Yuxin He

Yuxin He, An Li, Cheng Xue

Surgical phase recognition is a critical component for context-aware decision support in intelligent operating rooms, yet training robust models is hindered by limited annotated clinical videos and large domain gaps between synthetic and real surgical data. To address this, we propose CauCLIP, a causality-inspired vision-language framework that leverages CLIP to learn domain-invariant representations for surgical phase recognition without access to target domain data. Our approach integrates a frequency-based augmentation strategy to perturb domain-specific attributes while preserving semantic structures, and a causal suppression loss that mitigates non-causal biases and reinforces causal surgical features. These components are combined in a unified training framework that enables the model to focus on stable causal factors underlying surgical workflows. Experiments on the SurgVisDom hard adaptation benchmark demonstrate that our method substantially outperforms all competing approaches, highlighting the effectiveness of causality-guided vision-language models for domain-generalizable surgical video understanding.

Chen Chen, Yuxin He, Hao Wang et al.

Train delays can propagate rapidly throughout the Urban Rail Transit (URT) network under networked operation conditions, posing significant challenges to operational departments. Accurately predicting passenger travel choices under train delays can provide interpretable insights into the redistribution of passenger flow, offering crucial decision support for emergency response and service recovery. However, the diversity of travel choices due to passenger heterogeneity and the sparsity of delay events leads to issues of data sparsity and sample imbalance in the travel choices dataset under metro delays. It is challenging to model this problem using traditional machine learning approaches, which typically rely on large, balanced datasets. Given the strengths of large language models (LLMs) in text processing, understanding, and their capabilities in small-sample and even zero-shot learning, this paper proposes a novel Passenger Travel Choice prediction framework under metro delays with the Large Language Model (DelayPTC-LLM). The well-designed prompting engineering is developed to guide the LLM in making and rationalizing predictions about travel choices, taking into account passenger heterogeneity and features of the delay events. Utilizing real-world data from Shenzhen Metro, including Automated Fare Collection (AFC) data and detailed delay logs, a comparative analysis of DelayPTC-LLM with traditional prediction models demonstrates the superior capability of LLMs in handling complex, sparse datasets commonly encountered under disruption of transportation systems. The results validate the advantages of DelayPTC-LLM in terms of predictive accuracy and its potential to provide actionable insights for big traffic data.

Xiaobao Song, Hao Wang, Liwei Deng et al.

Time position embeddings capture the positional information of time steps, often serving as auxiliary inputs to enhance the predictive capabilities of time series models. However, existing models exhibit limitations in capturing intricate time positional information and effectively utilizing these embeddings. To address these limitations, this paper proposes a novel model called D2Vformer. Unlike typical prediction methods that rely on RNNs or Transformers, this approach can directly handle scenarios where the predicted sequence is not adjacent to the input sequence or where its length dynamically changes. In comparison to conventional methods, D2Vformer undoubtedly saves a significant amount of training resources. In D2Vformer, the Date2Vec module uses the timestamp information and feature sequences to generate time position embeddings. Afterward, D2Vformer introduces a new fusion block that utilizes an attention mechanism to explore the similarity in time positions between the embeddings of the input sequence and the predicted sequence, thereby generating predictions based on this similarity. Through extensive experiments on six datasets, we demonstrate that Date2Vec outperforms other time position embedding methods, and D2Vformer surpasses state-of-the-art methods in both fixed-length and variable-length prediction tasks.

Junhao Cheng, Baiqiao Yin, Kaixin Cai et al.

Recent advances in diffusion models can generate high-quality and stunning images from text. However, multi-turn image generation, which is of high demand in real-world scenarios, still faces challenges in maintaining semantic consistency between images and texts, as well as contextual consistency of the same subject across multiple interactive turns. To address this issue, we introduce TheaterGen, a training-free framework that integrates large language models (LLMs) and text-to-image (T2I) models to provide the capability of multi-turn image generation. Within this framework, LLMs, acting as a "Screenwriter", engage in multi-turn interaction, generating and managing a standardized prompt book that encompasses prompts and layout designs for each character in the target image. Based on these, Theatergen generate a list of character images and extract guidance information, akin to the "Rehearsal". Subsequently, through incorporating the prompt book and guidance information into the reverse denoising process of T2I diffusion models, Theatergen generate the final image, as conducting the "Final Performance". With the effective management of prompt books and character images, TheaterGen significantly improves semantic and contextual consistency in synthesized images. Furthermore, we introduce a dedicated benchmark, CMIGBench (Consistent Multi-turn Image Generation Benchmark) with 8000 multi-turn instructions. Different from previous multi-turn benchmarks, CMIGBench does not define characters in advance. Both the tasks of story generation and multi-turn editing are included on CMIGBench for comprehensive evaluation. Extensive experimental results show that TheaterGen outperforms state-of-the-art methods significantly. It raises the performance bar of the cutting-edge Mini DALLE 3 model by 21% in average character-character similarity and 19% in average text-image similarity.