Research map / Video / Video generation
LLM Is a Good Conditioner: End-to-End Sign Language Video Generation with VQ-Diffusion
Xiao Liu, Shiwei Gan
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an end-to-end sign language video generation approach that uses an LLM as the conditioner for a VQ-Diffusion model, avoiding intermediate poses or 3D meshes.
Problem
Sign language video generation from spoken text, where existing methods rely on intermediate representations (poses, 3D meshes) and a two-stage pipeline.
Approach
Replaces the two-stage pose-then-diffusion paradigm with a single end-to-end pipeline in which an LLM conditions a VQ-Diffusion model that generates sign language video directly from text.
Experimental setup
Builds on: VQ-Diffusion
Closest papers by meaning
- Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization (NeurIPS 2025 · similarity 0.94)
- Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observations (CVPR 2025 · similarity 0.92)
- Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment (AAAI 2024 · similarity 0.89)
- LLMs are Good Sign Language Translators (CVPR 2024 · similarity 0.89)
- Scaling Sign Language Translation (NeurIPS 2024 · similarity 0.89)
- Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment (NeurIPS 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
