Zobrazeno 1 - 10
of 57 972
pro vyhledávání: '"WANG, Qi"'
Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends t
Externí odkaz:
http://arxiv.org/abs/2411.13949
The abundant chemical compositions in ternary hydrides bring much more possibility to explore high temperature superconductors under lower pressure. Here we constructed 115 ternary hydrides on the basis of the elements substitution using 16 metal ele
Externí odkaz:
http://arxiv.org/abs/2411.11674
Autor:
Wu, Xinhua, Wang, Qi R.
As large language models (LLMs) are increasingly applied in areas influencing societal outcomes, it is critical to understand their tendency to perpetuate and amplify biases. This study investigates whether LLMs exhibit biases in predicting human mob
Externí odkaz:
http://arxiv.org/abs/2411.14469
Autor:
Wang, Qi, Zhou, Jinjia
We propose a novel and efficient logit distillation method, Multi-perspective Contrastive Logit Distillation (MCLD), which leverages contrastive learning to distill logits from multiple perspectives in knowledge distillation. Recent research on logit
Externí odkaz:
http://arxiv.org/abs/2411.10693
Autor:
Pei, Cuiying, Zhang, Mingxin, Peng, Di, Huangfu, Shangxiong, Zhu, Shihao, Wang, Qi, Wu, Juefei, Xing, Zhenfang, Zhang, Lili, Chen, Yulin, Zhao, Jinkui, Yang, Wenge, Suo, Hongli, Guo, Hanjie, Zeng, Qiaoshi, Qi, Yanpeng
The recent discovery of superconductivity in pressurized Ruddlesden-Popper (RP) of nickelates has potential similarities with cuprate superconductors, which may provide unique perspectives on the mechanisms of high-temperature superconductivity. Up t
Externí odkaz:
http://arxiv.org/abs/2411.08677
Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (
Externí odkaz:
http://arxiv.org/abs/2411.07934
Texts on the intelligent transportation scene include mass information. Fully harnessing this information is one of the critical drivers for advancing intelligent transportation. Unlike the general scene, detecting text in transportation has extra de
Externí odkaz:
http://arxiv.org/abs/2411.02794
The Gardner transition in structural glasses is characterized by full-replica symmetry breaking of the free-energy landscape and the onset of anomalous aging dynamics due to marginal stability. Here we show that this transition also has a structural
Externí odkaz:
http://arxiv.org/abs/2410.23797
Meta learning is a promising paradigm in the era of large models and task distributional robustness has become an indispensable consideration in real-world scenarios. Recent advances have examined the effectiveness of tail task risk minimization in f
Externí odkaz:
http://arxiv.org/abs/2410.22788
Autor:
Wang, Qi, Ren, Pu, Zhou, Hao, Liu, Xin-Yang, Deng, Zhiwen, Zhang, Yi, Chengze, Ruizhi, Liu, Hongsheng, Wang, Zidong, Wang, Jian-Xun, Ji-Rong_Wen, Sun, Hao, Liu, Yang
When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergence conditions, leading to high computational cost. Recently, machine le
Externí odkaz:
http://arxiv.org/abs/2411.00040