5 accepted papers
Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate these challenges have relied on fixed sparse attention patterns…
Slip detection and control is critical to achieving stable grasping in robotics. However, accurate and robust slip detection and control remains a challenging task. This letter proposes a learning framework with contrastive learning and feature alignment to improve the accuracy of end-to-end slip de
Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model merging techniques during the pre-training process. Through exten…
Advancements in distributed training and efficient attention mechanisms have significantly expanded the context window sizes of large language models (LLMs). However, recent work reveals that the effective context lengths of open-source LLMs often fall short, typically not exceeding half of their tr…
High-performance video frame interpolation is challenging for complex scenes with diverse motion and occlusion characteristics. Existing methods, deploying off-the-shelf flow estimators to acquire initial characterizations refined by multiple subsequent models, often require heavy network architectu…