https://github.com/jianguoz/jianguoz
https://github.com/jianguoz/jianguoz
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/jianguoz/jianguoz
- Owner: jianguoz
- Created: 2021-04-15T21:43:57.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2024-09-09T14:34:57.000Z (8 months ago)
- Last Synced: 2025-01-16T02:31:51.233Z (3 months ago)
- Size: 66.4 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### Hi there π
I am a Senior Research Scientist at [Salesforce AI Research](https://www.salesforceairesearch.com/). I received Ph.D. in the Department of Computer Science at the University of Illinois at Chicago. During my doctoral study, I was advised by Prof. [Philip S. Yu](https://scholar.google.com/citations?user=D0lL1r0AAAAJ&hl=en) in the [BDSC](https://bdsc-uic.github.io/index.html) Lab.
My research focuses on Conversational AI and AI Agent.
Personal Website: https://jianguoz.github.io/
## π News
- **[09.2024]** Check our latest work [xLAM: A Family of Large Action Models to Empower AI Agent Systems](https://arxiv.org/abs/2409.03215), which demonstrates top-tier performance across multiple challenging benchmarks and scenarios. Explore more through the [xLAM GitHub Repo](https://t.co/iBAp3MgXGo), [HuggingFace Model Collections](https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4) and [Project Webpage](https://www.salesforceairesearch.com/projects/xlam-large-action-models).
- **[07.2024]** Happy to contribute to the new work [Consent in Crisis: The Rapid Decline of the AI Data Commons](https://www.dataprovenance.org/consent-in-crisis-paper). See also the [New York Times](https://www.nytimes.com/2024/07/19/technology/ai-data-restrictions.html) and [Twitter](https://x.com/JianguoZhang3/status/1814310784903909532).
- **[06.2024]** Check our work [APIGen](https://apigen-pipeline.github.io/), the best open-sourced models for function calling. Our dataset [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) is currently among the Top-2 trending datasets on HuggingFace, standing out in a field of 176,238 datasets as of July 11, 2024. See also the [Twitter by Salesforce CEO](https://x.com/Benioff/status/1808365628551844186), [VentureBeat](https://venturebeat.com/ai/salesforce-proves-less-is-more-xlam-1b-tiny-giant-beats-bigger-ai-models/) and [ζ°ζΊε
](https://mp.weixin.qq.com/s/B3gyaGwzlQaUXyI8n7Rguw).
- **[03.2024]** [xLAM Repository](https://github.com/SalesforceAIResearch/xLAM) and [xLAM Model](https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4) are released! Try it together with [AgentLite benchmark](https://github.com/SalesforceAIResearch/AgentLite/tree/main/benchmark) or other benchmarks, which is comparable to GPT-4! See also the [Paper](https://arxiv.org/pdf/2402.15506) and [Twitter by Salesforce AI Research VP](https://x.com/CaimingXiong/status/1769778308659708316).
- **[02.2024]** Initial Release of AgentOhana and xLAM [paper](https://arxiv.org/abs/2402.15506)!
- **[12.2023]** DialogStudio [GitHub](https://github.com/salesforce/DialogStudio) has garnered 400 stars. [Huggingface Data](https://huggingface.co/datasets/Salesforce/dialogstudio) has more than 55k downloads and was previously ranked among the Top-10 trending datasets. See also the [Paper](https://arxiv.org/pdf/2307.10172) and [Twitter](https://x.com/Yampeleg/status/1683012386381242368).