Tom Hope
@Hoper_Tom
Followers
1K
Following
1K
Media
52
Statuses
517
Assistant professor and research scientist at AI2 | boosting scientific discovery with AI, NLP, IR, KG, HCI
Joined April 2011
Scimon🧪: Scientific Inspiration Machines Optimized for Novelty. LLMs + inspiration retrieval from papers + 🚀iterative novelty boosting🚀: .1. LLM (e.g. GPT4) generates idea .2. Compares to detected prior work.3. Refines idea novelty.4. Repeat until sufficient novelty reached.
5
24
102
RT @NoySternlicht: 🔔 New Paper!.We propose a challenging new benchmark for LLM judges: Evaluating debate speeches. Are they comparable to h….
0
15
0
RT @NoySternlicht: 7/7.Led with the guidance of @Hoper_Tom — thank you!. Paper - Project page - .
github.com
Official implementation of the paper "CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature" - noy-sternlicht/CHIMERA-KB
0
1
0
RT @NoySternlicht: 🚨 New paper!.We present CHIMERA — a KB of 28K+ scientific idea recombinations 💡. It captures how researchers blend conce….
0
22
0
RT @marissa_rad: We're seeking CS researchers to participate in a study on working with AI tools to come up with research project ideas!….
docs.google.com
We are a group of researchers from the Allen Institute for AI and University of Washington conducting a study to investigate how computer-science researchers work with AI tools to come up with...
0
8
0
RT @allen_ai: We’re excited to share some updates to Ai2 ScholarQA:.🗂️ You can now sign in via Google to save your query history across dev….
0
37
0
RT @marinkazitnik: Excited to share our latest on multimodal AI and agents for drug design and therapeutic reasoning #AAAI2025 @RealAAAI. 📅….
ai-2-ase.github.io
0
11
0
RT @kevpjk: 🔬Research ideation is hard: After the spark of a brilliant initial idea, much work is still needed to further develop it into a….
0
83
0
Join our workshop on scientific discovery with AI! Deadline EOM.
Some of our amazing teammates are organizing this exciting workshop for NAACL 2025 — submit your papers by January 30! 🎉.
0
1
12
RT @allen_ai: Some of our amazing teammates are organizing this exciting workshop for NAACL 2025 — submit your papers by January 30! 🎉.
0
32
0
RT @bhavana_dalvi: We (@peterjansen_ai, @mbodhisattwa, @tusharkhot,.@harsh3vedi, @Hoper_Tom, @_DougDowney, @erichorvitz) are excited to ann….
0
11
0
RT @eagle_hz: Excited to see many AI4Research papers at #EMNLP2024. If you want to learn more, join us at AAAI 2025 for the Second AI4Resea….
0
15
0
RT @MSheshera: Friends and colleagues! I'm on the academic job market in Fall 24/Spring 25. My research intersects NLP, IR, and HCI and I….
0
17
0
Join our workshop on AI for research! With invited speakers @hengjinlp @_DougDowney @jeffclune @marinkazitnik @WeiWang1973 @aviadlevis.
🚀 [CFP] Join Us at AAAI 2025 for the Second AI4Research Workshop! 🧪. Are you exploring cutting-edge research in an AI-assisted scientific research lifecycle? Do you want to uncover potential "hidden gems" and "sleeping beauties" in scientific literature? Our full-day workshop
0
10
24
Fascinating commentary @sannnnnnnaz ! Great to see engagment with our conceptual framework on human-AI scientific discovery (e.g., inner-outer world interfaces).
Two new commentaries out! .The first is in American Psychologist, where we provide a brief workflow for LLM-assisted hypothesis generation. (w/ Alejandro Hermida Carillo and @ClemensStachl) .
0
1
6
RT @sannnnnnnaz: Two new commentaries out! .The first is in American Psychologist, where we provide a brief workflow for LLM-assisted hypot….
0
10
0
Thanks @IntuitMachine for sharing our work on literature-based human-AI discovery!.
1/n Scideator: A Novel Tool for Scientific Ideation. The relentless pursuit of novel scientific ideas fuels progress and innovation. However, the very process of ideation, of conceiving new research directions, presents significant challenges for researchers. Navigating the
0
3
13
RT @PMinervini: My understanding is that @OpenAI heavily use @WecoAI's codebase (AIDE, without giving proper credi….
github.com
AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D. - WecoAI/aideml
0
4
0
@Sandeepiitp @TirthankarSlg I believe your "Idea Alignment", measuring how an LLM-proposed scientific idea aligns with the actual idea in the original paper, is also strongly related to this paper (I don't think it was mentioned/cited though).
Thanks for sharing our paper. We further conducted a human evaluation on computer science and found that LLMs have the potential to generate relevant, distinct, feasible, and novel ideas to some extent.
3
0
3