Shilin HE (@shilinhe) 's Twitter Profile
Shilin HE

@shilinhe

AI4SE, AI Coding, LLM, Agent
Applied Scientist @Bytedance, Prev MSRA Researcher @Microsoft , Ph.D. @CUHKOfficial

ID: 3320052781

linkhttps://shilinhe.github.io calendar_today19-08-2015 12:44:44

46 Tweet

99 Followers

420 Following

Shilin HE (@shilinhe) 's Twitter Profile Photo

#taskweaver Are you tired of working with cumbersome text strings for data analytics tasks? Say hello to TaskWeaver - the innovative code-first agent framework that streamlines planning and execution. (1/n) Checkout our repo at aka.ms/taskweaver

Shilin HE (@shilinhe) 's Twitter Profile Photo

With rich data structures, customized algorithms, and easy integration of domain-specific knowledge, TaskWeaver is your ticket to efficient and seamless data analytics. (2/n)

Shilin HE (@shilinhe) 's Twitter Profile Photo

It also offers stateful conversation, easy debugging, security considerations, and easy extension. Experience the TaskWeaver revolution and simplify your data analytics tasks today! (3/n)

Microsoft Research (@msftresearch) 's Twitter Profile Photo

AI-backed virtual assistants face challenges in handling complex data structures. TaskWeaver helps users build assistants that understand diverse domain questions, follow examples, & efficiently execute customizable algorithms on complex data structures. msft.it/6012imeZY

Shilin HE (@shilinhe) 's Twitter Profile Photo

Our recent work on leveraging LLMs to generate query code in production environment will be presented at ICSE 2024. Joint work with colleagues in Microsoft and my former intern Yuxuan Jiang from UMich.

Thomas Wolf (@thom_wolf) 's Twitter Profile Photo

Llama3 was trained on 15 trillion tokens of public data. But where can you find such datasets and recipes?? Here comes the first release of 🍷Fineweb. A high quality large scale filtered web dataset out-performing all current datasets of its scale. We trained 200+ ablation

elvis (@omarsar0) 's Twitter Profile Photo

LLM-brained GUI Agents Great survey on LLM-brained GUI agents, including techniques and applications. arxiv.org/abs/2411.18279

LLM-brained GUI Agents

Great survey on LLM-brained GUI agents, including techniques and applications.

arxiv.org/abs/2411.18279
Shilin HE (@shilinhe) 's Twitter Profile Photo

Overwhelmed by the flood of recent studies on GUI agents? Dive into our latest work, "Large Language Model-Brained GUI Agents: A Survey", by far the most comprehensive and insightful survey in the GUI agent domain—don't miss out! 😊

Overwhelmed by the flood of recent studies on GUI agents? 
Dive into our latest work, "Large Language Model-Brained GUI Agents: A Survey", by far the most comprehensive and insightful survey in the GUI agent domain—don't miss out! 😊
WebAgentlab (@webagentlab) 's Twitter Profile Photo

4/ 🧵 UFO2: The Desktop AgentOS UFO2 is a multiagent operating system for Windows that enhances desktop automation through deep OS integration, a hybrid GUI-API action layer, and a non-disruptive Picture-in-Picture interface, significantly improving reliability and efficiency

4/ 🧵 UFO2: The Desktop AgentOS

UFO2 is a multiagent operating system for Windows that enhances desktop automation through deep OS integration, a hybrid GUI-API action layer, and a non-disruptive Picture-in-Picture interface, significantly improving reliability and efficiency
Shilin HE (@shilinhe) 's Twitter Profile Photo

Coding agents keep reading many code files to understand the repository, increasing the context and cost😪. In SWE-Pruner, we propose a lightweight adaptor that can "pick out the code snippet of interest" , thereby reducing the cost significantly with minimum performance drop.