联想 发表于 2025-3-23 12:01:17
Combining Contrastive Learning and Sequence Learning for Automated Essay Scoring of subjective factors on grading. Previous works tend to treat it solely as a regression or classification task, without considering the integration of both. Additionally, neural networks trained on limited samples often exhibit poor performance in capturing the deep semantics of texts. To enhancecravat 发表于 2025-3-23 16:29:32
PIDM: Personality-Aware Interaction Diffusion Model for Gesture Generationcity and magnitude of motion during conversation are also affected by the personality traits of each participant. In this paper, we propose the personality-aware interaction diffusion model (PIDM) for a dyadic conversation. PIDM generates interaction behaviors based on the masking features of all panegotiable 发表于 2025-3-23 21:03:02
Prompt Design Using Past Dialogue Summarization for LLMs to Generate the Current Appropriate Dialoguowever, following fluently current dialogue from the past dialogue is crucial, especially for chat-oriented dialogue systems, which are difficult for only LLMs to handle. In this paper, we propose a prompt design using a method summarizing dialogue for LLMs to generate the current appropriate dialogFree-Radical 发表于 2025-3-23 22:52:56
http://reply.papertrans.cn/17/1677/167622/167622_14.pngENACT 发表于 2025-3-24 06:03:19
http://reply.papertrans.cn/17/1677/167622/167622_15.pngEvacuate 发表于 2025-3-24 07:26:24
http://reply.papertrans.cn/17/1677/167622/167622_16.pngLucubrate 发表于 2025-3-24 13:00:02
http://reply.papertrans.cn/17/1677/167622/167622_17.png有特色 发表于 2025-3-24 18:29:39
http://reply.papertrans.cn/17/1677/167622/167622_18.png大漩涡 发表于 2025-3-24 19:25:18
http://reply.papertrans.cn/17/1677/167622/167622_19.png博爱家 发表于 2025-3-24 23:34:47
http://reply.papertrans.cn/17/1677/167622/167622_20.png