@inproceedings{sagi-etal-2026-cinematic,
title = "Cinematic Compiler: A Typed Intermediate Representation with a Deterministic Pre-Generation Constraint Checker for Multi-Shot Keyframe Continuity",
author = "Sagi, Sai Rama Akash Varma and
Vemireddy, Karthik and
Akula, Sai Ganesh",
editor = "Zhang, Ningyu and
Wijaya, Derry",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics: System Demonstrations",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-demo.3/",
pages = "17--24",
ISBN = "979-8-89176-441-5",
abstract = "Large language model-based generation pipelines commonly transform natural-language requests into structured plans before invoking expensive downstream generators, yet these plans are rarely verified before generation. We present Cinematic Compiler, an interactive system that compiles a short narrative brief into a typed Cinematic Intermediate Representation containing shots, design specifications, entity schedules, and explicit per-shot continuity constraints. A deterministic pre-generation pass checks that every shot carries the required character, costume, prop, and location facts, propagates missing constraints, and rejects contradictory briefs before any generation cost is incurred. At rendering time, the system conditions each shot on a shared character reference image using a frozen commodity image-generation backend, followed by vision-based auditing and reference-anchored repair. Across 15 benchmark briefs, the full constraint pass achieves 100{\%} plan-level constraint coverage, compared with 2.2{\%} for direct prompting, 22.8{\%} for LLM-expanded prompting, and 36.5{\%} for the intermediate representation without propagation. Reference anchoring improves identity-to-reference similarity from 0.605 to 0.714 across 13 briefs, with gains on 12 of 13 briefs, while matched text-only prompting produces no significant improvement. We further show that pairwise cross-shot similarity can reward degenerate near-static generations and therefore report identity preservation jointly with visual dynamic degree. The demonstration allows users to compile, inspect, edit, verify, generate, audit, and repair multi-shot stories through an interactive canvas, while supporting offline replay of stored runs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sagi-etal-2026-cinematic">
<titleInfo>
<title>Cinematic Compiler: A Typed Intermediate Representation with a Deterministic Pre-Generation Constraint Checker for Multi-Shot Keyframe Continuity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Rama</namePart>
<namePart type="given">Akash</namePart>
<namePart type="given">Varma</namePart>
<namePart type="family">Sagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Vemireddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ganesh</namePart>
<namePart type="family">Akula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ningyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derry</namePart>
<namePart type="family">Wijaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-441-5</identifier>
</relatedItem>
<abstract>Large language model-based generation pipelines commonly transform natural-language requests into structured plans before invoking expensive downstream generators, yet these plans are rarely verified before generation. We present Cinematic Compiler, an interactive system that compiles a short narrative brief into a typed Cinematic Intermediate Representation containing shots, design specifications, entity schedules, and explicit per-shot continuity constraints. A deterministic pre-generation pass checks that every shot carries the required character, costume, prop, and location facts, propagates missing constraints, and rejects contradictory briefs before any generation cost is incurred. At rendering time, the system conditions each shot on a shared character reference image using a frozen commodity image-generation backend, followed by vision-based auditing and reference-anchored repair. Across 15 benchmark briefs, the full constraint pass achieves 100% plan-level constraint coverage, compared with 2.2% for direct prompting, 22.8% for LLM-expanded prompting, and 36.5% for the intermediate representation without propagation. Reference anchoring improves identity-to-reference similarity from 0.605 to 0.714 across 13 briefs, with gains on 12 of 13 briefs, while matched text-only prompting produces no significant improvement. We further show that pairwise cross-shot similarity can reward degenerate near-static generations and therefore report identity preservation jointly with visual dynamic degree. The demonstration allows users to compile, inspect, edit, verify, generate, audit, and repair multi-shot stories through an interactive canvas, while supporting offline replay of stored runs.</abstract>
<identifier type="citekey">sagi-etal-2026-cinematic</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-demo.3/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>17</start>
<end>24</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cinematic Compiler: A Typed Intermediate Representation with a Deterministic Pre-Generation Constraint Checker for Multi-Shot Keyframe Continuity
%A Sagi, Sai Rama Akash Varma
%A Vemireddy, Karthik
%A Akula, Sai Ganesh
%Y Zhang, Ningyu
%Y Wijaya, Derry
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-441-5
%F sagi-etal-2026-cinematic
%X Large language model-based generation pipelines commonly transform natural-language requests into structured plans before invoking expensive downstream generators, yet these plans are rarely verified before generation. We present Cinematic Compiler, an interactive system that compiles a short narrative brief into a typed Cinematic Intermediate Representation containing shots, design specifications, entity schedules, and explicit per-shot continuity constraints. A deterministic pre-generation pass checks that every shot carries the required character, costume, prop, and location facts, propagates missing constraints, and rejects contradictory briefs before any generation cost is incurred. At rendering time, the system conditions each shot on a shared character reference image using a frozen commodity image-generation backend, followed by vision-based auditing and reference-anchored repair. Across 15 benchmark briefs, the full constraint pass achieves 100% plan-level constraint coverage, compared with 2.2% for direct prompting, 22.8% for LLM-expanded prompting, and 36.5% for the intermediate representation without propagation. Reference anchoring improves identity-to-reference similarity from 0.605 to 0.714 across 13 briefs, with gains on 12 of 13 briefs, while matched text-only prompting produces no significant improvement. We further show that pairwise cross-shot similarity can reward degenerate near-static generations and therefore report identity preservation jointly with visual dynamic degree. The demonstration allows users to compile, inspect, edit, verify, generate, audit, and repair multi-shot stories through an interactive canvas, while supporting offline replay of stored runs.
%U https://aclanthology.org/2026.aacl-demo.3/
%P 17-24
Markdown (Informal)
[Cinematic Compiler: A Typed Intermediate Representation with a Deterministic Pre-Generation Constraint Checker for Multi-Shot Keyframe Continuity](https://aclanthology.org/2026.aacl-demo.3/) (Sagi et al., AACL-IJCNLP 2026)
ACL