new

Get trending papers in your email inbox!

Subscribe
AK ·

abs: https://arxiv.org/abs/2305.03048 github: https://github.com/ZrrSkywalker/Personalize-SAM propose a trainingfree Personalization approach for SAM, termed as PerSAM.

AK ·

FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size

AK ·

study the best way to place these layers using a neural architecture search inspired approach, and achieve an improvement of 1.3 CHRF (1.5 spBLEU) points over not using LSLs on a separate decoder architecture, and 1.9 CHRF (2.2 spBLEU) on a shared decoder one

AK ·

On the AlfWorld instruction following benchmark, the PET framework leads to a significant 15% improvement over SOTA for generalization to human goal specifications

AK ·

project page: https://mitibmdemos.draco.res.ibm.com/dromedary Applying SELF-ALIGN to the LLaMA-65b base language model, we develop an AI assistant named Dromedary . With fewer than 300 lines of human annotations (including < 200 seed prompts, 16 generic principles, and 5 exemplars for in-context learning), Dromedary significantly surpasses the performance of several state-of-the-art AI systems, including Text-Davinci-003 and Alpaca, on benchmark datasets with various settings

AK ·

github: https://github.com/Wendy-Xiao/chatgpt_editing_summ propose a triagent generation pipeline consisting of a generator, an instructor, and an editor to enhance the customization of generated outputs

AK ·

abs: https://arxiv.org/abs/2305.02463 github: https://github.com/openai/shap-e present Shap·E, a conditional generative model for 3D assets