C-FAITH: A Chinese Fine-Grained Benchmark for Automated Hallucination Evaluation

Despite the rapid advancement of large language models, they remain highly susceptible to generating hallucinations, which significantly hinders their widespread application. Hallucination research requires dynamic and fine-grained evaluation. However, most existing hallucination benchmarks (especially in Chinese language) rely on human annotations, making automatical and cost-effective hallucination evaluation challenging. To address this, we introduce HaluAgent, an agentic framework that automatically constructs fine-grained QA dataset based on some knowledge documents. Our experiments demonstrate that the manually designed rules and prompt optimization can improve the quality of generated data. Using HaluAgent, we construct C-FAITH, a Chinese QA hallucination benchmark created from 1,399 knowledge documents obtained from web scraping, totaling 60,702 entries. We comprehensively evaluate 16 mainstream LLMs with our proposed C-FAITH, providing detailed experimental results and analysis.

Pay More Attention to the Robustness of Prompt for Instruction Data Mining

Instruction tuning has emerged as a paramount method for tailoring the behaviors of LLMs. Recent work has unveiled the potential for LLMs to achieve high performance through fine-tuning with a limited quantity of high-quality instruction data. Building upon this approach, we further explore the impact of prompt's robustness on the selection of high-quality instruction data. This paper proposes a pioneering framework of high-quality online instruction data mining for instruction tuning, focusing on the impact of prompt's robustness on the data mining process. Our notable innovation, is to generate the adversarial instruction data by conducting the attack for the prompt of online instruction data. Then, we introduce an Adversarial Instruction-Following Difficulty metric to measure how much help the adversarial instruction data can provide to the generation of the corresponding response. Apart from it, we propose a novel Adversarial Instruction Output Embedding Consistency approach to select high-quality online instruction data. We conduct extensive experiments on two benchmark datasets to assess the performance. The experimental results serve to underscore the effectiveness of our proposed two methods. Moreover, the results underscore the critical practical significance of considering prompt's robustness.

MAVERIX: Multimodal Audio-Visual Evaluation Reasoning IndeX

Frontier models have either been language-only or have primarily focused on vision and language modalities. Although recent advancements in models with vision and audio understanding capabilities have shown substantial progress, the field lacks a standardized evaluation framework for thoroughly assessing their cross-modality perception performance. We introduce MAVERIX~(Multimodal Audio-Visual Evaluation Reasoning IndeX), a novel benchmark with 700 videos and 2,556 questions explicitly designed to evaluate multimodal models through tasks that necessitate close integration of video and audio information. MAVERIX uniquely provides models with audiovisual tasks, closely mimicking the multimodal perceptual experiences available to humans during inference and decision-making processes. To our knowledge, MAVERIX is the first benchmark aimed explicitly at assessing comprehensive audiovisual integration. Experiments with state-of-the-art models, including Gemini 1.5 Pro and o1, show performance approaching human levels (around 70% accuracy), while human experts reach near-ceiling performance (95.1%). With standardized evaluation protocols, a rigorously annotated pipeline, and a public toolkit, MAVERIX establishes a challenging testbed for advancing audiovisual multimodal intelligence.

Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with many approaches building upon the framework that maintains a pool of learnable prompts. Although effective, these methods introduce substantial computational overhead, primarily due to prompt pool querying and increased input sequence lengths from prompt concatenation. In this work, we present a novel prompt-based approach that addresses this limitation. Our method trains a single set of shared prompts across all tasks and, rather than concatenating prompts to the input, directly modifies the CLS token's attention computation by adding the prompts to it. This simple and lightweight design not only significantly reduces computational complexity-both in terms of inference costs and the number of trainable parameters-but also eliminates the need to optimize prompt lengths for different downstream tasks, offering a more efficient yet powerful solution for rehearsal-free class-incremental learning. Extensive experiments across a diverse range of CIL benchmarks demonstrate the effectiveness of our approach, highlighting its potential to establish a new prompt-based CIL paradigm. Furthermore, experiments on general recognition benchmarks beyond the CIL setting also show strong performance, positioning our method as a promising candidate for a general parameter-efficient fine-tuning approach.

AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP

Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capabilities, its inherent Anomaly-Unawareness leads to limited discrimination between normal and abnormal features. To address this problem, we propose Anomaly-Aware CLIP (AA-CLIP), which enhances CLIP's anomaly discrimination ability in both text and visual spaces while preserving its generalization capability. AA-CLIP is achieved through a straightforward yet effective two-stage approach: it first creates anomaly-aware text anchors to differentiate normal and abnormal semantics clearly, then aligns patch-level visual features with these anchors for precise anomaly localization. This two-stage strategy, with the help of residual adapters, gradually adapts CLIP in a controlled manner, achieving effective AD while maintaining CLIP's class knowledge. Extensive experiments validate AA-CLIP as a resource-efficient solution for zero-shot AD tasks, achieving state-of-the-art results in industrial and medical applications. The code is available at https://github.com/Mwxinnn/AA-CLIP.

