Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced

Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning taaft 3D perception plays a crucial role in real-world applications such as autonomous driving, robotics,… 2026-09-04 published
Mitigating stereotypical biases in text to image generative systems taaft State-of-the-art generative text-to-image models are known to exhibit social biases and over-repres… 2023-10-10 published
Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation taaft Integrating information from various reference databases is a major challenge for Retrieval-Augment… 2024-06-01 published
Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space taaft Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, e… 2023-10-14 published
Mixtral 8x22B (Cheaper, Better, Faster, Stronger) Mistral AI Research announcement describing Mixtral 8×22B, emphasizing MoE efficiency (active vs total params)… Mistral AI
Mixtral of Experts Mistral AI We introduce Mixtral 8x7B, a Sparse Mixture of Experts (SMoE) language model. Mixtral has the same… 2024-01-08 published
Mixture of Channel Experts: Static Sparse Supports with Input-Adaptive Mixing for Pointwise Projections taaft Mixture-of-Experts (MoE) scales language models by routing each input through a small set of indepe… 2026-08-24 published
Mixture of Demonstrations for Textual Graph Understanding and Question Answering taaft Textual graph-based retrieval-augmented generation (GraphRAG) has emerged as a powerful paradigm fo… 2026-03-23 published
Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models taaft Instruction Tuning has the potential to stimulate or enhance specific capabilities of large languag… 2024-03-06 published
MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning taaft Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual… 2026-06-23 published
ML-Decoder: Scalable and Versatile Classification Head Alibaba In this paper, we introduce ML-Decoder, a new attention-based classification head. ML-Decoder predi… 2021-11-25 published
MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations taaft Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at com… 2026-08-26 published
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models taaft As vision-language models (VLMs) rapidly advance in image understanding, cross-modal reasoning, and… 2026-09-04 published
MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation taaft This study aims to construct an audio-video generative model with minimal computational cost by lev… 2024-05-28 published
MMDS-Bench: Benchmarking Multimodal Large Language Models on Dynamic Stance in Social Media Interactions taaft Dynamic stance classification models how a reply responds to its direct parent message, rather than… 2026-08-31 published
MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak Vulnerabilities taaft Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet… 2026-08-26 published
MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain taaft Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's healt… 2026-09-04 published
MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences taaft We present a dynamical-systems based model for resting-state functional magnetic resonance imaging… 2026-08-25 published
MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents taaft AI agents in partially observable environments need to coordinate active sensing with working memor… 2026-08-31 published
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases Meta Platforms This paper addresses the growing need for efficient large language models (LLMs) on mobile devices,… 2024-02-22 published
Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective taaft Multimodal Emotion Recognition (MER) systems often suffer from missing modalities in real-world sce… 2026-08-31 published
Model Retirement Creates Reproducibility Risk in Biomedical AI Publications taaft Background. Large language models (LLMs) are being adopted in biomedical research at a rapid and ac… 2026-09-04 published
Model selection in hybrid quantum neural networks with applications to quantum transformer architectures taaft Quantum machine learning models generally lack principled design guidelines, often requiring full r… 2026-03-23 published
Model-Free Surrogate-Assisted Neural Architecture Search for Evolving Variable-Length Dense Blocks taaft Neural Architecture Search (NAS) has emerged as a powerful paradigm for automatically designing dee… 2026-09-02 published
Modeling Quantum Federated Autoencoder for Anomaly Detection in IoT Networks taaft We propose a Quantum Federated Autoencoder for Anomaly Detection, a framework that leverages quantu… 2026-03-23 published
Modeling What Changes: Sparse, Residual World Models for Object-Centric Manipulation taaft Monolithic world models predict the entire next state at every step, spending capacity re-predictin… 2026-09-02 published
Modern Transformers Are Implicit Hybrids: From Functional Differentiation to Principled Hybrid Architecture Design taaft Hybrid architectures combining Full Attention (FA) and Linear Attention (LA) are increasingly promi… 2026-09-02 published
MoDS: Model-oriented Data Selection for Instruction Tuning taaft Instruction tuning has become the de facto method to equip large language models (LLMs) with the ab… 2023-11-27 published
MOELIGA: a multi-objective evolutionary approach for feature selection with local improvement taaft Selecting the most relevant or informative features is a key issue in actual machine learning probl… 2026-03-21 published
MoirfEolas and CríochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology taaft This paper presents new tokenization resources for Irish and evaluation measures of alignment with… 2026-09-04 published
Molecular Déjà Vu: Digit-Level Retrieval of Published Values in Frontier Language Models taaft Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accur… 2026-09-04 published
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction taaft Motion forecasting is central to visual intelligence: agents must anticipate how objects will move… 2026-06-17 published
MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation taaft Large language models (LLMs) hold considerable potential for advancing scientific discovery, yet sy… 2026-03-26 published
MomentQuant: an even more minimalist interval method with linear time complexity for time series classification taaft Time series data is very common in many real-world applications and in numerous domains, with incre… 2026-09-04 published
Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency taaft We study when and how momentum improves large-batch training in the one-pass regime, using power-la… 2026-09-02 published
Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision taaft Reliable web-agent monitoring is difficult when model-internal uncertainty signals such as token lo… 2026-09-02 published