Pith. sign in

REVIEW 9 cited by

Anticipatory Music Transformer

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.08620 v2 pith:DXEGKEZT submitted 2023-06-14 cs.SD cs.LGeess.ASstat.ML

classification cs.SDcs.LGeess.ASstat.ML
keywords controlmusiceventsprocessanticipatorycontrolsgenerationinfilling
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce anticipation: a method for constructing a controllable generative model of a temporal point process (the event process) conditioned asynchronously on realizations of a second, correlated process (the control process). We achieve this by interleaving sequences of events and controls, such that controls appear following stopping times in the event sequence. This work is motivated by problems arising in the control of symbolic music generation. We focus on infilling control tasks, whereby the controls are a subset of the events themselves, and conditional generation completes a sequence of events given the fixed control events. We train anticipatory infilling models using the large and diverse Lakh MIDI music dataset. These models match the performance of autoregressive models for prompted music generation, with the additional capability to perform infilling control tasks, including accompaniment. Human evaluators report that an anticipatory model produces accompaniments with similar musicality to even music composed by humans over a 20-second clip.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation

    cs.SD 2026-08 conditional novelty 7.0 of 10

    Controlled experiments show that a 10ms performance-timed token stream lowers Frechet Music Distance roughly twofold versus beat-grid tokens, across model sizes from 0.8B to 27B.

  2. MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering

    cs.SD 2026-08 conditional novelty 6.0 of 10

    Musical concepts are linearly decodable and steerable in two public text-to-MIDI models, with prediction forming gradually in an encoder-decoder and late in a vocabulary-extended LLM.

  3. A Reproducible, Scalable Pipeline for Synthesizing Autoregressive Model Literature

    cs.IR 2025-08 conditional novelty 6.0 of 10

    A scalable literature-synthesis pipeline that retrieves, filters, extracts, summarizes, and converts AR-model papers into runnable training scripts, with F1 > 0.85 extraction and three reproduction case studies.

  4. Scaling Self-Supervised Representation Learning for Symbolic Piano Performance

    cs.SD 2025-06 conditional novelty 6.0 of 10

    Self-supervised pretraining on 60,000 hours of symbolic piano music produces a generative model and contrastive embeddings that beat leading baselines on continuation quality and several MIR classification benchmarks.

  5. AI Harmonizer: Expanding Vocal Expression with a Generative Neurosymbolic Music AI System

    cs.HC 2025-06 reject novelty 6.0 of 10

    A new offline system automatically adds three harmonized vocal parts to a solo melody using trained music AI models, but its claimed musical quality is not empirically evaluated.

  6. Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling

    cs.SD 2025-04 conditional novelty 6.0 of 10

    Aria-MIDI contributes 1.19 million piano MIDI files (about 100,000 hours) transcribed from web audio through LLM-guided crawling, source-separation-based classification, and the Aria-AMT transcription model.

  7. ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement

    cs.SD 2025-02 conditional novelty 6.0 of 10

    A corruption-refinement transformer, ImprovNet, generates controllable jazz and classical improvisations of complete piano pieces, and also handles harmonization, continuation, and infilling.

  8. Local deployment of large-scale music AI models on commodity hardware

    cs.SD 2024-11 conditional novelty 5.0 of 10

    The authors port the Anticipatory Music Transformer to MLC and WebLLM, run it in a browser, and measure faster-than-real-time MIDI generation on Apple silicon.

  9. TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization

    cs.SD 2025-08 reject novelty 4.0 of 10

    TinyMusician distills MusicGen and applies hand-picked mixed-precision quantization to make a 1.04 GB on-device music generator, but the headline '93% quality, 55% smaller' claims conflict with the paper's own tables.

Pith tools