Yi Luo

Wei Dong, Junsheng Wu, Yi Luo et al. · ibm-research

The key towards learning informative node representations in graphs lies in how to gain contextual information from the neighbourhood. In this work, we present a simple-yet-effective self-supervised node representation learning strategy via directly maximizing the mutual information between the hidden representations of nodes and their neighbourhood, which can be theoretically justified by its link to graph smoothing. Following InfoNCE, our framework is optimized via a surrogate contrastive loss, where the positive selection underpins the quality and efficiency of representation learning. To this end, we propose a topology-aware positive sampling strategy, which samples positives from the neighbourhood by considering the structural dependencies between nodes and thus enables positive selection upfront. In the extreme case when only one positive is sampled, we fully avoid expensive neighbourhood aggregation. Our methods achieve promising performance on various node classification datasets. It is also worth mentioning by applying our loss function to MLP based node encoders, our methods can be orders of faster than existing solutions. Our codes and supplementary materials are available at https://github.com/dongwei156/n2n.

Binbin Yang, Yi Luo, Ziliang Chen et al.

Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis. Prior works mostly rely on pre-trained linguistic models, but a text is often too abstract to properly specify all the spatial properties of an image, e.g., the layout configuration of a scene, leading to the sub-optimal results of complex scene generation. In this paper, we achieve accurate complex scene generation by proposing a semantically controllable Layout-AWare diffusion model, termed LAW-Diffusion. Distinct from the previous Layout-to-Image generation (L2I) methods that only explore category-aware relationships, LAW-Diffusion introduces a spatial dependency parser to encode the location-aware semantic coherence across objects as a layout embedding and produces a scene with perceptually harmonious object styles and contextual relations. To be specific, we delicately instantiate each object's regional semantics as an object region map and leverage a location-aware cross-object attention module to capture the spatial dependencies among those disentangled representations. We further propose an adaptive guidance schedule for our layout guidance to mitigate the trade-off between the regional semantic alignment and the texture fidelity of generated objects. Moreover, LAW-Diffusion allows for instance reconfiguration while maintaining the other regions in a synthesized image by introducing a layout-aware latent grafting mechanism to recompose its local regional semantics. To better verify the plausibility of generated scenes, we propose a new evaluation metric for the L2I task, dubbed Scene Relation Score (SRS) to measure how the images preserve the rational and harmonious relations among contextual objects. Comprehensive experiments demonstrate that our LAW-Diffusion yields the state-of-the-art generative performance, especially with coherent object relations.

Yi Luo, Guiduo Duan, Guangchun Luo et al.

The success of Graph Neural Networks (GNN) in learning on non-Euclidean data arouses many subtopics, such as Label-inputted GNN (LGNN) and Implicit GNN (IGNN). LGNN, explicitly inputting supervising information (a.k.a. labels) in GNN, integrates label propagation to achieve superior performance, but with the dilemma between its propagating distance and adaptiveness. IGNN, outputting an equilibrium point by iterating its network infinite times, exploits information in the entire graph to capture long-range dependencies, but with its network constrained to guarantee the existence of the equilibrium. This work unifies the two subdomains by interpreting LGNN in the theory of IGNN and reducing prevailing LGNNs to the form of IGNN. The unification facilitates the exchange between the two subdomains and inspires more studies. Specifically, implicit differentiation of IGNN is introduced to LGNN to differentiate its infinite-range label propagation with constant memory, making the propagation both distant and adaptive. Besides, the masked label strategy of LGNN is proven able to guarantee the well-posedness of IGNN in a network-agnostic manner, granting its network more complex and thus more expressive. Combining the advantages of LGNN and IGNN, Label-inputted Implicit GNN (LI-GNN) is proposed. It can be widely applied to any specific GNN to boost its performance. Node classification experiments on two synthesized and six real-world datasets demonstrate its effectiveness. Code is available at https://github.com/cf020031308/LI-GNN

Jiashuo Sun, Yi Luo, Yeyun Gong et al.

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by LLMs are prone to errors, which can subsequently lead to incorrect reasoning during inference. Furthermore, inappropriate exemplars (overly simplistic or complex), can affect overall performance among varying levels of difficulty. We introduce Iter-CoT (Iterative bootstrapping in Chain-of-Thoughts Prompting), an iterative bootstrapping approach for selecting exemplars and generating reasoning chains. By utilizing iterative bootstrapping, our approach enables LLMs to autonomously rectify errors, resulting in more precise and comprehensive reasoning chains. Simultaneously, our approach selects challenging yet answerable questions accompanied by reasoning chains as exemplars with a moderate level of difficulty, which enhances the LLMs' generalizability across varying levels of difficulty. Experimental results indicate that Iter-CoT exhibits superiority, achieving competitive performance across three distinct reasoning tasks on ten datasets.

Bijie Bai, Yi Luo, Tianyi Gan et al.

Privacy protection is a growing concern in the digital era, with machine vision techniques widely used throughout public and private settings. Existing methods address this growing problem by, e.g., encrypting camera images or obscuring/blurring the imaged information through digital algorithms. Here, we demonstrate a camera design that performs class-specific imaging of target objects with instantaneous all-optical erasure of other classes of objects. This diffractive camera consists of transmissive surfaces structured using deep learning to perform selective imaging of target classes of objects positioned at its input field-of-view. After their fabrication, the thin diffractive layers collectively perform optical mode filtering to accurately form images of the objects that belong to a target data class or group of classes, while instantaneously erasing objects of the other data classes at the output field-of-view. Using the same framework, we also demonstrate the design of class-specific permutation cameras, where the objects of a target data class are pixel-wise permuted for all-optical class-specific encryption, while the other objects are irreversibly erased from the output image. The success of class-specific diffractive cameras was experimentally demonstrated using terahertz (THz) waves and 3D-printed diffractive layers that selectively imaged only one class of the MNIST handwritten digit dataset, all-optically erasing the other handwritten digits. This diffractive camera design can be scaled to different parts of the electromagnetic spectrum, including, e.g., the visible and infrared wavelengths, to provide transformative opportunities for privacy-preserving digital cameras and task-specific data-efficient imaging.

Cagatay Isil, Deniz Mengu, Yifan Zhao et al.

High-resolution synthesis/projection of images over a large field-of-view (FOV) is hindered by the restricted space-bandwidth-product (SBP) of wavefront modulators. We report a deep learning-enabled diffractive display design that is based on a jointly-trained pair of an electronic encoder and a diffractive optical decoder to synthesize/project super-resolved images using low-resolution wavefront modulators. The digital encoder, composed of a trained convolutional neural network (CNN), rapidly pre-processes the high-resolution images of interest so that their spatial information is encoded into low-resolution (LR) modulation patterns, projected via a low SBP wavefront modulator. The diffractive decoder processes this LR encoded information using thin transmissive layers that are structured using deep learning to all-optically synthesize and project super-resolved images at its output FOV. Our results indicate that this diffractive image display can achieve a super-resolution factor of ~4, demonstrating a ~16-fold increase in SBP. We also experimentally validate the success of this diffractive super-resolution display using 3D-printed diffractive decoders that operate at the THz spectrum. This diffractive image decoder can be scaled to operate at visible wavelengths and inspire the design of large FOV and high-resolution displays that are compact, low-power, and computationally efficient.

