Santiago Castro Vizcaya

[Shunyu Yao @ShunyuYao12]

Language Agents are cool & fast-moving, but no systematic way to understand & design them..

So we use classical CogSci & AI insights to propose Cognitive Architectures for Language Agents (🐨CoALA)!

https://t.co/nPInnglURT
w/ great @tedsumers @karthik_r_n @cocosci_lab
(1/6)

[AK @_akhaliq]

LLaMA2-Accessory: An Open-source Toolkit for LLM Development 🚀

github: https://t.co/ykc1I0w2iu

🚀LLaMA2-Accessory is an open-source toolkit for pre-training, fine-tuning and deployment of Large Language Models (LLMs) and mutlimodal LLMs. This repo is mainly inherited from LLaMA-Adapter with more advanced features.🧠

[AK @_akhaliq]

Tracking Anything in High Quality

paper page: https://t.co/WlLixHlSAx

Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows the unification of single/multiobject and box/mask-based tracking. Among them, the Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, a framework for High Quality Tracking anything in videos. HQTrack mainly consists of a video multi-object segmenter (VMOS) and a mask refiner (MR). Given the object to be tracked in the initial frame of a video, VMOS propagates the object masks to the current frame. The mask results at this stage are not accurate enough since VMOS is trained on several closeset video object segmentation (VOS) datasets, which has limited ability to generalize to complex and corner scenes. To further improve the quality of tracking masks, a pretrained MR model is employed to refine the tracking results. As a compelling testament to the effectiveness of our paradigm, without employing any tricks such as test-time data augmentations and model ensemble, HQTrack ranks the 2nd place in the Visual Object Tracking and Segmentation (VOTS2023) challenge.

[Pavel Shibanov @shibanovp]

Excited to share a Colab notebook that initiates the MPT-30B-Chat by @MosaicML on @vast_ai, using @huggingface's text-generation-inference.
It integrates seamlessly with @langchain's ConversationChain and the interactive @Gradio Chatbot interface.
https://t.co/NR6hoWawj6