{
  "id": 19445,
  "url": "https://arxiv.org/abs/2608.13368v1",
  "title": "Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs",
  "summary": "This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators -- global, hand, and head -- each guide a corresponding expert branch in the generator toward a distinct visual region, enabling implicit feature specialization without explicit diversity losses. To stabilize this multi-discriminator system,",
  "authors": "Dingzhan Nong, Zhihao Ren, Ziqi Li, Tim Lo",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T15:32:40.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/19445",
  "original_url": "https://arxiv.org/abs/2608.13368v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}