Yi Luo, Jianwei Yu

The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipelines. However, recent model designs for MSS were mainly motivated by other audio processing tasks or other research fields, while the intrinsic characteristics and patterns of the music signals were not fully discovered. In this paper, we propose band-split RNN (BSRNN), a frequency-domain model that explictly splits the spectrogram of the mixture into subbands and perform interleaved band-level and sequence-level modeling. The choices of the bandwidths of the subbands can be determined by a priori knowledge or expert knowledge on the characteristics of the target source in order to optimize the performance on a certain type of target musical instrument. To better make use of unlabeled data, we also describe a semi-supervised model finetuning pipeline that can further improve the performance of the model. Experiment results show that BSRNN trained only on MUSDB18-HQ dataset significantly outperforms several top-ranking models in Music Demixing (MDX) Challenge 2021, and the semi-supervised finetuning stage further improves the performance on all four instrument tracks.

Yi Luo, Bijie Bai, Yuhang Li et al.

Classification of an object behind a random and unknown scattering medium sets a challenging task for computational imaging and machine vision fields. Recent deep learning-based approaches demonstrated the classification of objects using diffuser-distorted patterns collected by an image sensor. These methods demand relatively large-scale computing using deep neural networks running on digital computers. Here, we present an all-optical processor to directly classify unknown objects through unknown, random phase diffusers using broadband illumination detected with a single pixel. A set of transmissive diffractive layers, optimized using deep learning, forms a physical network that all-optically maps the spatial information of an input object behind a random diffuser into the power spectrum of the output light detected through a single pixel at the output plane of the diffractive network. We numerically demonstrated the accuracy of this framework using broadband radiation to classify unknown handwritten digits through random new diffusers, never used during the training phase, and achieved a blind testing accuracy of 88.53%. This single-pixel all-optical object classification system through random diffusers is based on passive diffractive layers that process broadband input light and can operate at any part of the electromagnetic spectrum by simply scaling the diffractive features proportional to the wavelength range of interest. These results have various potential applications in, e.g., biomedical imaging, security, robotics, and autonomous driving.

Yuhang Li, Yi Luo, Bijie Bai et al.

Imaging through diffusive media is a challenging problem, where the existing solutions heavily rely on digital computers to reconstruct distorted images. We provide a detailed analysis of a computer-free, all-optical imaging method for seeing through random, unknown phase diffusers using diffractive neural networks, covering different deep learning-based training strategies. By analyzing various diffractive networks designed to image through random diffusers with different correlation lengths, a trade-off between the image reconstruction fidelity and distortion reduction capability of the diffractive network was observed. During its training, random diffusers with a range of correlation lengths were used to improve the diffractive network's generalization performance. Increasing the number of random diffusers used in each epoch reduced the overfitting of the diffractive network's imaging performance to known diffusers. We also demonstrated that the use of additional diffractive layers improved the generalization capability to see through new, random diffusers. Finally, we introduced deliberate misalignments in training to 'vaccinate' the network against random layer-to-layer shifts that might arise due to the imperfect assembly of the diffractive networks. These analyses provide a comprehensive guide in designing diffractive networks to see through random diffusers, which might profoundly impact many fields, such as biomedical imaging, atmospheric physics, and autonomous driving.

Yi Luo, Yijie Zhang, Tairan Liu et al.

Exposure to bio-aerosols such as mold spores and pollen can lead to adverse health effects. There is a need for a portable and cost-effective device for long-term monitoring and quantification of various bio-aerosols. To address this need, we present a mobile and cost-effective label-free bio-aerosol sensor that takes holographic images of flowing particulate matter concentrated by a virtual impactor, which selectively slows down and guides particles larger than ~6 microns to fly through an imaging window. The flowing particles are illuminated by a pulsed laser diode, casting their inline holograms on a CMOS image sensor in a lens-free mobile imaging device. The illumination contains three short pulses with a negligible shift of the flowing particle within one pulse, and triplicate holograms of the same particle are recorded at a single frame before it exits the imaging field-of-view, revealing different perspectives of each particle. The particles within the virtual impactor are localized through a differential detection scheme, and a deep neural network classifies the aerosol type in a label-free manner, based on the acquired holographic images. We demonstrated the success of this mobile bio-aerosol detector with a virtual impactor using different types of pollen (i.e., bermuda, elm, oak, pine, sycamore, and wheat) and achieved a blind classification accuracy of 92.91%. This mobile and cost-effective device weighs ~700 g and can be used for label-free sensing and quantification of various bio-aerosols over extended periods since it is based on a cartridge-free virtual impactor that does not capture or immobilize particulate matter.

Zhongtian Hua, Yi Luo, Meijia Yu et al.

In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream claim verification process. Existing general multimodal retrieval methods are often constructed based on semantics, resulting in the retrieved evidence being similar but not relevant to the claim. This paper proposes a \textbf{D}ynamic \textbf{A}daptive \textbf{C}ontrastive \textbf{L}earning method for evidence \textbf{R}etrieval called DACLR to address these issues. DACLR first uses a Multimodal Large Language Model (MLLM) to uniformly convert multimodal evidence and claims into text modalities, and extracts the features of these information at event level. Then, it conducts evidence retrieval through a two-stage retrieval method of recall-rerank. DACLR enhances the model's event perception ability of the retrieval stage by optimizing the contrastive loss and mining hard negative samples. Specifically, DACLR designs three loss functions at two levels (semantic and event) based on the InfoNCE loss.Corresponding to these, three sets of hard negative sample candidates are set up. The model dynamically adjusts the ratio based on the accuracy supervision signal of intra-batch samples, allowing the model to learn the correlation between claims and positive samples at the event level without forgetting the semantic retrieval ability. Extensive comparison and ablation experiments demonstrates the effectiveness of DACLR and its internal optimization methods. Further research also prove the advantages of DACLR in the field of multimodal evidence retrieval.

