On the 30th floor of the Chartered Square building in downtown Bangkok, the low-key office of Skyhub Technologies serves as a nexus for a burgeoning and contentious trade. The space, rented out by a serviced office provider, is visited only rarely by the company's sole director and occasionally by Chinese nationals, according to building staff who asked not to be identified speaking about clients. No contact number is listed on its online registration documents. No one was available during a visit in late January. Despite the appearance of inactivity, this is a busy conduit for advanced drones. Trade documents show that Skyhub Technologies is Thailand's second-biggest importer of unmanned aerial vehicles from China.

A new framework is proposed in this paper to address these issues.

With the success of deep learning, there are growing concerns over interpretability (Lipton, 2018). Ideally, the explanation should be both faithful (reflecting the model's actual behavior) and plausible

Sign language translation (SL T) addresses the problem of translating information from a sign language in video to a spoken language in text. Existing studies, while showing progress, are often limited to narrow domains and/or few sign languages and struggle with open-domain tasks. In this paper, we push forward the frontier of SL T by scaling pretraining data, model size, and number of translation directions. We perform large-scale SL T pretraining on different data including 1) noisy multilingual Y ouTube SL T data, 2) parallel text corpora, and 3) SL T data augmented by translating video captions to other languages with off-the-shelf machine translation models. We unify different pretraining tasks with task-specific prompts under the encoder-decoder architecture, and initialize the SL T model with pretrained (m/By)T5 models across model sizes. SL T pretraining results on How2Sign and FLEURS-ASL#0 (ASL to 42 spoken languages) demonstrate the significance of data/model scaling and cross-lingual cross-modal transfer, as well as the feasibility of zero-shot SL T. We finetune the pretrained SL T models on 5 downstream open-domain SL T benchmarks covering 5 sign languages. Experiments show substantial quality improvements over the vanilla baselines, surpassing the previous state-of-the-art (SOT A) by wide margins.

The advent of large language models (LLMs) [Brown et al., 2020] has revolutionized the field of