Zobrazeno 1 - 10
of 7 375
pro vyhledávání: '"LIN, YONG"'
We review the status of baryon form factors with a special focus on the nucleon electromagnetic form factors which are known best. First, we give an introduction into the dispersive analyses and emphasize the role of unitarity and analyticity in the
Externí odkaz:
http://arxiv.org/abs/2412.12885
Autor:
Zhang, Hanning, Wang, Pengcheng, Diao, Shizhe, Lin, Yong, Pan, Rui, Dong, Hanze, Zhang, Dylan, Molchanov, Pavlo, Zhang, Tong
Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL) guided by rewar
Externí odkaz:
http://arxiv.org/abs/2412.11006
Autor:
Lin, Yong, Seto, Skyler, ter Hoeve, Maartje, Metcalf, Katherine, Theobald, Barry-John, Wang, Xuan, Zhang, Yizhe, Huang, Chen, Zhang, Tong
Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to RLHF is learning a reward function for scoring human preferences. Two main approaches for learning a reward model
Externí odkaz:
http://arxiv.org/abs/2409.03650
Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing arithmetic operati
Externí odkaz:
http://arxiv.org/abs/2408.13656
Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbor patterns, exhibiting local n
Externí odkaz:
http://arxiv.org/abs/2408.09490
In this paper, we first define a discrete version of the fractional Laplace operator $(-\Delta)^{s}$ through the heat semigroup on a stochastically complete, connected, locally finite graph $G = (V, E, \mu, w)$. Secondly, we define the fractional div
Externí odkaz:
http://arxiv.org/abs/2408.02902
We investigate the feasibility of measuring the proton charge radius through dimuon photoproduction off a proton target. Our findings indicate that the Bethe-Heitler mechanism, which dominates at small momentum transfers, allows for an extraction of
Externí odkaz:
http://arxiv.org/abs/2407.20375
Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models have limited
Externí odkaz:
http://arxiv.org/abs/2406.10216
This paper aims to compute and estimate the eigenvalues of the Hodge Laplacians on directed graphs. We have devised a new method for computing Hodge spectra with the following two ingredients. (I) We have observed that the product rule does work for
Externí odkaz:
http://arxiv.org/abs/2406.09814
Underwater Image Enhancement (UIE) is critical for marine research and exploration but hindered by complex color distortions and severe blurring. Recent deep learning-based methods have achieved remarkable results, yet these methods struggle with hig
Externí odkaz:
http://arxiv.org/abs/2406.08444