Kai Li, Yi Luo

Audio restoration has become increasingly significant in modern society, not only due to the demand for high-quality auditory experiences enabled by advanced playback devices, but also because the growing capabilities of generative audio models necessitate high-fidelity audio. Typically, audio restoration is defined as a task of predicting undistorted audio from damaged input, often trained using a GAN framework to balance perception and distortion. Since audio degradation is primarily concentrated in mid- and high-frequency ranges, especially due to codecs, a key challenge lies in designing a generator capable of preserving low-frequency information while accurately reconstructing high-quality mid- and high-frequency content. Inspired by recent advancements in high-sample-rate music separation, speech enhancement, and audio codec models, we propose Apollo, a generative model designed for high-sample-rate audio restoration. Apollo employs an explicit frequency band split module to model the relationships between different frequency bands, allowing for more coherent and higher-quality restored audio. Evaluated on the MUSDB18-HQ and MoisesDB datasets, Apollo consistently outperforms existing SR-GAN models across various bit rates and music genres, particularly excelling in complex scenarios involving mixtures of multiple instruments and vocals. Apollo significantly improves music restoration quality while maintaining computational efficiency. The source code for Apollo is publicly available at https://github.com/JusperLee/Apollo.

Hangting Chen, Jianwei Yu, Yi Luo et al.

Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning model complexity. In this paper, we introduce time-frequency dual-path compression to achieve a wide range of compression ratios on computational cost. Specifically, for frequency compression, trainable filters are used to replace manually designed filters for dimension reduction. For time compression, only using frame skipped prediction causes large performance degradation, which can be alleviated by a post-processing network with full sequence modeling. We have found that under fixed compression ratios, dual-path compression combining both the time and frequency methods will give further performance improvement, covering compression ratios from 4x to 32x with little model size change. Moreover, the proposed models show competitive performance compared with fast FullSubNet and DeepFilterNet.

Junqi Liu, Zejun Wu, Pedro R. A. S. Bassi et al.

Image enhancement improves visual quality and helps reveal details that are hard to see in the original image. In medical imaging, it can support clinical decision-making, but current models often over-edit. This can distort organs, create false findings, and miss small tumors because these models do not understand anatomy or contrast dynamics. We propose SMILE, an anatomy-aware diffusion model that learns how organs are shaped and how they take up contrast. It enhances only clinically relevant regions while leaving all other areas unchanged. SMILE introduces three key ideas: (1) structure-aware supervision that follows true organ boundaries and contrast patterns; (2) registration-free learning that works directly with unaligned multi-phase CT scans; (3) unified inference that provides fast and consistent enhancement across all contrast phases. Across six external datasets, SMILE outperforms existing methods in image quality (14.2% higher SSIM, 20.6% higher PSNR, 50% better FID) and in clinical usefulness by producing anatomically accurate and diagnostically meaningful images. SMILE also improves cancer detection from non-contrast CT, raising the F1 score by up to 10 percent.

Rongzhi Gu, Yi Luo

We introduce region-customizable sound extraction (ReZero), a general and flexible framework for the multi-channel region-wise sound extraction (R-SE) task. R-SE task aims at extracting all active target sounds (e.g., human speech) within a specific, user-defined spatial region, which is different from conventional and existing tasks where a blind separation or a fixed, predefined spatial region are typically assumed. The spatial region can be defined as an angular window, a sphere, a cone, or other geometric patterns. Being a solution to the R-SE task, the proposed ReZero framework includes (1) definitions of different types of spatial regions, (2) methods for region feature extraction and aggregation, and (3) a multi-channel extension of the band-split RNN (BSRNN) model specified for the R-SE task. We design experiments for different microphone array geometries, different types of spatial regions, and comprehensive ablation studies on different system configurations. Experimental results on both simulated and real-recorded data demonstrate the effectiveness of ReZero. Demos are available at https://innerselfm.github.io/rezero/.

Lin Wang, Xiufen Ye, Donghao Zhang et al.

Usually, lesions are not isolated but are associated with the surrounding tissues. For example, the growth of a tumour can depend on or infiltrate into the surrounding tissues. Due to the pathological nature of the lesions, it is challenging to distinguish their boundaries in medical imaging. However, these uncertain regions may contain diagnostic information. Therefore, the simple binarization of lesions by traditional binary segmentation can result in the loss of diagnostic information. In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i.e., a soft mask, to describe lesions in a 3D medical image. The traditional soft mask acted as a training trick to compensate for the easily mislabelled or under-labelled ambiguous regions. In contrast, 3D matting uses soft segmentation to characterize the uncertain regions more finely, which means that it retains more structural information for subsequent diagnosis and treatment. The current study of image matting methods in 3D is limited. To address this issue, we conduct a comprehensive study of 3D matting, including both traditional and deep-learning-based methods. We adapt four state-of-the-art 2D image matting algorithms to 3D scenes and further customize the methods for CT images to calibrate the alpha matte with the radiodensity. Moreover, we propose the first end-to-end deep 3D matting network and implement a solid 3D medical image matting benchmark. Its efficient counterparts are also proposed to achieve a good performance-computation balance. Furthermore, there is no high-quality annotated dataset related to 3D matting, slowing down the development of data-driven deep-learning-based methods. To address this issue, we construct the first 3D medical matting dataset. The validity of the dataset was verified through clinicians' assessments and downstream experiments.

Yihang Zheng, Bo Li, Zhenghao Lin et al.

The development of Large Language Models (LLMs) has revolutionized QA across various industries, including the database domain. However, there is still a lack of a comprehensive benchmark to evaluate the capabilities of different LLMs and their modular components in database QA. To this end, we introduce DQABench, the first comprehensive database QA benchmark for LLMs. DQABench features an innovative LLM-based method to automate the generation, cleaning, and rewriting of evaluation dataset, resulting in over 200,000 QA pairs in English and Chinese, separately. These QA pairs cover a wide range of database-related knowledge extracted from manuals, online communities, and database instances. This inclusion allows for an additional assessment of LLMs' Retrieval-Augmented Generation (RAG) and Tool Invocation Generation (TIG) capabilities in the database QA task. Furthermore, we propose a comprehensive LLM-based database QA testbed DQATestbed. This testbed is highly modular and scalable, with basic and advanced components such as Question Classification Routing (QCR), RAG, TIG, and Prompt Template Engineering (PTE). Moreover, DQABench provides a comprehensive evaluation pipeline that computes various metrics throughout a standardized evaluation process to ensure the accuracy and fairness of the evaluation. We use DQABench to evaluate the database QA capabilities under the proposed testbed comprehensively. The evaluation reveals findings like (i) the strengths and limitations of nine LLM-based QA bots and (ii) the performance impact and potential improvements of various service components (e.g., QCR, RAG, TIG). Our benchmark and findings will guide the future development of LLM-based database QA research.

Yiquan Wu, Bo Tang, Chenyang Xi et al.

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

Haina Zhu, Yizhi Zhou, Hangting Chen et al.

