Rui Xia

Xubo Liu, Qiuqiang Kong, Yan Zhao et al. · bytedance

Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with natural language queries. We train AudioSep on large-scale multimodal datasets and extensively evaluate its capabilities on numerous tasks including audio event separation, musical instrument separation, and speech enhancement. AudioSep demonstrates strong separation performance and impressive zero-shot generalization ability using audio captions or text labels as queries, substantially outperforming previous audio-queried and language-queried sound separation models. For reproducibility of this work, we will release the source code, evaluation benchmark and pre-trained model at: https://github.com/Audio-AGI/AudioSep.

Artem Artemev, Rui Xia, Benjamin M. Boyd et al.

Many machine learning techniques rely on approximating a loss function's curvature, but this is notoriously hard to do at the scale of modern deep networks. Surprisingly, no previous work has exploited the curvature constraints that arise from well known weight-space symmetries in loss landscapes. By analytically averaging over group actions that leave the loss invariant, we construct structured Hessian approximations from single gradients that can be tractably estimated, stored, and inverted. The choice of user-specified symmetry group directly governs the trade-off between approximation accuracy and computational cost. Moreover, our framework provides a unifying theoretical lens for viewing existing methods; in particular, a specific choice of symmetry group recovers Shampoo/Muon-like curvature estimates. We validate our method on a range of network architectures, and deploy it to second-order optimization benchmarks, including a small language model. Our curvature estimation framework might find applications in other machine learning problems such as uncertainty estimation, continual learning, compression/pruning, training data attribution, and more.

Yan Ling, Jianfei Yu, Rui Xia

As an important task in sentiment analysis, Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted increasing attention in recent years. However, previous approaches either (i) use separately pre-trained visual and textual models, which ignore the crossmodal alignment or (ii) use vision-language models pre-trained with general pre-training tasks, which are inadequate to identify finegrained aspects, opinions, and their alignments across modalities. To tackle these limitations, we propose a task-specific Vision-Language Pre-training framework for MABSA (VLPMABSA), which is a unified multimodal encoder-decoder architecture for all the pretraining and downstream tasks. We further design three types of task-specific pre-training tasks from the language, vision, and multimodal modalities, respectively. Experimental results show that our approach generally outperforms the state-of-the-art approaches on three MABSA subtasks. Further analysis demonstrates the effectiveness of each pretraining task. The source code is publicly released at https://github.com/NUSTM/VLP-MABSA.

Hongjie Cai, Nan Song, Zengzhi Wang et al.

Aspect-based sentiment analysis is a long-standing research interest in the field of opinion mining, and in recent years, researchers have gradually shifted their focus from simple ABSA subtasks to end-to-end multi-element ABSA tasks. However, the datasets currently used in the research are limited to individual elements of specific tasks, usually focusing on in-domain settings, ignoring implicit aspects and opinions, and with a small data scale. To address these issues, we propose a large-scale Multi-Element Multi-Domain dataset (MEMD) that covers the four elements across five domains, including nearly 20,000 review sentences and 30,000 quadruples annotated with explicit and implicit aspects and opinions for ABSA research. Meanwhile, we evaluate generative and non-generative baselines on multiple ABSA subtasks under the open domain setting, and the results show that open domain ABSA as well as mining implicit aspects and opinions remain ongoing challenges to be addressed. The datasets are publicly released at \url{https://github.com/NUSTM/MEMD-ABSA}.

Yun Luo, Hongjie Cai, Linyi Yang et al.

Since previous studies on open-domain targeted sentiment analysis are limited in dataset domain variety and sentence level, we propose a novel dataset consisting of 6,013 human-labeled data to extend the data domains in topics of interest and document level. Furthermore, we offer a nested target annotation schema to extract the complete sentiment information in documents, boosting the practicality and effectiveness of open-domain targeted sentiment analysis. Moreover, we leverage the pre-trained model BART in a sequence-to-sequence generation method for the task. Benchmark results show that there exists large room for improvement of open-domain targeted sentiment analysis. Meanwhile, experiments have shown that challenges remain in the effective use of open-domain data, long documents, the complexity of target structure, and domain variances.

Zengzhi Wang, Qiming Xie, Yi Feng et al.

