吸引人的花招
发表于 2025-3-27 01:02:00
http://reply.papertrans.cn/67/6697/669627/669627_31.png
CAJ
发表于 2025-3-27 02:07:23
What is the Best Model? Application-Driven Evaluation for Large Language Models and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an applicatio
syring
发表于 2025-3-27 09:15:38
Sparse Mixture of Experts Language Models Excel in Knowledge Distillationn distilling large language models have primarily focused on loss functions and training methodologies, with limited attention given to structural improvements of student models. This is largely due to the challenges posed by cross-architecture distillation and the substantial computational resource
来这真柔软
发表于 2025-3-27 10:43:19
http://reply.papertrans.cn/67/6697/669627/669627_34.png
reperfusion
发表于 2025-3-27 14:47:48
Reparameterization-Based Parameter-Efficient Fine-Tuning Methods for Large Language Models: A Systemning objectives to achieve unprecedented performance. To fully exploit the potential of LLMs, fine-tuning LLMs on specific downstream tasks is essential. However, traditional full fine-tuning methods pose significant computational challenges, prompting the emergence of Parameter-Efficient Fine-Tunin
自由职业者
发表于 2025-3-27 21:28:38
http://reply.papertrans.cn/67/6697/669627/669627_36.png
white-matter
发表于 2025-3-27 22:21:50
http://reply.papertrans.cn/67/6697/669627/669627_37.png
LAITY
发表于 2025-3-28 04:54:57
http://reply.papertrans.cn/67/6697/669627/669627_38.png
学术讨论会
发表于 2025-3-28 06:50:27
FIRP: Faster LLM Inference via Future Intermediate Representation Predictionnature of LLM decoding, which generates only a single token per forward propagation, fails to fully exploit the parallel computational power of GPUs, leading to considerable latency. To address this, we introduce a novel speculative decoding method named FIRP which generates multiple tokens instead
colostrum
发表于 2025-3-28 11:48:37
http://reply.papertrans.cn/67/6697/669627/669627_40.png