract: Massively multilingual automatic speech recognition (ASR) models covering hundreds of languages must maintain robust performance across diverse linguist

Monitoring Post-Disaster Urban Recovery Using High-Resolution SAR Time Series and Unsupervised Learning: Evidence from the 2023 Turkiye-Syria Earthquake

arXiv:2607.24180v1 Announce Type: cross Abstract: Monitoring post-disaster recovery is essential for understanding how urban systems rebuild and progressively return to functionality. However, trackin

Moral Hazard in Multi-Agent Language Models

arXiv:2607.23982v1 Announce Type: cross Abstract: Cooperation can fail when socially valuable effort is costly, weakly observable, and mainly benefits others. Drawing on Holmstrom's team moral-hazard

Moving-Horizon Estimation and Nonlinear Model Predictive Control of Cable-Driven Soft Manipulators

arXiv:2607.24029v1 Announce Type: new Abstract: Precise control of soft manipulators remains challenging due to the difficulty of developing accurate yet computationally tractable models for model-bas

researcharxiv-cs-ro

MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation

arXiv:2607.22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in gener

MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

arXiv:2607.23607v1 Announce Type: cross Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/

safetyarxiv-cs-cl

Applications

MSG-Loc: Multi-Label Likelihood-based Semantic Graph Matching for Object-Level Global Localization

arXiv:2512.03522v3 Announce Type: replace-cross Abstract: Robots are often required to localize in environments with unknown object classes and semantic ambiguity. However, when performing global loca

applicationsarxiv-cs-cv

MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction

arXiv:2607.24436v1 Announce Type: new Abstract: High-fidelity 3D generative modeling increasingly relies on the latent diffusion paradigm, where the reconstruction quality of the underlying 3D VAE bec

researcharxiv-cs-cv

MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents

arXiv:2607.23870v1 Announce Type: cross Abstract: Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follo