Recently, ChatGPT has drawn great attention from both the research community and the public. We are particularly interested in whether it can serve as a universal sentiment analyzer. To this end, in this work, we provide a preliminary evaluation of ChatGPT on the understanding of \emph{opinions}, \emph{sentiments}, and \emph{emotions} contained in the text. Specifically, we evaluate it in three settings, including \emph{standard} evaluation, \emph{polarity shift} evaluation and \emph{open-domain} evaluation. We conduct an evaluation on 7 representative sentiment analysis tasks covering 17 benchmark datasets and compare ChatGPT with fine-tuned BERT and corresponding state-of-the-art (SOTA) models on them. We also attempt several popular prompting techniques to elicit the ability further. Moreover, we conduct human evaluation and present some qualitative case studies to gain a deep comprehension of its sentiment analysis capabilities.

Zongqian Zhan, Rui Xia, Yifei Yu et al.

Over the last decades, ample achievements have been made on Structure from motion (SfM). However, the vast majority of them basically work in an offline manner, i.e., images are firstly captured and then fed together into a SfM pipeline for obtaining poses and sparse point cloud. In this work, on the contrary, we present an on-the-fly SfM: running online SfM while image capturing, the newly taken On-the-Fly image is online estimated with the corresponding pose and points, i.e., what you capture is what you get. Specifically, our approach firstly employs a vocabulary tree that is unsupervised trained using learning-based global features for fast image retrieval of newly fly-in image. Then, a robust feature matching mechanism with least squares (LSM) is presented to improve image registration performance. Finally, via investigating the influence of newly fly-in image's connected neighboring images, an efficient hierarchical weighted local bundle adjustment (BA) is used for optimization. Extensive experimental results demonstrate that on-the-fly SfM can meet the goal of robustly registering the images while capturing in an online way.

Zongqian Zhan, Yifei Yu, Rui Xia et al.

In the last twenty years, Structure from Motion (SfM) has been a constant research hotspot in the fields of photogrammetry, computer vision, robotics etc., whereas real-time performance is just a recent topic of growing interest. This work builds upon the original on-the-fly SfM (Zhan et al., 2024) and presents an updated version with three new advancements to get better 3D from what you capture: (i) real-time image matching is further boosted by employing the Hierarchical Navigable Small World (HNSW) graphs, thus more true positive overlapping image candidates are faster identified; (ii) a self-adaptive weighting strategy is proposed for robust hierarchical local bundle adjustment to improve the SfM results; (iii) multiple agents are included for supporting collaborative SfM and seamlessly merge multiple 3D reconstructions into a complete 3D scene when commonly registered images appear. Various comprehensive experiments demonstrate that the proposed SfM method (named on-the-fly SfMv2) can generate more complete and robust 3D reconstructions in a high time-efficient way. Code is available at http://yifeiyu225.github.io/on-the-flySfMv2.github.io/.

Xiangqing Shen, Siwei Wu, Rui Xia

ATOMIC is a large-scale commonsense knowledge graph (CSKG) containing everyday if-then knowledge triplets, i.e., {head event, relation, tail event}. The one-hop annotation manner made ATOMIC a set of independent bipartite graphs, which ignored the numerous links between events in different bipartite graphs and consequently caused shortages in knowledge coverage and multi-hop paths. In this work, we aim to construct Dense-ATOMIC with high knowledge coverage and massive multi-hop paths. The events in ATOMIC are normalized to a consistent pattern at first. We then propose a CSKG completion method called Rel-CSKGC to predict the relation given the head event and the tail event of a triplet, and train a CSKG completion model based on existing triplets in ATOMIC. We finally utilize the model to complete the missing links in ATOMIC and accordingly construct Dense-ATOMIC. Both automatic and human evaluation on an annotated subgraph of ATOMIC demonstrate the advantage of Rel-CSKGC over strong baselines. We further conduct extensive evaluations on Dense-ATOMIC in terms of statistics, human evaluation, and simple downstream tasks, all proving Dense-ATOMIC's advantages in Knowledge Coverage and Multi-hop Paths. Both the source code of Rel-CSKGC and Dense-ATOMIC are publicly available on https://github.com/NUSTM/Dense-ATOMIC.

Hengbo Liu, Ziqing Ma, Linxiao Yang et al.

