Event-Centric Audio-Video Consistency Evaluation · Full reward-model checkpoint. From the GitHub repository, after setting up the environment
Independent publisher
Yuruo Wu
Tsuki0512
Models in Library2
Datasets in Library1
Models on Hugging Face2
Followers1
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
LTX-2 dev LoRA optimized with AVC-Reward. From the GitHub repository, after installing the LTX-2 runtime and preparing the Gemma encoder
Datasets
706-sample audio-video consistency benchmark. Media is here; the score CSV and evaluation script are on GitHub. From the GitHub repository