ScVLM: a Vision-Language Model for Driving Safety Critical Event Understanding

Accurately identifying, understanding, and describing driving safety-critical events (SCEs), including crashes and near-crashes, is crucial for traffic safety, automated driving systems, and advanced driver assistance systems research and application. As SCEs are rare events, most general Vision-Language Models (VLMs) have not been trained sufficiently to link SCE videos and narratives, which could lead to hallucination and missing key safety characteristics. To tackle these challenges, we propose ScVLM, a hybrid approach that combines supervised learning and contrastive learning to improve driving video understanding and event description rationality for VLMs. The proposed approach is trained on and evaluated by more than 8,600 SCEs from the Second Strategic Highway Research Program Naturalistic Driving Study dataset, the largest publicly accessible driving dataset with videos and SCE annotations. The results demonstrate the superiority of the proposed approach in generating contextually accurate event descriptions and mitigate hallucinations from VLMs.

Large Étendue 3D Holographic Display with Content-adpative Dynamic Fourier Modulation

Emerging holographic display technology offers unique capabilities for next-generation virtual reality systems. Current holographic near-eye displays, however, only support a small \'etendue, which results in a direct tradeoff between achievable field of view and eyebox size. \'Etendue expansion has recently been explored, but existing approaches are either fundamentally limited in the image quality that can be achieved or they require extremely high-speed spatial light modulators. We describe a new \'etendue expansion approach that combines multiple coherent sources with content-adaptive amplitude modulation of the hologram spectrum in the Fourier plane. To generate time-multiplexed phase and amplitude patterns for our spatial light modulators, we devise a pupil-aware gradient-descent-based computer-generated holography algorithm that is supervised by a large-baseline target light field. Compared with relevant baseline approaches, our method demonstrates significant improvements in image quality and \'etendue in simulation and with an experimental holographic display prototype.

A Survey on Employing Large Language Models for Text-to-SQL Tasks

The increasing volume of data stored in relational databases has led to the need for efficient querying and utilization of this data in various sectors. However, writing SQL queries requires specialized knowledge, which poses a challenge for non-professional users trying to access and query databases. Text-to-SQL parsing solves this issue by converting natural language queries into SQL queries, thus making database access more accessible for non-expert users. To take advantage of the recent developments in Large Language Models (LLMs), a range of new methods have emerged, with a primary focus on prompt engineering and fine-tuning. This survey provides a comprehensive overview of LLMs in text-to-SQL tasks, discussing benchmark datasets, prompt engineering, fine-tuning methods, and future research directions. We hope this review will enable readers to gain a broader understanding of the recent advances in this field and offer some insights into its future trajectory.

Anonymization Prompt Learning for Facial Privacy-Preserving Text-to-Image Generation

Text-to-image diffusion models, such as Stable Diffusion, generate highly realistic images from text descriptions. However, the generation of certain content at such high quality raises concerns. A prominent issue is the accurate depiction of identifiable facial images, which could lead to malicious deepfake generation and privacy violations. In this paper, we propose Anonymization Prompt Learning (APL) to address this problem. Specifically, we train a learnable prompt prefix for text-to-image diffusion models, which forces the model to generate anonymized facial identities, even when prompted to produce images of specific individuals. Extensive quantitative and qualitative experiments demonstrate the successful anonymization performance of APL, which anonymizes any specific individuals without compromising the quality of non-identity-specific image generation. Furthermore, we reveal the plug-and-play property of the learned prompt prefix, enabling its effective application across different pretrained text-to-image models for transferrable privacy and security protection against the risks of deepfakes.

Real Face Foundation Representation Learning for Generalized Deepfake Detection

The emergence of deepfake technologies has become a matter of social concern as they pose threats to individual privacy and public security. It is now of great significance to develop reliable deepfake detectors. However, with numerous face manipulation algorithms present, it is almost impossible to collect sufficient representative fake faces, and it is hard for existing detectors to generalize to all types of manipulation. Therefore, we turn to learn the distribution of real faces, and indirectly identify fake images that deviate from the real face distribution. In this study, we propose Real Face Foundation Representation Learning (RFFR), which aims to learn a general representation from large-scale real face datasets and detect potential artifacts outside the distribution of RFFR. Specifically, we train a model on real face datasets by masked image modeling (MIM), which results in a discrepancy between input faces and the reconstructed ones when applying the model on fake samples. This discrepancy reveals the low-level artifacts not contained in RFFR, making it easier to build a deepfake detector sensitive to all kinds of potential artifacts outside the distribution of RFFR. Extensive experiments demonstrate that our method brings about better generalization performance, as it significantly outperforms the state-of-the-art methods in cross-manipulation evaluations, and has the potential to further improve by introducing extra real faces for training RFFR.