Accurate prediction of electric load is crucial in power grid planning and management. In this paper, we solve the electric load forecasting problem under extreme events such as scorching heats. One challenge for accurate forecasting is the lack of training samples under extreme conditions. Also load usually changes dramatically in these extreme conditions, which calls for interpretable model to make better decisions. In this paper, we propose a novel forecasting framework, named Self-adaptive Decomposed Interpretable framework~(SaDI), which ensembles long-term trend, short-term trend, and period modelings to capture temporal characteristics in different components. The external variable triggered loss is proposed for the imbalanced learning under extreme events. Furthermore, Generalized Additive Model (GAM) is employed in the framework for desirable interpretability. The experiments on both Central China electric load and public energy meters from buildings show that the proposed SaDI framework achieves average 22.14% improvement compared with the current state-of-the-art algorithms in forecasting under extreme events in terms of daily mean of normalized RMSE. Code, Public datasets, and Appendix are available at: https://doi.org/10.24433/CO.9696980.v1 .

Zengzhi Wang, Rui Xia, Jianfei Yu

Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.

Yaochen Zhu, Xiangqing Shen, Rui Xia

Personality traits, emotions, and beliefs shape individuals' behavioral choices and decision-making processes. However, for one thing, the affective computing community normally focused on predicting personality traits but overlooks their application in behavior prediction. For another, the multimodal reasoning task emphasized the prediction of future states and behaviors but often neglected the incorporation of individual personality traits. In this work, we introduce a new task called Personality-aware Human-centric Multimodal Reasoning (PHMR) (T1), with the goal of forecasting the future behavior of a particular individual using multimodal information from past instances, while integrating personality factors. We accordingly construct a new dataset based on six television shows, encompassing 225 characters and 12k samples. To establish a benchmark for the task, we propose seven baseline methods: three adapted from related tasks, two pre-trained model, and two multimodal large language models. The experimental results demonstrate that incorporating personality traits enhances human-centric multimodal reasoning performance. To further solve the lack of personality annotation in real-life scenes, we introduce an extension task called Personality-predicted Human-centric Multimodal Reasoning task (T2) along with the corresponding dataset and method. We will make our dataset and code available on GitHub.

Jinliang Lu, Ziliang Pang, Min Xiao et al.

The remarkable success of Large Language Models (LLMs) has ushered natural language processing (NLP) research into a new era. Despite their diverse capabilities, LLMs trained on different corpora exhibit varying strengths and weaknesses, leading to challenges in maximizing their overall efficiency and versatility. To address these challenges, recent studies have explored collaborative strategies for LLMs. This paper provides a comprehensive overview of this emerging research area, highlighting the motivation behind such collaborations. Specifically, we categorize collaborative strategies into three primary approaches: Merging, Ensemble, and Cooperation. Merging involves integrating multiple LLMs in the parameter space. Ensemble combines the outputs of various LLMs. Cooperation} leverages different LLMs to allow full play to their diverse capabilities for specific tasks. We provide in-depth introductions to these methods from different perspectives and discuss their potential applications. Additionally, we outline future research directions, hoping this work will catalyze further studies on LLM collaborations and paving the way for advanced NLP applications.

Qisong Xiao, Xinhai Chen, Qinglin Wang et al.

Deep learning has emerged as a promising paradigm for spatio-temporal modeling of fluid dynamics. However, existing approaches often suffer from limited generalization to unseen flow conditions and typically require retraining when applied to new scenarios. In this paper, we present LLM4Fluid, a spatio-temporal prediction framework that leverages Large Language Models (LLMs) as generalizable neural solvers for fluid dynamics. The framework first compresses high-dimensional flow fields into a compact latent space via reduced-order modeling enhanced with a physics-informed disentanglement mechanism, effectively mitigating spatial feature entanglement while preserving essential flow structures. A pretrained LLM then serves as a temporal processor, autoregressively predicting the dynamics of physical sequences with time series prompts. To bridge the modality gap between prompts and physical sequences, which can otherwise degrade prediction accuracy, we propose a dedicated modality alignment strategy that resolves representational mismatch and stabilizes long-term prediction. Extensive experiments across diverse flow scenarios demonstrate that LLM4Fluid functions as a robust and generalizable neural solver without retraining, achieving state-of-the-art accuracy while exhibiting powerful zero-shot and in-context learning capabilities. Code and datasets are publicly available at https://github.com/qisongxiao/LLM4Fluid.

Yunlong Chen, Yaming Zhang, Jianfei Yu et al.

