open-thoughts/OpenThinker3-7B
Text Generation
•
Updated
•
273
•
36
Di Zhang
di-zhang-fdu
AI & ML interests
AI4Chem, LLM, Green LLM
Recent Activity
liked
a model
about 6 hours ago
open-thoughts/OpenThinker3-7B
upvoted
a
paper
about 7 hours ago
Control-R: Towards controllable test-time scaling
upvoted
a
paper
about 7 hours ago
AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual
Counting for MLLMs
Organizations
di-zhang-fdu's activity
liked
a
model
about 6 hours ago
upvoted
2
papers
about 7 hours ago
updated
a
dataset
2 days ago
commented
a
paper
2 days ago
published
a
dataset
2 days ago
upvoted
a
paper
3 days ago
updated
a
dataset
7 days ago
published
a
dataset
7 days ago
liked
a
model
8 days ago
liked
2
datasets
8 days ago
updated
a
dataset
9 days ago
published
a
dataset
9 days ago
liked
a
dataset
9 days ago
liked
2
models
9 days ago
authored
a
paper
11 days ago
posted
an
update
12 days ago
Post
326
Our new paper Moose-chem 3 introduces experiment-guided hypothesis ranking, a novel setting where candidate hypotheses are prioritized based on experimental feedback from previously tested hypotheses.
To support research in this area, the work proposes a simulator grounded in three domain-informed assumptions that can generate simulated experimental feedback without requiring costly real-world trials.
The simulator is validated on a curated dataset of 124 chemistry hypotheses, and the resulting method outperforms strong pre-experiment baselines. This enables scalable research on feedback-driven hypothesis discovery strategies in scientific domains where empirical validation is expensive or slow.
MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback (2505.17873)
To support research in this area, the work proposes a simulator grounded in three domain-informed assumptions that can generate simulated experimental feedback without requiring costly real-world trials.
The simulator is validated on a curated dataset of 124 chemistry hypotheses, and the resulting method outperforms strong pre-experiment baselines. This enables scalable research on feedback-driven hypothesis discovery strategies in scientific domains where empirical validation is expensive or slow.
MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback (2505.17873)
commented
a
paper
12 days ago