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

MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval taaft Information retrieval (IR) increasingly targets open-ended queries that admit diverse perspectives.… 2026-08-31 published
MultiAttenGastro: Multi-Dimensional Attention Augmentation for Gastrointestinal Endoscopy Classification taaft Automated gastrointestinal (GI) endoscopy classification requires models that generalize across div… 2026-09-04 published
MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation taaft Subject-driven image generation is increasingly expected to support fine-grained control over multi… 2026-03-23 published
MultiBiSage: A Web-Scale Recommendation System Using Multiple Bipartite Graphs at Pinterest Pinterest Graph Convolutional Networks (GCN) can efficiently integrate graph structure and node features to l… 2022-05-21 published
MultiCam: On-the-fly Multi-Camera Pose Estimation Using Spatiotemporal Overlaps of Known Objects taaft Multi-camera dynamic Augmented Reality (AR) applications require a camera pose estimation to levera… 2026-03-24 published
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts taaft While existing work on LLM authorship attribution (AA) has made progress, available benchmarks rema… 2026-09-02 published
Multimodal Chain-of-Thought Reasoning in Language Models Amazon Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging c… 2023-02-02 published
MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment taaft Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modali… 2026-08-11 published
Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation taaft We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce t… 2023-11-15 published
MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image Retrieval taaft Training-free zero-shot composed image retrieval finds a target image in a gallery from a reference… 2026-08-26 published
MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation taaft Distributional metrics such as Fréchet Audio Distance cannot score individual music clips and corre… 2026-03-24 published
MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning taaft Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse inter… 2026-09-04 published
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects taaft We propose an end-to-end music mixing style transfer system that converts the mixing style of an in… 2022-11-04 published
MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models taaft Recent advances in text-to-music generation models have opened new avenues in musical creativity. H… 2024-02-09 published
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data taaft Recent large language models (LLMs) have witnessed significant advancement in various tasks, includ… 2024-02-14 published
MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse Fusion taaft The 3D center of mass (CoM) is a primary quantity in the biomechanical analysis of sport, rehabilit… 2026-09-02 published
MV-dVRK: A Multi-Viewpoint Benchmark for Spatial Surgical Perception taaft Large-scale training and refined optimization techniques have greatly improved sparse multi-view 3D… 2026-09-02 published
MVC-Bench: Benchmarking Calibration of Medical Vision-Language Models taaft Reliable evaluation of vision-language models (VLMs) and medical vision-language models (Medical-VL… 2026-08-27 published
MVDream: Multi-view Diffusion for 3D Generation taaft We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from… 2023-08-31 published
MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching taaft Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such… 2026-08-26 published
MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting taaft Accurate station-level precipitation nowcasting is critical for agriculture, water resource managem… 2026-09-04 published
mzCache: On-Device LLM Memory Management under Multitasking taaft On-device mobile Large Language Model (LLM) inference is gaining significant attention. However, mo… 2026-09-01 published
Names Can Hurt: Spotting Slopsquatting Risks Caused by Package Name Hallucinations in Local Coding LLMs taaft When a code generating language model fabricates a Python package name, an adversary who has pre-re… 2026-08-24 published
Narcissus: Program Synthesis Using Context-Aware LLM Approximations taaft Large language models (LLMs) excel at programming, but not when the task fixes the target language:… 2026-08-26 published
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games taaft Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains,… 2026-09-01 published
NASimJax: GPU-Accelerated Policy Learning Framework for Penetration Testing taaft Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a comp… 2026-03-20 published
Natural Adversarial Objects taaft Although state-of-the-art object detection methods have shown compelling performance, models often… 2021-11-07 published
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning taaft Named Entity Recognition (NER) has achieved substantial progress since the advent of large language… 2026-09-02 published
NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer taaft AI-driven de novo molecular design offers a promising route to accelerate early-stage drug discover… 2026-09-04 published
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence taaft LLM decision components that can operate within agent workflows often produce action-relevant recom… 2026-09-04 published
Neither parallel nor sequential: how DiffusionGemma actually commits tokens Transformer Lab An inference-only interpretability study hooking DiffusionGemma's token-commit mechanism. Across si… Transformer Lab
NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis taaft Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substan… 2026-09-03 published
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Google Research We present a method that achieves state-of-the-art results for synthesizing novel views of complex… 2020-03-19 published
Nerfies: Deformable Neural Radiance Fields taaft We present the first method capable of photorealistically reconstructing deformable scenes using ph… 2020-11-25 published
Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result taaft A byte-level BPE tokenizer is an ordered list of merge rules, so applying only a prefix yields a vo… 2026-08-28 published
Network-Aware Forecasting on Wireless Access Points taaft Enterprise wireless access points (APs) are promising platforms for predictive machine learning (ML… 2026-09-02 published