Knowledge Base Question Answering (KBQA) aims to answer factoid questions based on knowledge bases. However, generating the most appropriate knowledge base query code based on Natural Language Questions (NLQ) poses a significant challenge in KBQA. In this work, we focus on the CCKS2023 Competition of Question Answering with Knowledge Graph Inference for Unmanned Systems. Inspired by the recent success of large language models (LLMs) like ChatGPT and GPT-3 in many QA tasks, we propose a ChatGPT-based Cypher Query Language (CQL) generation framework to generate the most appropriate CQL based on the given NLQ. Our generative framework contains six parts: an auxiliary model predicting the syntax-related information of CQL based on the given NLQ, a proper noun matcher extracting proper nouns from the given NLQ, a demonstration example selector retrieving similar examples of the input sample, a prompt constructor designing the input template of ChatGPT, a ChatGPT-based generation model generating the CQL, and an ensemble model to obtain the final answers from diversified outputs. With our ChatGPT-based CQL generation framework, we achieved the second place in the CCKS 2023 Question Answering with Knowledge Graph Inference for Unmanned Systems competition, achieving an F1-score of 0.92676.

Yukun Feng, Ming Tu, Rui Xia et al.

Recent studies have shown that using an external Language Model (LM) benefits the end-to-end Automatic Speech Recognition (ASR). However, predicting tokens that appear less frequently in the training set is still quite challenging. The long-tail prediction problems have been widely studied in many applications, but only been addressed by a few studies for ASR and LMs. In this paper, we propose a new memory augmented lookup dictionary based Transformer architecture for LM. The newly introduced lookup dictionary incorporates rich contextual information in training set, which is vital to correctly predict long-tail tokens. With intensive experiments on Chinese and English data sets, our proposed method is proved to outperform the baseline Transformer LM by a great margin on both word/character error rate and tail tokens error rate. This is achieved without impact on the decoding efficiency. Overall, we demonstrate the effectiveness of our proposed method in boosting the ASR decoding performance, especially for long-tail tokens.

Qiming Xie, Zengzhi Wang, Yi Feng et al.

We observe that current conversational language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable responses and building user trust. To comprehensively assess this issue, we introduce a \textsc{Follow-up Questioning Mechanism} along with two metrics to quantify this inconsistency, confirming its widespread presence in current language models. To mitigate this issue, we explore various prompting strategies for closed-source models; moreover, we develop a training-based framework \textsc{Unwavering-FQ} that teaches language models to maintain their originally correct judgments through synthesized high-quality preference data. Our experimental results confirm the effectiveness of our framework and its ability to enhance the general capabilities of models.

Zengzhi Wang, Xuefeng Li, Rui Xia et al.

High-quality, large-scale corpora are the cornerstone of building foundation models. In this work, we introduce MathPile, a diverse and high-quality math-centric corpus comprising about 9.5 billion tokens. Throughout its creation, we adhered to the principle of "less is more", firmly believing in the supremacy of data quality over quantity, even in the pre-training phase. Our meticulous data collection and processing efforts included a complex suite of preprocessing, prefiltering, language identification, cleaning, filtering, and deduplication, ensuring the high quality of our corpus. Furthermore, we performed data contamination detection on downstream benchmark test sets to eliminate duplicates and conducted continual pre-training experiments, booting the performance on common mathematical reasoning benchmarks. We aim for our MathPile to boost language models' mathematical reasoning abilities and open-source its different versions and processing scripts to advance the field.

Rui Xia, Chao Xue, Boyu Deng et al.

Current researches indicate that inductive bias (IB) can improve Vision Transformer (ViT) performance. However, they introduce a pyramid structure concurrently to counteract the incremental FLOPs and parameters caused by introducing IB. This structure destroys the unification of computer vision and natural language processing (NLP) and complicates the model. We study an NLP model called LSRA, which introduces IB with a pyramid-free structure. We analyze why it outperforms ViT, discovering that introducing IB increases the share of high-frequency data in each layer, giving "attention" to more information. As a result, the heads notice more diverse information, showing better performance. To further explore the potential of transformers, we propose EIT, which Efficiently introduces IB to ViT with a novel decreasing convolutional structure under a pyramid-free structure. EIT achieves competitive performance with the state-of-the-art (SOTA) methods on ImageNet-1K and achieves SOTA performance over the same scale models which have the pyramid-free structure.