Recent years have witnessed the success of foundation models pre-trained with self-supervised learning (SSL) in various music informatics understanding tasks, including music tagging, instrument classification, key detection, and more. In this paper, we propose a self-supervised music representation learning model for music understanding. Distinguished from previous studies adopting random projection or existing neural codec, the proposed model, named MuQ, is trained to predict tokens generated by Mel Residual Vector Quantization (Mel-RVQ). Our Mel-RVQ utilizes residual linear projection structure for Mel spectrum quantization to enhance the stability and efficiency of target extraction and lead to better performance. Experiments in a large variety of downstream tasks demonstrate that MuQ outperforms previous self-supervised music representation models with only 0.9K hours of open-source pre-training data. Scaling up the data to over 160K hours and adopting iterative training consistently improve the model performance. To further validate the strength of our model, we present MuQ-MuLan, a joint music-text embedding model based on contrastive learning, which achieves state-of-the-art performance in the zero-shot music tagging task on the MagnaTagATune dataset. Code and checkpoints are open source in https://github.com/tencent-ailab/MuQ.

Chongliu Jia, Yi Luo, Sipeng Han et al.

Medium- to long-horizon equity allocation is challenging due to weak predictive structure, non-stationary market regimes, and the degradation of signals under realistic trading constraints. Conventional approaches often rely on single predictors or loosely coupled pipelines, which limit robustness under distributional shift. This paper proposes EvoNash-MARL, a closed-loop framework that integrates reinforcement learning with population-based policy optimization and execution-aware selection to improve robustness in medium- to long-horizon allocation. The framework combines multi-agent policy populations, game-theoretic aggregation, and constraint-aware validation within a unified walk-forward design. Under a 120-window walk-forward protocol, the final configuration achieves the highest robust score among internal baselines. On out-of-sample data from 2014 to 2024, it delivers a 19.6% annualized return, compared to 11.7% for SPY, and remains stable under extended evaluation through 2026. While the framework demonstrates consistent performance under realistic constraints and across market settings, strong global statistical significance is not established under White's Reality Check (WRC) and SPA-lite tests. The results therefore provide evidence of improved robustness rather than definitive proof of superior market timing performance.

Yuqi Wang, Boran Jiang, Yi Luo et al.

Large language models (LLMs), such as GPT3.5, GPT4 and LLAMA2 perform surprisingly well and outperform human experts on many tasks. However, in many domain-specific evaluations, these LLMs often suffer from hallucination problems due to insufficient training of relevant corpus. Furthermore, fine-tuning large models may face problems such as the LLMs are not open source or the construction of high-quality domain instruction is difficult. Therefore, structured knowledge databases such as knowledge graph can better provide domain background knowledge for LLMs and make full use of the reasoning and analysis capabilities of LLMs. In some previous works, LLM was called multiple times to determine whether the current triplet was suitable for inclusion in the subgraph when retrieving subgraphs through a question. Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power. Moreover, when choosing the reasoning path, LLM will be called once for each step, and if one of the steps is selected incorrectly, it will lead to the accumulation of errors in the following steps. In this paper, we integrated and optimized a pipeline for selecting reasoning paths from KG based on LLM, which can reduce the dependency on LLM. In addition, we propose a simple and effective subgraph retrieval method based on chain of thought (CoT) and page rank which can returns the paths most likely to contain the answer. We conduct experiments on three datasets: GenMedGPT-5k [14], WebQuestions [2], and CMCQA [21]. Finally, RoK can demonstrate that using fewer LLM calls can achieve the same results as previous SOTAs models.

Yi Luo, Yike Guo, Hamed Hooshangnejad et al.

Lung nodule detection in chest CT is crucial for early lung cancer diagnosis, yet existing deep learning approaches face challenges when deployed in clinical settings with limited annotated data. While curriculum learning has shown promise in improving model training, traditional static curriculum strategies fail in data-scarce scenarios. We propose Scale Adaptive Curriculum Learning (SACL), a novel training strategy that dynamically adjusts curriculum design based on available data scale. SACL introduces three key mechanisms:(1) adaptive epoch scheduling, (2) hard sample injection, and (3) scale-aware optimization. We evaluate SACL on the LUNA25 dataset using YOLOv11 as the base detector. Experimental results demonstrate that while SACL achieves comparable performance to static curriculum learning on the full dataset in mAP50, it shows significant advantages under data-limited conditions with 4.6%, 3.5%, and 2.0% improvements over baseline at 10%, 20%, and 50% of training data respectively. By enabling robust training across varying data scales without architectural modifications, SACL provides a practical solution for healthcare institutions to develop effective lung nodule detection systems despite limited annotation resources.

Yi Luo, Xu Sun, Guangchun Luo et al.

Graph neural networks (GNNs) have been widely adopted in engineering applications such as social network analysis, chemical research and computer vision. However, their efficacy is severely compromised by the inherent homophily assumption, which fails to hold for heterophilic graphs where dissimilar nodes are frequently connected. To address this fundamental limitation in graph learning, we first draw inspiration from the recently discovered monophily property of real-world graphs, and propose Neighbourhood Transformers (NT), a novel paradigm that applies self-attention within every local neighbourhood instead of aggregating messages to the central node as in conventional message-passing GNNs. This design makes NT inherently monophily-aware and theoretically guarantees its expressiveness is no weaker than traditional message-passing frameworks. For practical engineering deployment, we further develop a neighbourhood partitioning strategy equipped with switchable attentions, which reduces the space consumption of NT by over 95% and time consumption by up to 92.67%, significantly expanding its applicability to larger graphs. Extensive experiments on 10 real-world datasets (5 heterophilic and 5 homophilic graphs) show that NT outperforms all current state-of-the-art methods on node classification tasks, demonstrating its superior performance and cross-domain adaptability. The full implementation code of this work is publicly available at https://github.com/cf020031308/MoNT to facilitate reproducibility and industrial adoption.

Gongzhu Yin, Hongli Zhang, Yuchen Yang et al.

N-ary relational facts represent semantic correlations among more than two entities. While recent studies have developed link prediction (LP) methods to infer missing relations for knowledge graphs (KGs) containing n-ary relational facts, they are generally limited to transductive settings. Fully inductive settings, where predictions are made on previously unseen entities, remain a significant challenge. As existing methods are mainly entity embedding-based, they struggle to capture entity-independent logical rules. To fill in this gap, we propose an n-ary subgraph reasoning framework for fully inductive link prediction (ILP) on n-ary relational facts. This framework reasons over local subgraphs and has a strong inductive inference ability to capture n-ary patterns. Specifically, we introduce a novel graph structure, the n-ary semantic hypergraph, to facilitate subgraph extraction. Moreover, we develop a subgraph aggregating network, NS-HART, to effectively mine complex semantic correlations within subgraphs. Theoretically, we provide a thorough analysis from the score function optimization perspective to shed light on NS-HART's effectiveness for n-ary ILP tasks. Empirically, we conduct extensive experiments on a series of inductive benchmarks, including transfer reasoning (with and without entity features) and pairwise subgraph reasoning. The results highlight the superiority of the n-ary subgraph reasoning framework and the exceptional inductive ability of NS-HART. The source code of this paper has been made publicly available at https://github.com/yin-gz/Nary-Inductive-SubGraph.

