All entries

MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection

arXiv:2608.09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a real

Made by Google 2026: all the Pixel news and announcements

DGX agent

Google has revealed a bunch of new Pixel devices ahead of its Made by Google event. The colorful Pixel 11 lineup comes with upgraded cameras and performance, with the Pro models offering a built-in LE

model-releasesthe-verge-ai

11 Aug 2026

MAGIC-SSCIL: Manifold Anchoring and Geometric Incremental Calibration for Semi-Supervised Class Incremental Learning

arXiv:2608.07586v1 Announce Type: new Abstract: Semi-supervised Class Incremental Learning (SSCIL) is a severe challenge for neural networks, and it is hardest in the exemplar-free setting where no pa

safetyarxiv-cs-cv

'Many Are My Names': The Anatomy of the Assistant and Its Personas via Sparse Autoencoders

arXiv:2608.07852v1 Announce Type: new Abstract: How a language model internally represents who is speaking, the Assistant, an assigned roleplay persona, or a narrated story character, remains underexp

researcharxiv-cs-cl

MARA: Flow-Matching-Guided Multi-Agent Resource Allocation for Computational Resource Efficient Learning

arXiv:2608.09130v1 Announce Type: cross Abstract: Allocating limited computation among concurrent learning tasks is difficult when each task must reach a target loss before a deadline but its required

Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking

model-releasesarxiv-cs-cv

arXiv:2608.09613v1 Announce Type: new Abstract: Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacki

MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures

arXiv:2608.07556v1 Announce Type: cross Abstract: Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original a

Applications

Mask-aware inference with State-Space Models

arXiv:2603.04568v2 Announce Type: replace Abstract: Many real-world computer vision tasks, such as depth completion, must handle inputs with arbitrarily shaped regions of missing or invalid data. For

applicationsarxiv-cs-cv

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training

arXiv:2604.01499v2 Announce Type: replace Abstract: Evolution Strategies (ES) have emerged as a scalable gradient-free alternative to reinforcement learning based LLM fine-tuning, but it remains uncle

Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation

arXiv:2608.08176v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves the reasoning abilities of LLMs by internalizing privileged context into model parameters through self-disti

MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Multimodal Educational Tasks

arXiv:2507.03162v2 Announce Type: replace-cross Abstract: The rapid advancement of Large Language Models (LLMs) has transformed various domains, particularly computer science (CS) education. These mod

Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation Capabilities

arXiv:2608.08964v1 Announce Type: new Abstract: The generation of mathematically precise diagrams from tex- tual prompts has emerged as a critical yet underexplored capability of Large Language Models

MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language Models

arXiv:2608.08503v1 Announce Type: new Abstract: Mathematical reasoning remains challenging in low-resource languages such as Bangla. We study whether teacher-generated Bangla Chain-of-Thought (CoT) su

Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks

arXiv:2403.10232v2 Announce Type: replace-cross Abstract: Conventional matrix completion methods approximate the missing values by assuming the matrix to be low-rank, which leads to a linear approxima

researcharxiv-cs-lg

Matrix-free Neural Preconditioner for the Dirac Operator in Lattice Gauge Theory

arXiv:2509.10378v2 Announce Type: replace-cross Abstract: Linear systems arise in generating samples and in calculating observables in lattice quantum chromodynamics~(QCD). Solving the Hermitian posit

Matryoshka Language Model Suites

arXiv:2608.09703v1 Announce Type: new Abstract: Training a language model suite classically requires training each model separately and serving them independently. We improve both training and inferen

Mawqif-v2: An Arabic Benchmark Dataset for Cross-Target Stance Detection

arXiv:2608.09539v1 Announce Type: new Abstract: Publicly available Arabic datasets for target-specific stance detection remain limited, particularly for evaluating cross-target generalization. This pa

Tutorials

MaxModShift: Model Privacy via Designed Shifts

arXiv:2608.09328v1 Announce Type: new Abstract: Model learning by an eavesdropper is treated as an estimation problem in a federated environment. The Fisher Information Matrix for the eavesdropper's e

tutorialsarxiv-cs-lg

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks

arXiv:2507.19634v4 Announce Type: replace-cross Abstract: Recent advances in large language models have laid the foundation for multimodal LLMs (MLLMs), which unify text, speech, and vision within a s

MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

arXiv:2608.09588v1 Announce Type: new Abstract: Traditional Text-to-SQL research and benchmarks assume a known target database, overlooking settings in which a query must be routed within a large, het

researcharxiv-cs-cl

Applications

MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution

arXiv:2608.09405v1 Announce Type: new Abstract: Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods

applicationsarxiv-cs-cv

Measuring and Reducing WebGPU Dispatch Overhead for LLM Inference

arXiv:2608.08730v1 Announce Type: new Abstract: Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platfo

researcharxiv-cs-lg

Measuring the Tokenization Premium: A Cost Audit for Underserved Language Communities

arXiv:2608.09046v1 Announce Type: new Abstract: Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their underlying infrastructure doe

Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

arXiv:2608.09624v1 Announce Type: cross Abstract: Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones.

Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation

model-releasesarxiv-cs-cv

arXiv:2608.07562v1 Announce Type: new Abstract: Urban flooding poses an escalating threat to transportation infrastructure, yet no operational system provides real-time, street-level flood-depth estim

Med-CRAFT: An Information System for Explainable and Configurable Construction of Multimodal Medical QA Datasets

arXiv:2512.01045v2 Announce Type: replace Abstract: Data-intensive artificial intelligence applications increasingly rely on large-scale, high-quality, explainable, and reproducible datasets, yet the

researcharxiv-cs-ai

MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning

arXiv:2608.08623v1 Announce Type: new Abstract: In Reinforcement Learning with Verifiable Rewards (RLVR) frameworks for mathematical reasoning tasks, floating-point results are typically evaluated usi

MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

arXiv:2608.09818v1 Announce Type: cross Abstract: Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-

MELLON - Multimodal Enhanced LLM for Online Navigation

arXiv:2608.09121v1 Announce Type: new Abstract: Web navigation agents are capable of addressing various types of tasks on different websites. Current baselines on web navigation are either unimodal or

MemeMind: Reference-Guided Trace Construction for Offline Context Optimization

model-releasesarxiv-cs-cv

arXiv:2608.09316v1 Announce Type: new Abstract: Offline context optimization improves an agent by revising its instructions and examples while keeping the model frozen. This approach learns from rollo

Memorization Dynamics in Knowledge Distillation for Language Models

arXiv:2601.15394v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improv

Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorch

arXiv:2608.08740v1 Announce Type: new Abstract: Activation checkpointing minimizes the runtime of neural networks under a given memory budget, by selecting which intermediate tensors to store and whic

Agents

Mendel Godel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution

arXiv:2608.07645v1 Announce Type: new Abstract: Self-improving coding agents that iteratively rewrite their own source code have demonstrated impressive performance on coding tasks. However, existing

agentsarxiv-cs-ai

Hardware

Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Locality

arXiv:2512.20968v2 Announce Type: replace-cross Abstract: Distributed attention is essential for scaling large language models (LLMs) to long contexts, yet existing methods either have limited paralle

hardwarearxiv-cs-ai

Applications

Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

arXiv:2608.07946v1 Announce Type: cross Abstract: Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers,

applicationsarxiv-cs-ai

Metanormative Theory for RL-Based Moral Agents

arXiv:2608.08220v1 Announce Type: new Abstract: The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial agents that are aligned with human values and

MetaSpace: Metamorphic Testing for Spatial Cognition in Embodied Agents

arXiv:2608.07533v1 Announce Type: new Abstract: An embodied agent is an intelligent entity that interacts with its environment through a physical body. Currently, the evaluation of embodied agents pri

MGMCL: Multi-Granularity Manifold Contrastive Learning With Neural ODEs for Cross-Subject EEG Emotion Recognition

arXiv:2608.08440v1 Announce Type: new Abstract: Cross-subject electroencephalogram (EEG)-based emotion recognition remains challenging due to substantial inter-individual variability and discrete form

safetyarxiv-cs-lg

Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation

arXiv:2608.09001v1 Announce Type: cross Abstract: Black-box privacy scores for retrieval-augmented generation (RAG) are difficult to interpret unless the audited defense's active pipeline hook is know

Local Ai

MiniMax-H3: ~38 GB less VRAM with Runtime LoRA Bypass — DoRA Dynamic LoRA Loader v1.0.39

local-air-stablediffusion

GitHub: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader Release v1.0.39: https://github.com/xmarre/ComfyUI-DoRA-Dynamic-LoRA-Loader/releases/tag/v1.0.39 Also available through ComfyUI Manag

MiraMind: Benchmarking Reliable Mental Health Reasoning beyond Answer Accuracy

arXiv:2512.09636v3 Announce Type: replace Abstract: Mental-health reasoning with large language models (LLMs) is an evidence-constrained judgment problem: models must transform limited, subjective, an

Mismatch Matters: On-Policy Distillation Beyond Token Agreement

arXiv:2608.09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement,

☁️Mistral is bringing together the inference infrastructure, open models, and long-term commitments Europe needs to control its AI future, a…

model-releasesmistral-ai--x

☁️Mistral is bringing together the inference infrastructure, open models, and long-term commitments Europe needs to control its AI future, and setting a roadmap for the world. 🧵: https://mistral.ai/ne

Mitigating Gender Bias in English to Romanian Machine Translation

arXiv:2608.08606v1 Announce Type: cross Abstract: Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a

Mitigating Over-Personalization in LLMs via Structured Memory

arXiv:2608.08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses across sessions. However, when stored user informati

researcharxiv-cs-ai

MixFormer: Linear Transformer with Mixture of Memory Experts

arXiv:2608.09468v1 Announce Type: cross Abstract: State Space Models (SSMs), as a mainstream research direction of linear Transformers, aim to achieve higher efficiency than standard Transformers in l

researcharxiv-cs-ai

ML-Based Hierarchical Prediction for Practical Energy Scheduling in Dynamic NTN-WPT Systems

arXiv:2608.08804v1 Announce Type: cross Abstract: With advancements in long-distance wireless power transfer (WPT) and space-based energy technologies, integrating WPT into non-terrestrial networks (N

safetyarxiv-cs-lg

ML-PWS: Estimating the Mutual Information Between Experimental Time Series Using Neural Networks

arXiv:2508.16509v3 Announce Type: replace-cross Abstract: The ability to quantify information transmission is crucial for the analysis and design of both natural and engineered systems. For systems dr

researcharxiv-cs-lg