Chemical knowledge-informed framework for privacy-aware retrosynthesis learning

Chemical reaction data is a pivotal asset, driving advances in competitive fields such as pharmaceuticals, materials science, and industrial chemistry. Its proprietary nature renders it sensitive, as it often includes confidential insights and competitive advantages organizations strive to protect. However, in contrast to this need for confidentiality, the current standard training paradigm for machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models. This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries and frequent data transmission between entities, potentially exposing proprietary information to unauthorized access or interception during storage and transfer. In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models. CKIF enables distributed training across multiple chemical organizations without compromising the confidentiality of proprietary reaction data. Instead of gathering raw reaction data, CKIF learns retrosynthesis models through iterative, chemical knowledge-informed aggregation of model parameters. In particular, the chemical properties of predicted reactants are leveraged to quantitatively assess the observable behaviors of individual models, which in turn determines the adaptive weights used for model aggregation. On a variety of reaction datasets, CKIF outperforms several strong baselines by a clear margin (e.g., ~20% performance improvement over FedAvg on USPTO-50K), showing its feasibility and superiority to stimulate further research on privacy-preserving retrosynthesis.

A Low-cost and Ultra-lightweight Binary Neural Network for Traffic Signal Recognition

The deployment of neural networks in vehicle platforms and wearable Artificial Intelligence-of-Things (AIOT) scenarios has become a research area that has attracted much attention. With the continuous evolution of deep learning technology, many image classification models are committed to improving recognition accuracy, but this is often accompanied by problems such as large model resource usage, complex structure, and high power consumption, which makes it challenging to deploy on resource-constrained platforms. Herein, we propose an ultra-lightweight binary neural network (BNN) model designed for hardware deployment, and conduct image classification research based on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. In addition, we also verify it on the Chinese Traffic Sign (CTS) and Belgian Traffic Sign (BTS) datasets. The proposed model shows excellent recognition performance with an accuracy of up to 97.64%, making it one of the best performing BNN models in the GTSRB dataset. Compared with the full-precision model, the accuracy loss is controlled within 1%, and the parameter storage overhead of the model is only 10% of that of the full-precision model. More importantly, our network model only relies on logical operations and low-bit width fixed-point addition and subtraction operations during the inference phase, which greatly simplifies the design complexity of the processing element (PE). Our research shows the great potential of BNN in the hardware deployment of computer vision models, especially in the field of computer vision tasks related to autonomous driving.

MobileNetV2: A lightweight classification model for home-based sleep apnea screening

This study proposes a novel lightweight neural network model leveraging features extracted from electrocardiogram (ECG) and respiratory signals for early OSA screening. ECG signals are used to generate feature spectrograms to predict sleep stages, while respiratory signals are employed to detect sleep-related breathing abnormalities. By integrating these predictions, the method calculates the apnea-hypopnea index (AHI) with enhanced accuracy, facilitating precise OSA diagnosis. The method was validated on three publicly available sleep apnea databases: the Apnea-ECG database, the UCDDB dataset, and the MIT-BIH Polysomnographic database. Results showed an overall OSA detection accuracy of 0.978, highlighting the model's robustness. Respiratory event classification achieved an accuracy of 0.969 and an area under the receiver operating characteristic curve (ROC-AUC) of 0.98. For sleep stage classification, in UCDDB dataset, the ROC-AUC exceeded 0.85 across all stages, with recall for Sleep reaching 0.906 and specificity for REM and Wake states at 0.956 and 0.937, respectively. This study underscores the potential of integrating lightweight neural networks with multi-signal analysis for accurate, portable, and cost-effective OSA screening, paving the way for broader adoption in home-based and wearable health monitoring systems.

FGP: Feature-Gradient-Prune for Efficient Convolutional Layer Pruning

To reduce computational overhead while maintaining model performance, model pruning techniques have been proposed. Among these, structured pruning, which removes entire convolutional channels or layers, significantly enhances computational efficiency and is compatible with hardware acceleration. However, existing pruning methods that rely solely on image features or gradients often result in the retention of redundant channels, negatively impacting inference efficiency. To address this issue, this paper introduces a novel pruning method called Feature-Gradient Pruning (FGP). This approach integrates both feature-based and gradient-based information to more effectively evaluate the importance of channels across various target classes, enabling a more accurate identification of channels that are critical to model performance. Experimental results demonstrate that the proposed method improves both model compactness and practicality while maintaining stable performance. Experiments conducted across multiple tasks and datasets show that FGP significantly reduces computational costs and minimizes accuracy loss compared to existing methods, highlighting its effectiveness in optimizing pruning outcomes. The source code is available at: https://github.com/FGP-code/FGP.

QARM: Quantitative Alignment Multi-Modal Recommendation at Kuaishou

In recent years, with the significant evolution of multi-modal large models, many recommender researchers realized the potential of multi-modal information for user interest modeling. In industry, a wide-used modeling architecture is a cascading paradigm: (1) first pre-training a multi-modal model to provide omnipotent representations for downstream services; (2) The downstream recommendation model takes the multi-modal representation as additional input to fit real user-item behaviours. Although such paradigm achieves remarkable improvements, however, there still exist two problems that limit model performance: (1) Representation Unmatching: The pre-trained multi-modal model is always supervised by the classic NLP/CV tasks, while the recommendation models are supervised by real user-item interaction. As a result, the two fundamentally different tasks' goals were relatively separate, and there was a lack of consistent objective on their representations; (2) Representation Unlearning: The generated multi-modal representations are always stored in cache store and serve as extra fixed input of recommendation model, thus could not be updated by recommendation model gradient, further unfriendly for downstream training. Inspired by the two difficulties challenges in downstream tasks usage, we introduce a quantitative multi-modal framework to customize the specialized and trainable multi-modal information for different downstream models.