Yi Luo, Haochen Zhao, Xiao Liang et al.

Drug synergy prediction is a critical task in the development of effective combination therapies for complex diseases, including cancer. Although existing methods have shown promising results, they often operate as black-box predictors that rely predominantly on statistical correlations between drug characteristics and results. To address this limitation, we propose CausalDDS, a novel framework that disentangles drug molecules into causal and spurious substructures, utilizing the causal substructure representations for predicting drug synergy. By focusing on causal sub-structures, CausalDDS effectively mitigates the impact of redundant features introduced by spurious substructures, enhancing the accuracy and interpretability of the model. In addition, CausalDDS employs a conditional intervention mechanism, where interventions are conditioned on paired molecular structures, and introduces a novel optimization objective guided by the principles of sufficiency and independence. Extensive experiments demonstrate that our method outperforms baseline models, particularly in cold start and out-of-distribution settings. Besides, CausalDDS effectively identifies key substructures underlying drug synergy, providing clear insights into how drug combinations work at the molecular level. These results underscore the potential of CausalDDS as a practical tool for predicting drug synergy and facilitating drug discovery.

Gongzhu Yin, Hongli Zhang, Yi Luo et al.

Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data. With the surge of Large Language Models (LLMs), recent studies have begun exploring their integration into TKG forecasting and achieved some success. However, they still face limitations such as limited input length, inefficient output generation, and resource-intensive refinement, which undermine their performance and practical applicability. To address these limitations, we introduce SPARK, a Sequence-level Proxy-Adapting framework for Refining LLMs in TKG forecasting. Inspired by inference-time algorithms adopted in controlling generation, SPARK offers a cost-effective, plug-and-play solution through two key innovations: (1) Beam Sequence-Level Generation, which reframes TKG forecasting as a top-K sequence-level generation task, using beam search for efficiently generating next-entity distribution in a single forward pass. (2) TKG Adapter for Refinement, which employs traditional TKG models as trainable proxy adapters to leverage global graph information and refine LLM outputs, overcoming both the input length and the resource-intensive fine-tuning problems. Experiments across diverse datasets validate SPARK's forecasting performance, robust generalization capabilities, and high efficiency. We release source codes at https://github.com/yin-gz/SPARK.

Mingshu Zhao, Yi Luo, Yong Ouyang

Recent advances in vision transformers (ViTs) have demonstrated the advantage of global modeling capabilities, prompting widespread integration of large-kernel convolutions for enlarging the effective receptive field (ERF). However, the quadratic scaling of parameter count and computational complexity (FLOPs) with respect to kernel size poses significant efficiency and optimization challenges. This paper introduces RecConv, a recursive decomposition strategy that efficiently constructs multi-frequency representations using small-kernel convolutions. RecConv establishes a linear relationship between parameter growth and decomposing levels which determines the effective receptive field $k\times 2^\ell$ for a base kernel $k$ and $\ell$ levels of decomposition, while maintaining constant FLOPs regardless of the ERF expansion. Specifically, RecConv achieves a parameter expansion of only $\ell+2$ times and a maximum FLOPs increase of $5/3$ times, compared to the exponential growth ($4^\ell$) of standard and depthwise convolutions. RecNeXt-M3 outperforms RepViT-M1.1 by 1.9 $AP^{box}$ on COCO with similar FLOPs. This innovation provides a promising avenue towards designing efficient and compact networks across various modalities. Codes and models can be found at https://github.com/suous/RecNeXt.

Mingshu Zhao, Yi Luo, Yong Ouyang

In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tailored for resource-constrained applications. We introduce RepNeXt, a novel model series integrates multi-scale feature representations and incorporates both serial and parallel structural reparameterization (SRP) to enhance network depth and width without compromising inference speed. Extensive experiments demonstrate RepNeXt's superiority over current leading lightweight CNNs and ViTs, providing advantageous latency across various vision benchmarks. RepNeXt-M4 matches RepViT-M1.5's 82.3\% accuracy on ImageNet within 1.5ms on an iPhone 12, outperforms its AP$^{box}$ by 1.3 on MS-COCO, and reduces parameters by 0.7M. Codes and models are available at https://github.com/suous/RepNeXt.

Yi Luo, Guangchun Luo, Ke Qin et al.

Node classifiers are required to comprehensively reduce prediction errors, training resources, and inference latency in the industry. However, most graph neural networks (GNN) concentrate only on one or two of them. The compromised aspects thus are the shortest boards on the bucket, hindering their practical deployments for industrial-level tasks. This work proposes a novel semi-supervised learning method termed Graph Entropy Minimization (GEM) to resolve the three issues simultaneously. GEM benefits its one-hop aggregation from massive uncategorized nodes, making its prediction accuracy comparable to GNNs with two or more hops message passing. It can be decomposed to support stochastic training with mini-batches of independent edge samples, achieving extremely fast sampling and space-saving training. While its one-hop aggregation is faster in inference than deep GNNs, GEM can be further accelerated to an extreme by deriving a non-hop classifier via online knowledge distillation. Thus, GEM can be a handy choice for latency-restricted and error-sensitive services running on resource-constraint hardware. Code is available at https://github.com/cf020031308/GEM.

Qiaohong Zhang, Weihao Ye, Jialong Chen et al.

Evaluating autonomous data analysis agents requires testing their ability to perform exploratory analysis in underexplored data environments. However, many existing benchmarks emphasize final answer accuracy in prior-guided data settings and provide limited support for reasoning process evaluation. We introduce DataClaw, a process-oriented benchmark for exploratory real-world data analysis. DataClaw contains approximately 2.06 million real-world records across enterprise, industry and policy domains, with native data noise preserved. It further includes 492 cross-domain tasks derived from think-tank consulting scenarios, each annotated with intermediate milestones for process-level evaluation. These annotations allow DataClaw to measure how far an agent progresses and where its reasoning breaks down. Experiments with eight advanced LLMs show that current agents remain far from reliable in this setting, with seven models achieving below 50% overall accuracy. Process analysis further reveals partial progress hidden behind wrong answers and distinct exploration strategies across models. Overall, DataClaw provides a less data constrained diagnostic testbed for probing the capability boundaries of autonomous data-analysis agents.

Victoria Benjamin, Emily Braca, Israel Carter et al.

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection tests, we observed a strong correlation between model parameters and vulnerability, with statistical analyses, such as logistic regression and random forest feature analysis, indicating that parameter size and architecture significantly influence susceptibility. Results revealed that 56 percent of tests led to successful prompt injections, emphasizing widespread vulnerability across various parameter sizes, with clustering analysis identifying distinct vulnerability profiles associated with specific model configurations. Additionally, our analysis uncovered correlations between certain prompt injection techniques, suggesting potential overlaps in vulnerabilities. These findings underscore the urgent need for robust, multi-layered defenses in LLMs deployed across critical infrastructure and sensitive industries. Successful prompt injection attacks could result in severe consequences, including data breaches, unauthorized access, or misinformation. Future research should explore multilingual and multi-step defenses alongside adaptive mitigation strategies to strengthen LLM security in diverse, real-world environments.

