14 papers
UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs
Yizhe Xiong, Wei Huang, Xin Ye +6
Post-training is essential for adapting Large Language Models (LLMs) to real-world applications. Deploying post-trained models faces significant challenges due to substantial memor…
MiLe Loss: a New Entropy-Weighed Loss for Mitigating the Bias of Learning Difficulties in Large Language Models
Zhenpeng Su, Xing Wu, Xue Bai +5
Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonst…
YOLOE: Real-Time Seeing Anything
Ao Wang, Lihao Liu, Hui Chen +3
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predef…
PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
Ao Wang, Hui Chen, Jiaxin Li +6
Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these…
CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
Ao Wang, Hui Chen, Zijia Lin +3
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited de…
Temporal Scaling Law for Large Language Models
Yizhe Xiong, Xiansheng Chen, Xin Ye +8
Recently, Large Language Models (LLMs) have been widely adopted in a wide range of tasks, leading to increasing attention towards the research on how scaling LLMs affects their per…