Daniel Weld
@dsweld
Followers
3K
Following
1K
Media
12
Statuses
1K
Computer science prof & entrepreneur. Excited by crowdsourcing, computational/social systems, MOOCs, relation extraction and Web-scale NLP.
Seattle, WA
Joined March 2009
RT @WeijiaShi2: Can data owners & LM developers collaborate to build a strong shared model while each retaining data control?. Introducing….
0
82
0
RT @__JohnNguyen__: AI2 Paper Finder and AI2 ScholarQA are the best tools for finding related works. I'm surprised they aren't more popular….
0
4
0
Need someone (or something!) to amplify the speed of your ML/NLP experimentation rate?.
Imagine AI doing science: reading papers, generating ideas, designing and running experiments, analyzing results… How many more discoveries can we reveal? 🧐. Meet CodeScientist, a promising next step toward autonomous scientific discovery. 🧵
0
0
7
Use the power of LLMs to find academic papers for your hardest queries!.
Meet Ai2 Paper Finder, an LLM-powered literature search system. Searching for relevant work is a multi-step process that requires iteration. Paper Finder mimics this workflow — and helps researchers find more papers than ever 🔍
0
3
18
Try our new scientific question answering system!.
Can AI really help with literature reviews? 🧐. Meet Ai2 ScholarQA, an experimental solution that allows you to ask questions that require multiple scientific papers to answer. It gives more in-depth, detailed, and contextual answers with table comparisons, expandable sections
1
0
14
This is still experimental, but . really cool! Try it!.
Joint work with @aps6992 @arnaik19 @SergeyFeldman @Siangliulue @kylelostat @_DougDowney @dsweld and more. Please check it out and give us feedback : ).
0
0
0
RT @josephcc: Joint work with @aps6992 @arnaik19 @SergeyFeldman @Siangliulue @kylelostat @_DougDowney @dsweld and more. Please check it o….
0
4
0
More great work by FutureHouse!.
Finishing 2024 with one more research result! We’ve trained small language agents to do hard sci tasks: engineering proteins, manipulating DNA, and working with sci literature in a new library called Aviary. We beat humans and frontier LLMs on these tasks!
0
0
4
Nice work on a method and UI for human-ai teaming!.Task is the process of performing scientific research, but technique is general. With @kjfeng_ @josephcc @amyxzh and many more.
arxiv.org
Human collaboration benefits from continuous coordination -- planning, delegating tasks, sharing progress, and adjusting objectives -- to align on shared goals. However, agentic AI systems often...
0
4
34
Curious people's reaction to this. How should one design for effective human-AI communication?.
☀️Excited to share our new paper!. Generative AI agents are powerful but complex—how do we design them for transparency and human control? 🤖✨. At the heart of this challenge is establishing common ground, a concept from human communication. Our new paper identifies 12 key
0
0
9
RT @AkariAsai: 3/ 🔍 What is OpenScholar?.It's a retrieval-augmented LM with.1️⃣ a datastore of 45M+ open-access papers.2️⃣ a specialized re….
0
8
0
Very cool scientific QA system - try it!.
1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 @uwnlp @allen_ai .With open models & 45M-paper datastores, it outperforms proprietary systems & match human experts. Try out our demo!.We also introduce ꜱᴄʜᴏʟᴀʀQᴀʙᴇɴᴄʜ,
0
0
2
