Personal llm agents: Insights and survey about the capability, efficiency and security

Y Li, H Wen, W Wang, X Li, Y Yuan, G Liu, J Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Since the advent of personal computing devices, intelligent personal assistants (IPAs) have
been one of the key technologies that researchers and engineers have focused on, aiming …

Mathverse: Does your multi-modal llm truly see the diagrams in visual math problems?

R Zhang, D Jiang, Y Zhang, H Lin, Z Guo, P Qiu… - arXiv preprint arXiv …, 2024 - arxiv.org
The remarkable progress of Multi-modal Large Language Models (MLLMs) has garnered
unparalleled attention, due to their superior performance in visual contexts. However, their …

Mavis: Mathematical visual instruction tuning

R Zhang, X Wei, D Jiang, Y Zhang, Z Guo… - arXiv preprint arXiv …, 2024 - arxiv.org
Multi-modal Large Language Models (MLLMs) have recently emerged as a significant focus
in academia and industry. Despite their proficiency in general multi-modal scenarios, the …

Referred by multi-modality: A unified temporal transformer for video object segmentation

S Yan, R Zhang, Z Guo, W Chen, W Zhang… - Proceedings of the …, 2024 - ojs.aaai.org
Recently, video object segmentation (VOS) referred by multi-modal signals, eg, language
and audio, has evoked increasing attention in both industry and academia. It is challenging …

Integrating large language models into recommendation via mutual augmentation and adaptive aggregation

S Luo, Y Yao, B He, Y Huang, A Zhou, X Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Conventional recommendation methods have achieved notable advancements by
harnessing collaborative or sequential information from user behavior. Recently, large …

Scaling synthetic data creation with 1,000,000,000 personas

X Chan, X Wang, D Yu, H Mi, D Yu - arXiv preprint arXiv:2406.20094, 2024 - arxiv.org
We propose a novel persona-driven data synthesis methodology that leverages various
perspectives within a large language model (LLM) to create diverse synthetic data. To fully …

Reft: Reasoning with reinforced fine-tuning

TQ Luong, X Zhang, Z Jie, P Sun, X Jin, H Li - arXiv preprint arXiv …, 2024 - arxiv.org
One way to enhance the reasoning capability of Large Language Models (LLMs) is to
conduct Supervised Fine-Tuning (SFT) using Chain-of-Thought (CoT) annotations. This …

Step-dpo: Step-wise preference optimization for long-chain reasoning of llms

X Lai, Z Tian, Y Chen, S Yang, X Peng, J Jia - arXiv preprint arXiv …, 2024 - arxiv.org
Mathematical reasoning presents a significant challenge for Large Language Models
(LLMs) due to the extensive and precise chain of reasoning required for accuracy. Ensuring …

Mathgenie: Generating synthetic data with question back-translation for enhancing mathematical reasoning of llms

Z Lu, A Zhou, H Ren, K Wang, W Shi, J Pan… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have exhibited great potential in mathematical reasoning.
However, there remains a performance gap in this area between existing open-source …

A survey of neural code intelligence: Paradigms, advances and beyond

Q Sun, Z Chen, F Xu, K Cheng, C Ma, Z Yin… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural Code Intelligence--leveraging deep learning to understand, generate, and optimize
code--holds immense potential for transformative impacts on the whole society. Bridging the …