Machine Translation (MT) has developed rapidly since the release of Large language Models and current MT evaluation is performed through comparison with reference human translations or by predicting quality scores fro...
详细信息
Learning a model of a stochastic setting often involves learning both general structure rules and specific properties of the instance. This paper investigates the interplay between learning the general and the specifi...
详细信息
Current instruction-tuned language models are exclusively trained with textual preference data and thus are often not aligned with the unique requirements of other modalities, such as speech. To better align language ...
详细信息
Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuro...
详细信息
Historically, sign language machine translation has been posed as a sentence-level task: datasets consisting of continuous narratives are chopped up and presented to the model as isolated clips. In this work, we explo...
详细信息
While Reinforcement Learning from Human Feedback (RLHF) significantly enhances the generation quality of Large language Models (LLMs), recent studies have raised concerns regarding the complexity and instability assoc...
Ensuring that the benefits of sign language technologies are distributed equitably among all community members is crucial. Thus, it is important to address potential biases and inequities that may arise from the desig...
详细信息
Large language models (LLMs) are pivotal in advancing naturallanguageprocessing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to ad...
详细信息
Recent advancements in Large language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding. However, processing extensive videos such as 24-hour CCTV foota...
详细信息
We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied *** this task, two agents in a shared scene must take into account one another's visual perspective, wh...
详细信息
暂无评论