论文解读
Motionbeat: Motion-Aligned Music Representation via Embodied Contrastive Learning and Bar-Equivariant Contact-Aware Encoding
舞蹈生成 | 7.5/10
音乐生成
子标签
下方只统计已核验方向的论文记录，按已核身份去重，身份待核时按页面保留。“直接”只含明确标注该方向的论文；“含子树”同时包含下级方向。点击名称进入论文库继续筛选；数量与上方按标签名称收录的页面数不同。
论文解读
MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation
音乐生成 | 7.5/10
论文解读
MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding
音乐生成 | 8.5/10
论文解读
Pianoroll-Event: A Novel Score Representation for Symbolic Music
音乐生成 | 6.5/10
论文解读
Sing2Song: An Accompaniment Generation System Based on Solo Singing
音乐生成 | 7.5/10
论文解读
Stemphonic: All-At-Once Flexible Multi-Stem Music Generation
音乐生成 | 7.7/10
论文解读
Symphony Rendering: Midi and Composer-Conditioned Auto Orchestration with Flow-Matching Transformers
音乐生成 | 7.0/10
论文解读
SymphonyGen: 3D Hierarchical Orchestral Generation with Controllable Harmony Skeleton
音乐生成 | 7.5/10
论文解读
Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment
音乐生成 | 7.5/10
论文解读
Time-Shifted Token Scheduling for Symbolic Music Generation
音乐生成 | 8.5/10
论文解读
Towards Multi-View Hierarchical Video-to-Piano Generation with MIDI Guidance
音乐生成 | 7.0/10
论文解读
Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation
音乐生成 | 7.5/10
论文解读
Virtual Consistency for Audio Editing
音乐生成 | 8.0/10
论文解读
Visual Keys to Symphonies: Latent Diffusion for Multi-Scene Video-to-Music Generation
音乐生成 | 7.5/10
论文解读
ViTex: Visual Texture Control for Multi-Track Symbolic Music Generation via Discrete Diffusion Models
音乐生成 | 7.0/10
论文解读
VMSP: Video-to-Music Generation with Two-Stage Alignment and Synthesis
音乐生成 | 7.0/10
论文解读
When Noise Lowers the Loss: Rethinking Likelihood-Based Evaluation in Music Large Language Models
音乐生成 | 7.0/10
论文解读
Opening the Design Space: Two Years of Performance with Intelligent Musical Instruments
音乐生成 | 6.5/10
论文解读
Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation
音乐生成 | 7.0/10
论文解读
BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps
本文针对符号音乐生成中主流的事件序列（event-based）tokenization方法隐含处理时间规律、导致模型需额外学习时间网格的问题，提出了一种名为**BEAT**的新型网格化tokenization框架。其核心思想是将音乐在时间上均匀离散化为“拍”（beat）作为基本单位，将每拍内每个音高