31 citations · 125 across the 11 of their papers we have counts for
12 papers
Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning
Bingjie Zhang, Yibo Yang, Qiantong Liu +3
Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing methods typically rely on fina…
Evolution of the dipole polarizability in the stable tin isotope chain
S. Bassauer, P. von Neumann-Cosel, P. -G. Reinhard +36
The dipole polarizability of stable even-mass tin isotopes 112,114,116,118,120,124 was extracted from inelastic proton scattering experiments at 295 MeV under very forward angles p…
Question Answering from Unstructured Text by Retrieval and Comprehension
Yusuke Watanabe, Bhuwan Dhingra, Ruslan Salakhutdinov
Open domain Question Answering (QA) systems must interact with external knowledge sources, such as web pages, to find relevant information. Information sources like Wikipedia, howe…
Domain Adaptation for Neural Networks by Parameter Augmentation
Yusuke Watanabe, Kazuma Hashimoto, Yoshimasa Tsuruoka
We propose a simple domain adaptation method for neural networks in a supervised setting. Supervised domain adaptation is a way of improving the generalization performance on the t…
A conjecture on independent sets and graph covers
Yusuke Watanabe
In this article, I present a conjecture on the number of independent sets on graph covers. I also show that the conjecture implies that the partition function of a binary pairwise…
Loopy Belief Propagation, Bethe Free Energy and Graph Zeta Function
Yusuke Watanabe, Kenji Fukumizu
We propose a new approach to the theoretical analysis of Loopy Belief Propagation (LBP) and the Bethe free energy (BFE) by establishing a formula to connect LBP and BFE with a grap…