Zobrazeno 1 - 10
of 175
pro vyhledávání: '"Xu, WENda"'
Autor:
Xu, Wenda
This dissertation presents a comprehensive exploration encompassing the design, development, control and the application of reinforcement learning-based force planning for the autonomous grasping capabilities of the innovative assistive robotic exosk
Externí odkaz:
http://hdl.handle.net/10919/116452
CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation
Simultaneous speech translation (SimulST) systems must balance translation quality with response time, making latency measurement crucial for evaluating their real-world performance. However, there has been a longstanding belief that current metrics
Externí odkaz:
http://arxiv.org/abs/2410.16011
Autor:
Xu, Wenda, Han, Rujun, Wang, Zifeng, Le, Long T., Madeka, Dhruv, Li, Lei, Wang, William Yang, Agarwal, Rishabh, Lee, Chen-Yu, Pfister, Tomas
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the knowledge gaps bet
Externí odkaz:
http://arxiv.org/abs/2410.11325
Despite advancements in Large Language Model (LLM) alignment, understanding the reasons behind LLM preferences remains crucial for bridging the gap between desired and actual behavior. LLMs often exhibit biases or tendencies that diverge from human p
Externí odkaz:
http://arxiv.org/abs/2410.06965
With the rapid advancement of machine translation research, evaluation toolkits have become essential for benchmarking system progress. Tools like COMET and SacreBLEU offer single quality score assessments that are effective for pairwise system compa
Externí odkaz:
http://arxiv.org/abs/2410.10861
Autor:
Li, Fulan, Guo, Yunfei, Xu, Wenda, Zhang, Weide, Zhao, Fangyun, Wang, Baiyu, Du, Huaguang, Zhang, Chengkun
Publikováno v:
Frontiers in Rehabilitation Sciences, 5 (2024)
This paper presents GARD, an upper limb end-effector rehabilitation device developed for stroke patients. GARD offers assistance force along or towards a 2D trajectory during physical therapy sessions. GARD employs a non-backdrivable mechanism with n
Externí odkaz:
http://arxiv.org/abs/2406.14795
Direct alignment from preferences (DAP) has emerged as a promising paradigm for aligning large language models (LLMs) to human desiderata from pre-collected, offline preference datasets. While recent studies indicate that existing offline DAP methods
Externí odkaz:
http://arxiv.org/abs/2406.12168
Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary is due to LLM's bias in evaluating their own output. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2402.11436
Autor:
Xu, Wenda, Deutsch, Daniel, Finkelstein, Mara, Juraska, Juraj, Zhang, Biao, Liu, Zhongtao, Wang, William Yang, Li, Lei, Freitag, Markus
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. However, human feedback is costly to obtain, especially during inference. In this work, we propose LLMRefine, an inference time optimization method
Externí odkaz:
http://arxiv.org/abs/2311.09336
Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A
Externí odkaz:
http://arxiv.org/abs/2308.03188