Computational Discovery of Microstructured Composites with Optimal Strength-Toughness Trade-Offs

The conflict between strength and toughness is a fundamental problem in engineering materials design. However, systematic discovery of microstructured composites with optimal strength-toughness trade-offs has never been demonstrated due to the discrepancies between simulation and reality and the lack of data-efficient exploration of the entire Pareto front. Here, we report a widely applicable pipeline harnessing physical experiments, numerical simulations, and artificial neural networks to efficiently discover microstructured designs that are simultaneously tough and strong. Using a physics-based simulator with moderate complexity, our strategy runs a data-driven proposal-validation workflow in a nested-loop fashion to bridge the gap between simulation and reality in high sample efficiency. Without any prescribed expert knowledge of materials design, our approach automatically identifies existing toughness enhancement mechanisms that were traditionally discovered through trial-and-error or biomimicry. We provide a blueprint for the computational discovery of optimal designs, which inverts traditional scientific approaches, and is applicable to a wide range of research problems beyond composites, including polymer chemistry, fluid dynamics, meteorology, and robotics.

MSRL: Distributed Reinforcement Learning with Dataflow Fragments

Reinforcement learning~(RL) trains many agents, which is resource-intensive and must scale to large GPU clusters. Different RL training algorithms offer different opportunities for distributing and parallelising the computation. Yet, current distributed RL systems tie the definition of RL algorithms to their distributed execution: they hard-code particular distribution strategies and only accelerate specific parts of the computation (e.g. policy network updates) on GPU workers. Fundamentally, current systems lack abstractions that decouple RL algorithms from their execution. We describe MindSpore Reinforcement Learning (MSRL), a distributed RL training system that supports distribution policies that govern how RL training computation is parallelised and distributed on cluster resources, without requiring changes to the algorithm implementation. MSRL introduces the new abstraction of a fragmented dataflow graph, which maps Python functions from an RL algorithm's training loop to parallel computational fragments. Fragments are executed on different devices by translating them to low-level dataflow representations, e.g. computational graphs as supported by deep learning engines, CUDA implementations or multi-threaded CPU processes. We show that MSRL subsumes the distribution strategies of existing systems, while scaling RL training to 64 GPUs.

A photonic chip-based machine learning approach for the prediction of molecular properties

Machine learning methods have revolutionized the discovery process of new molecules and materials. However, the intensive training process of neural networks for molecules with ever increasing complexity has resulted in exponential growth in computation cost, leading to long simulation time and high energy consumption. Photonic chip technology offers an alternative platform for implementing neural network with faster data processing and lower energy usage compared to digital computers. Here, we demonstrate the capability of photonic neural networks in predicting the quantum mechanical properties of molecules. Additionally, we show that multiple properties can be learned simultaneously in a photonic chip via a multi-task regression learning algorithm, which we believe is the first of its kind, as most previous works focus on implementing a network for the task of classification. Photonics technology are also naturally capable of implementing complex-valued neural networks at no additional hardware cost and we show that such neural networks outperform conventional real-valued networks for molecular property prediction. Our work opens the avenue for harnessing photonic technology for large-scale machine learning applications in molecular sciences such as drug discovery and materials design.

Pre-trained Model for Chinese Word Segmentation with Meta Learning

Recent researches show that pre-trained models such as BERT (Devlin et al., 2019) are beneficial for Chinese Word Segmentation tasks. However, existing approaches usually finetune pre-trained models directly on a separate downstream Chinese Word Segmentation corpus. These recent methods don't fully utilize the prior knowledge of existing segmentation corpora, and don't regard the discrepancy between the pre-training tasks and the downstream Chinese Word Segmentation tasks. In this work, we propose a Pre-Trained Model for Chinese Word Segmentation, which can be abbreviated as PTM-CWS. PTM-CWS model employs a unified architecture for different segmentation criteria, and is pre-trained on a joint multi-criteria corpus with meta learning algorithm. Empirical results show that our PTM-CWS model can utilize the existing prior segmentation knowledge, reduce the discrepancy between the pre-training tasks and the downstream Chinese Word Segmentation tasks, and achieve new state-of-the-art performance on twelve Chinese Word Segmentation corpora.

Unified Multi-Criteria Chinese Word Segmentation with BERT

Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word boundaries in a Chinese sentence composed of continuous characters while multiple segmentation criteria exist. The unified framework has been widely used in MCCWS and shows its effectiveness. Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework. In this paper, we combine the superiority of the unified framework and pretrained language model, and propose a unified MCCWS model based on BERT. Moreover, we augment the unified BERT-based MCCWS model with the bigram features and an auxiliary criterion classification task. Experiments on eight datasets with diverse criteria demonstrate that our methods could achieve new state-of-the-art results for MCCWS.