Yi Luo, Linghang Shi, Yihao Li et al.

Conventional biomedical research is increasingly labor-intensive due to the exponential growth of scientific literature and datasets. Artificial intelligence (AI), particularly Large Language Models (LLMs), has the potential to revolutionize this process by automating various steps. Still, significant challenges remain, including the need for multidisciplinary expertise, logicality of experimental design, and performance measurements. This paper introduces BioResearcher, the first end-to-end automated system designed to streamline the entire biomedical research process involving dry lab experiments. BioResearcher employs a modular multi-agent architecture, integrating specialized agents for search, literature processing, experimental design, and programming. By decomposing complex tasks into logically related sub-tasks and utilizing a hierarchical learning approach, BioResearcher effectively addresses the challenges of multidisciplinary requirements and logical complexity. Furthermore, BioResearcher incorporates an LLM-based reviewer for in-process quality control and introduces novel evaluation metrics to assess the quality and automation of experimental protocols. BioResearcher successfully achieves an average execution success rate of 63.07% across eight previously unmet research objectives. The generated protocols, on average, outperform typical agent systems by 22.0% on five quality metrics. The system demonstrates significant potential to reduce researchers' workloads and accelerate biomedical discoveries, paving the way for future innovations in automated research systems.

Bin Lei, Yuchen Li, Yiming Zeng et al.

Despite the impressive capabilities of large language models (LLMs), they currently exhibit two primary limitations, \textbf{\uppercase\expandafter{\romannumeral 1}}: They struggle to \textbf{autonomously solve the real world engineering problem}. \textbf{\uppercase\expandafter{\romannumeral 2}}: They remain \textbf{challenged in reasoning through complex logic problems}. To address these challenges, we developed the \textsc{Infant Agent}, integrating task-aware functions, operators, a hierarchical management system, and a memory retrieval mechanism. Together, these components enable large language models to sustain extended reasoning processes and handle complex, multi-step tasks efficiently, all while significantly reducing API costs. Using the \textsc{Infant Agent}, GPT-4o's accuracy on the SWE-bench-lite dataset rises from $\mathbf{0.33\%}$ to $\mathbf{30\%}$, and in the AIME-2024 mathematics competition, it increases GPT-4o's accuracy from $\mathbf{13.3\%}$ to $\mathbf{37\%}$.

Yi Luo, Jianwei Yu, Hangting Chen et al.

We introduce Gull, a generative multifunctional audio codec. Gull is a general purpose neural audio compression and decompression model which can be applied to a wide range of tasks and applications such as real-time communication, audio super-resolution, and codec language models. The key components of Gull include (1) universal-sample-rate modeling via subband modeling schemes motivated by recent progress in audio source separation, (2) gain-shape representations motivated by traditional audio codecs, (3) improved residual vector quantization modules, (4) elastic decoder network that enables user-defined model size and complexity during inference time, (5) built-in ability for audio super-resolution without the increase of bitrate. We compare Gull with existing traditional and neural audio codecs and show that Gull is able to achieve on par or better performance across various sample rates, bitrates and model complexities in both subjective and objective evaluation metrics.

Miao Li, Ming-Bin Chen, Bo Tang et al.

We present NewsBench, a novel evaluation framework to systematically assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. Our constructed benchmark dataset is focused on four facets of writing proficiency and six facets of safety adherence, and it comprises manually and carefully designed 1,267 test samples in the types of multiple choice questions and short answer questions for five editorial tasks in 24 news domains. To measure performances, we propose different GPT-4 based automatic evaluation protocols to assess LLM generations for short answer questions in terms of writing proficiency and safety adherence, and both are validated by the high correlations with human evaluations. Based on the systematic evaluation framework, we conduct a comprehensive analysis of ten popular LLMs which can handle Chinese. The experimental results highlight GPT-4 and ERNIE Bot as top performers, yet reveal a relative deficiency in journalistic safety adherence in creative writing tasks. Our findings also underscore the need for enhanced ethical guidance in machine-generated journalistic content, marking a step forward in aligning LLMs with journalistic standards and safety considerations.

Yinqiu Huang, Shuli Wang, Min Gao et al.

Uplift modeling, vital in online marketing, seeks to accurately measure the impact of various strategies, such as coupons or discounts, on different users by predicting the Individual Treatment Effect (ITE). In an e-commerce setting, user behavior follows a defined sequential chain, including impression, click, and conversion. Marketing strategies exert varied uplift effects at each stage within this chain, impacting metrics like click-through and conversion rate. Despite its utility, existing research has neglected to consider the inter-task across all stages impacts within a specific treatment and has insufficiently utilized the treatment information, potentially introducing substantial bias into subsequent marketing decisions. We identify these two issues as the chain-bias problem and the treatment-unadaptive problem. This paper introduces the Entire Chain UPlift method with context-enhanced learning (ECUP), devised to tackle these issues. ECUP consists of two primary components: 1) the Entire Chain-Enhanced Network, which utilizes user behavior patterns to estimate ITE throughout the entire chain space, models the various impacts of treatments on each task, and integrates task prior information to enhance context awareness across all stages, capturing the impact of treatment on different tasks, and 2) the Treatment-Enhanced Network, which facilitates fine-grained treatment modeling through bit-level feature interactions, thereby enabling adaptive feature adjustment. Extensive experiments on public and industrial datasets validate ECUPs effectiveness. Moreover, ECUP has been deployed on the Meituan food delivery platform, serving millions of daily active users, with the related dataset released for future research.

Kai Li, Yi Luo

Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high. Although there exist ways for model pruning or distillation, it is typically required to perform a full round of model training or finetuning procedure in order to obtain a smaller model that satisfies the model size or complexity constraints. Motivated by recent works on dynamic neural networks, we propose a simple way to train a large network and flexibly extract a subnetwork from it given a model size or complexity constraint during inference. We introduce a new way to allow a large model to be trained with dynamic depth and width during the training phase, and after the large model is trained we can select a subnetwork from it with arbitrary depth and width during the inference phase with a relatively better performance compared to training the subnetwork independently from scratch. Experiment results on a music source separation model show that our proposed method can effectively improve the separation performance across different subnetwork sizes and complexities with a single large model, and training the large model takes significantly shorter time than training all the different subnetworks.

Guanlong Jiao, Chenyangguang Zhang, Haonan Yin et al.

Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn the capability of generalized semantic segmentation towards the unseen target domains. Previous works typically address this challenge by global style randomization or feature regularization. In this paper, we argue that given the observation that different local semantic regions perform different visual characteristics from the source domain to the target domain, methods focusing on global operations are hard to capture such regional discrepancies, thus failing to construct domain-invariant representations with the consistency from local to global level. Therefore, we propose the Semantic-Rearrangement-based Multi-Level Alignment (SRMA) to overcome this problem. SRMA first incorporates a Semantic Rearrangement Module (SRM), which conducts semantic region randomization to enhance the diversity of the source domain sufficiently. A Multi-Level Alignment module (MLA) is subsequently proposed with the help of such diversity to establish the global-regional-local consistent domain-invariant representations. By aligning features across randomized samples with domain-neutral knowledge at multiple levels, SRMA provides a more robust way to handle the source-target domain gap. Extensive experiments demonstrate the superiority of SRMA over the current state-of-the-art works on various benchmarks.

Yi Luo, Zhenghao Lin, Yuhao Zhang et al.

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising from the imprecision of manually crafted rules and inadequate risk perception in models without safety training. To address these, we introduce Guide-Align, a two-stage approach. Initially, a safety-trained model identifies potential risks and formulates specific guidelines for various inputs, establishing a comprehensive library of guidelines and a model for input-guidelines retrieval. Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values. An additional optional stage involves fine-tuning a model with well-aligned datasets generated through the process implemented in the second stage. Our method customizes guidelines to accommodate diverse inputs, thereby enhancing the fine-grainedness and comprehensiveness of the guideline library. Furthermore, it incorporates safety expertise from a safety-trained LLM through a lightweight retrieval model. We evaluate our approach on three benchmarks, demonstrating significant improvements in LLM security and quality. Notably, our fine-tuned model, Labrador, even at 13 billion parameters, outperforms GPT-3.5-turbo and surpasses GPT-4 in alignment capabilities.

Yi Luo, Hamed Hooshangnejad, Xue Feng et al.

Background: Lung cancer ranks as the leading cause of cancer-related mortality worldwide. The complexity of tumor delineation, crucial for radiation therapy, requires expertise often unavailable in resource-limited settings. Artificial Intelligence(AI), particularly with advancements in deep learning (DL) and natural language processing (NLP), offers potential solutions yet is challenged by high false positive rates. Purpose: The Oncology Contouring Copilot (OCC) system is developed to leverage oncologist expertise for precise tumor contouring using textual descriptions, aiming to increase the efficiency of oncological workflows by combining the strengths of AI with human oversight. Methods: Our OCC system initially identifies nodule candidates from CT scans. Employing Language Vision Models (LVMs) like GPT-4V, OCC then effectively reduces false positives with clinical descriptive texts, merging textual and visual data to automate tumor delineation, designed to elevate the quality of oncology care by incorporating knowledge from experienced domain experts. Results: Deployments of the OCC system resulted in a significant reduction in the false discovery rate by 35.0%, a 72.4% decrease in false positives per scan, and an F1-score of 0.652 across our dataset for unbiased evaluation. Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs to improve contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation, reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVMs hallucinations with ablation study, and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.

Jian Lu, Yi Luo

Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention, with growing efforts to reproduce and apply it. However, training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training are typically deployed on the same devices. While this approach reduces costs through resource consolidation, its synchronous execution imposes a computational coupling that prevents concurrent inference and training. In this study, we are returning to the strategy of separating inference and training deployment, and by introducing improvements in the data loader, we transform the conventional synchronous architecture into a periodically asynchronous framework, which allows for demand-driven, independent, and elastic scaling of each component, while the accuracy of the algorithm remains completely equivalent to the synchronization method, with both belonging to the on-policy strategy. It is worth emphasizing that we apply a unified tri-model architecture in the training phase, and we also proposed a shared-prompt attention mask to reduce repetitive computation. In practice, our approach consistently delivers significant end-to-end training efficiency improvements on NPU platforms, indicating its potential for widespread application.

Shengyu Chen, Shihang Feng, Yi Luo et al.

Ultrasound brain imaging remains challenging due to the large difference in sound speed between the skull and brain tissues and the difficulty of coupling large probes to the skull. This work aims to achieve quantitative transcranial ultrasound by reconstructing an accurate speed-of-sound (SoS) map of the brain. Traditional physics-based full-waveform inversion (FWI) is limited by weak signals caused by skull-induced attenuation, mode conversion, and phase aberration, as well as incomplete spatial coverage since full-aperture arrays are clinically impractical. In contrast, purely data-driven methods that learn directly from raw ultrasound data often fail to model the complex nonlinear and nonlocal wave propagation through bone, leading to anatomically plausible but quantitatively biased SoS maps under low signal-to-noise and sparse-aperture conditions. To address these issues, we propose BrainPuzzle, a hybrid two-stage framework that combines physical modeling with machine learning. In the first stage, reverse time migration (time-reversal acoustics) is applied to multi-angle acquisitions to produce migration fragments that preserve structural details even under low SNR. In the second stage, a transformer-based super-resolution encoder-decoder with a graph-based attention unit (GAU) fuses these fragments into a coherent and quantitatively accurate SoS image. A partial-array acquisition strategy using a movable low-count transducer set improves feasibility and coupling, while the hybrid algorithm compensates for the missing aperture. Experiments on two synthetic datasets show that BrainPuzzle achieves superior SoS reconstruction accuracy and image completeness, demonstrating its potential for advancing quantitative ultrasound brain imaging.

Shengjiao Ji, Yujin Zhang, Zihan Zou et al.

Accurate and efficient simulation of infrared (IR) and Raman spectra is essential for molecular identification and structural analysis. Traditional quantum chemistry methods based on the harmonic approximation neglect anharmonicity and nuclear quantum effects, while ab initio molecular dynamics (AIMD) remains computationally expensive. Here, we integrate our deep equivariant tensor attention network (DetaNet) with a velocity-Verlet integrator to enable fast and accurate machine learning molecular dynamics (MLMD) simulations for spectral prediction. Trained on the QMe14S dataset containing energies, forces, dipole moments, and polarizabilities for 186,102 small organic molecules, DetaNet yields a universal and transferable force field with high-order tensor prediction capability. Using time-correlation functions derived from MLMD and ring-polymer molecular dynamics (RPMD) trajectories, we computed IR and Raman spectra that accurately reproduce anharmonic and nuclear quantum effects. Benchmark tests on isolated molecules, including polycyclic aromatic hydrocarbons, demonstrate that the DetaNet-based MD approach achieves near-experimental spectral accuracy with speedups up to three orders of magnitude over AIMD. Furthermore, the framework extends seamlessly to molecular and inorganic crystals, molecular aggregates, and biological macromolecules such as polypeptides with minimal fine-tuning. In all systems, DetaNet maintains high accuracy while significantly reducing computational cost. Overall, this work establishes a universal machine learning force field and tensor-aware MLMD framework that enable fast, accurate, and broadly applicable dynamic simulations and IR/Raman spectral predictions across diverse molecular and material systems.

