vivo AI Lab introduces CAPO-SLT, a confidence-aware policy optimization method that stabilizes sign language translation by giving each token a dynamic clipping bound based on old-policy confidence, achieving state-of-the-art results on Chinese and American sign language benchmarks using only pose input.
The paper introduces SignThought, a gloss‑free sign language translation model that inserts an ordered latent‑thought chain between video encoding and text generation, uses a plan‑then‑ground decoding strategy, and is evaluated on five benchmarks and a newly built 1,311‑hour LC‑HKSLT dataset, achieving state‑of‑the‑art BLEU‑4 and ROUGE scores.
The paper introduces SignThought, a gloss‑free sign language translation framework that uses a latent chain‑of‑thought reasoning layer and a plan‑then‑ground decoder, evaluates it on five benchmarks with state‑of‑the‑art BLEU‑4 and ROUGE scores, and releases a large new Hong Kong sign language dataset.
In his 2021 Cloud Conference keynote, Alibaba CTO Cheng Li outlines the company’s vision of “good technology,” emphasizing AI-driven solutions that benefit everyone, assume responsibility, and promote open sharing—from sign‑language translation and dementia screening to green computing, zero‑carbon cloud and open‑source initiatives.
