Searcharxiv⌕ Search

arXiv subjects

Taowen Wang

Publications and source records attributed to Taowen Wang.

21 records · Page 2Linked to original sources

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities. Instruction tuning has emerged as an effective strategy for achieving zero-shot generalization by finetuning pretrained models on diverse multimodal tasks. As the scale of MLLMs continues to grow, parameter-efficient finetuning becomes increasingly critical. However, most existing parameter-efficient approaches focus only on single modalities and often overlook the multimodal characteristics during finetuning. In this work, we introduce a novel Multimodal Prompt Tuning (M$^2$PT) approach for efficient instruction tuning of MLLMs. M$^2$PT effectively integrates visual and textual prompts into the vision encoder and language processor respectively during finetuning, facilitating the extraction and alignment of features across modalities. Empirical results on various multimodal evaluation datasets demonstrate the superior performance of our approach compared to several state-of-the-art baselines. A comprehensive set of ablation studies validates the effectiveness of our prompt design and the efficiency of our approach.

cs.AI↗

Inertial Confinement Fusion Forecasting via Large Language Models

Controlled fusion energy is deemed pivotal for the advancement of human civilization. In this study, we introduce $\textbf{LPI-LLM}$, a novel integration of Large Language Models (LLMs) with classical reservoir computing paradigms tailored to address a critical challenge, Laser-Plasma Instabilities ($\texttt{LPI}$), in Inertial Confinement Fusion ($\texttt{ICF}$). Our approach offers several key contributions: Firstly, we propose the $\textit{LLM-anchored Reservoir}$, augmented with a $\textit{Fusion-specific Prompt}$, enabling accurate forecasting of $\texttt{LPI}$-generated-hot electron dynamics during implosion. Secondly, we develop $\textit{Signal-Digesting Channels}$ to temporally and spatially describe the driver laser intensity across time, capturing the unique characteristics of $\texttt{ICF}$ inputs. Lastly, we design the $\textit{Confidence Scanner}$ to quantify the confidence level in forecasting, providing valuable insights for domain experts to design the $\texttt{ICF}$ process. Extensive experiments demonstrate the superior performance of our method, achieving 1.90 CAE, 0.14 $\texttt{top-1}$ MAE, and 0.11 $\texttt{top-5}$ MAE in predicting Hard X-ray ($\texttt{HXR}$) energies emitted by the hot electrons in $\texttt{ICF}$ implosions, which presents state-of-the-art comparisons against concurrent best systems. Additionally, we present $\textbf{LPI4AI}$, the first $\texttt{LPI}$ benchmark based on physical experiments, aimed at fostering novel ideas in $\texttt{LPI}$ research and enhancing the utility of LLMs in scientific exploration. Overall, our work strives to forge an innovative synergy between AI and $\texttt{ICF}$ for advancing fusion energy.

cs.LG↗

On the origin of tail states and VOC losses in Cu(In,Ga)Se2

The detrimental effect of tail states on the radiative and non-radiative voltage loss has been demonstrated to be a limiting factor for the open circuit voltage in Cu(In,Ga)Se2 solar cells. A strategy that has proven effective in reducing tail states is the addition of alkali metals, the effect of which has been associated with the passivation of charged defects at grain boundaries. Herein, tail states in Cu(In,Ga)Se2 are revisited by studying the effect of compositional variations and alkali incorporation into single crystals. The results demonstrate that alkalis decrease the density of tail states despite the absence of grain boundaries, suggesting that there is more to alkalis than just grain boundary effects. Moreover, an increase in doping as a result of alkali incorporation is shown to contribute to the reduced tail states, which are demonstrated to arise largely from electrostatic potential fluctuations and to be determined by grain interior properties. By analyzing the voltage loss in high-efficiency polycrystalline and single crystalline devices, this work presents a model that explains the entirety of the voltage loss in Cu(In,Ga)Se2 based on the combined effect of doping on tail states and VOC.

cond-mat.mtrl-sci↗