Yi Luo, Yike Guo, Hamed Hooshangnejad et al.

Lung cancer remains the leading cause of cancerrelated deaths globally. Accurate delineation of internal gross tumor volume (IGTV) in PET/CT imaging is pivotal for optimal radiation therapy in mobile tumors such as lung cancer to account for tumor motion, yet is hindered by the limited availability of annotated IGTV datasets and attenuated PET signal intensity at tumor boundaries. In this study, we present a transfer learningbased methodology utilizing a multimodal interactive perception network with MAMBA, pre-trained on extensive gross tumor volume (GTV) datasets and subsequently fine-tuned on a private IGTV cohort. This cohort constitutes the PET/CT subset of the Lung-cancer Unified Cross-modal Imaging Dataset (LUCID). To further address the challenge of weak PET intensities in IGTV peripheral slices, we introduce a slice interaction module (SIM) within a 2.5D segmentation framework to effectively model inter-slice relationships. Our proposed module integrates channel and spatial attention branches with depthwise convolutions, enabling more robust learning of slice-to-slice dependencies and thereby improving overall segmentation performance. A comprehensive experimental evaluation demonstrates that our approach achieves a Dice of 0.609 on the private IGTV dataset, substantially surpassing the conventional baseline score of 0.385. This work highlights the potential of transfer learning, coupled with advanced multimodal techniques and a SIM to enhance the reliability and clinical relevance of IGTV segmentation for lung cancer radiation therapy planning.

Zilong Guo, Yi Luo, Long Sha et al.

End-to-end autonomous driving has drawn tremendous attention recently. Many works focus on using modular deep neural networks to construct the end-to-end archi-tecture. However, whether using powerful large language models (LLM), especially multi-modality Vision Language Models (VLM) could benefit the end-to-end driving tasks remain a question. In our work, we demonstrate that combining end-to-end architectural design and knowledgeable VLMs yield impressive performance on the driving tasks. It is worth noting that our method only uses a single camera and is the best camera-only solution across the leaderboard, demonstrating the effectiveness of vision-based driving approach and the potential for end-to-end driving tasks.

Yuntao Shi, Yi Luo, Yeyun Gong et al.

Large Language Models (LLMs) have achieved remarkable success in various domains. However, when handling long-form text modification tasks, they still face two major problems: (1) producing undesired modifications by inappropriately altering or summarizing irrelevant content, and (2) missing necessary modifications to implicitly related passages that are crucial for maintaining document coherence. To address these issues, we propose HiCaM, a Hierarchical-Causal Modification framework that operates through a hierarchical summary tree and a causal graph. Furthermore, to evaluate HiCaM, we derive a multi-domain dataset from various benchmarks, providing a resource for assessing its effectiveness. Comprehensive evaluations on the dataset demonstrate significant improvements over strong LLMs, with our method achieving up to a 79.50\% win rate. These results highlight the comprehensiveness of our approach, showing consistent performance improvements across multiple models and domains.

Yi Luo, Qiwen Wang, Junqi Yang et al.

Generalized Category Discovery (GCD) aims to classify both known and novel categories using partially labeled data that contains only known classes. Despite achieving strong performance on existing benchmarks, current textual GCD methods lack sufficient validation in realistic settings. We introduce Event-Centric GCD (EC-GCD), characterized by long, complex narratives and highly imbalanced class distributions, posing two main challenges: (1) divergent clustering versus classification groupings caused by subjective criteria, and (2) Unfair alignment for minority classes. To tackle these, we propose PaMA, a framework leveraging LLMs to extract and refine event patterns for improved cluster-class alignment. Additionally, a ranking-filtering-mining pipeline ensures balanced representation of prototypes across imbalanced categories. Evaluations on two EC-GCD benchmarks, including a newly constructed Scam Report dataset, demonstrate that PaMA outperforms prior methods with up to 12.58% H-score gains, while maintaining strong generalization on base GCD datasets.

Yi Luo

Frequency-domain beamformers have been successful in a wide range of multi-channel neural separation systems in the past years. However, the operations in conventional frequency-domain beamformers are typically independently-defined and complex-valued, which result in two drawbacks: the former does not fully utilize the advantage of end-to-end optimization, and the latter may introduce numerical instability during the training phase. Motivated by the recent success in end-to-end neural separation systems, in this paper we propose time-domain real-valued generalized Wiener filter (TD-GWF), a linear filter defined on a 2-D learnable real-valued signal transform. TD-GWF splits the transformed representation into groups and performs an minimum mean-square error (MMSE) estimation on all available channels on each of the groups. We show how TD-GWF can be connected to conventional filter-and-sum beamformers when certain signal transform and the number of groups are specified. Moreover, given the recent success in the sequential neural beamforming frameworks, we show how TD-GWF can be applied in such frameworks to perform iterative beamforming and separation to obtain an overall performance gain. Comprehensive experiment results show that TD-GWF performs consistently better than conventional frequency-domain beamformers in the sequential neural beamforming pipeline with various neural network architectures, microphone array scenarios, and task configurations.

Xiaolin Hu, Kai Li, Weiyi Zhang et al.

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired architecture called Fully Recurrent Convolutional Neural Network (FRCNN) to solve the separation task. This model contains bottom-up, top-down and lateral connections to fuse information processed at various time-scales represented by \textit{stages}. In contrast to the traditional approach updating stages in parallel, we propose to first update the stages one by one in the bottom-up direction, then fuse information from adjacent stages simultaneously and finally fuse information from all stages to the bottom stage together. Experiments showed that this asynchronous updating scheme achieved significantly better results with much fewer parameters than the traditional synchronous updating scheme. In addition, the proposed model achieved good balance between speech separation accuracy and computational efficiency as compared to other state-of-the-art models on three benchmark datasets.

Yi Luo, Deniz Mengu, Aydogan Ozcan

Owing to its potential advantages such as scalability, low latency and power efficiency, optical computing has seen rapid advances over the last decades. A core unit of a potential all-optical processor would be the NAND gate, which can be cascaded to perform an arbitrary logical operation. Here, we present the design and analysis of cascadable all-optical NAND gates using diffractive neural networks. We encoded the logical values at the input and output planes of a diffractive NAND gate using the relative optical power of two spatially-separated apertures. Based on this architecture, we numerically optimized the design of a diffractive neural network composed of 4 passive layers to all-optically perform NAND operation using the diffraction of light, and cascaded these diffractive NAND gates to perform complex logical functions by successively feeding the output of one diffractive NAND gate into another. We demonstrated the cascadability of our diffractive NAND gates by using identical diffractive designs to all-optically perform AND and OR operations, as well as a half-adder. Cascadable all-optical NAND gates composed of spatially-engineered passive diffractive layers can serve as a core component of various optical computing platforms.