Siwei Wu, Xiangqing Shen, Rui Xia

Large Language Models (LLMs), such as ChatGPT, have recently been applied to various NLP tasks due to its open-domain generation capabilities. However, there are two issues with applying LLMs to dialogue tasks. 1. During the dialogue process, users may have implicit intentions that might be overlooked by LLMs. Consequently, generated responses couldn't align with the user's intentions. 2. It is unlikely for LLMs to encompass all fields comprehensively. In certain specific domains, their knowledge may be incomplete, and LLMs cannot update the latest knowledge in real-time. To tackle these issues, we propose a framework~\emph{using LLM to \textbf{E}nhance dialogue response generation by asking questions to \textbf{D}etect user's \textbf{I}mplicit in\textbf{T}entions} (\textbf{EDIT}). Firstly, EDIT generates open questions related to the dialogue context as the potential user's intention; Then, EDIT answers those questions by interacting with LLMs and searching in domain-specific knowledge bases respectively, and use LLMs to choose the proper answers to questions as extra knowledge; Finally, EDIT enhances response generation by explicitly integrating those extra knowledge. Besides, previous question generation works only focus on asking questions with answers in context. In order to ask open questions, we construct a Context-Open-Question (COQ) dataset. On two task-oriented dialogue tasks (Wizard of Wikipedia and Holl-E), EDIT outperformed other LLMs.

Xiangqing Shen, Fanfan Wang, Siwei Wu et al.

Visual commonsense plays a vital role in understanding and reasoning about the visual world. While commonsense knowledge bases like ConceptNet provide structured collections of general facts, they lack visually grounded representations. Scene graph datasets like Visual Genome, though rich in object-level descriptions, primarily focus on directly observable information and lack systematic categorization of commonsense knowledge. We present Visual Commonsense Dataset (VCD), a large-scale dataset containing over 100,000 images and 14 million object-commonsense pairs that bridges this gap. VCD introduces a novel three-level taxonomy for visual commonsense, integrating both Seen (directly observable) and Unseen (inferrable) commonsense across Property, Action, and Space aspects. Each commonsense is represented as a triple where the head entity is grounded to object bounding boxes in images, enabling scene-dependent and object-specific visual commonsense representation. To demonstrate VCD's utility, we develop VCM, a generative model that combines a vision-language model with instruction tuning to discover diverse visual commonsense from images. Extensive evaluations demonstrate both the high quality of VCD and its value as a resource for advancing visually grounded commonsense understanding and reasoning. Our dataset and code will be released on https://github.com/NUSTM/VCD.

Yaochen Zhu, Rui Xia, Jiajun Zhang

Model merging is to combine fine-tuned models derived from multiple domains, with the intent of enhancing the model's proficiency across various domains. The principal concern is the resolution of parameter conflicts. A substantial amount of existing research remedy this issue during the merging stage, with the latest study focusing on resolving this issue throughout the pruning stage. The DARE approach has exhibited promising outcomes when applied to a simplistic fine-tuned model. However, the efficacy of this method tends to wane when employed on complex fine-tuned models that show a significant parameter bias relative to the baseline model. In this paper, we introduce a dual-stage method termed Dynamic Pruning Partition Amplification (DPPA), devised to tackle the challenge of merging complex fine-tuned models. Initially, we introduce Dynamically Pruning (DP), an improved approach based on magnitude pruning, which aim is to enhance performance at higher pruning rates. Subsequently, we propose Dynamically Partition Amplification (DPA), a rescaling strategy, is designed to dynamically amplify parameter partitions in relation to their significance levels. The experimental results show that our method maintains a mere 20% of domain-specific parameters and yet delivers a performance comparable to other methodologies that preserve up to 90% of parameters. Furthermore, our method displays outstanding performance post-pruning, leading to a significant improvement of nearly 20% performance in model merging. We make our code on Github.

Zilu Dong, Xiangqing Shen, Rui Xia

As large language models continue to scale up, knowledge editing techniques that modify models' internal knowledge without full retraining have gained significant attention. MEMIT, a prominent batch editing algorithm, stands out for its capability to perform mass knowledge modifications. However, we uncover that MEMIT's editing efficacy significantly deteriorates when processing batches containing multiple edits sharing the same subject. Our analysis reveals this stems from MEMIT's key value modeling framework: identical keys (derived from the shared subject) are forced to represent different values (corresponding to different knowledge), resulting in update conflicts during editing. Addressing this issue, we propose MEMIT-Merge, an enhanced approach that merges value computation processes for facts sharing the same subject, effectively resolving the performance degradation in samesubject batch editing scenarios. Experimental results demonstrate that when MEMIT's edit success rate drops to around 50% at larger batch sizes, MEMIT-Merge maintains a success rate exceeding 90%, showcasing remarkable robustness to subject entity collisions. The code is available at https://github.com/NUSTM/ MEMIT-Merge.

Tengfei Wang, Zongqian Zhan, Rui Xia et al.

Over the last few decades, image-based building surface reconstruction has garnered substantial research interest and has been applied across various fields, such as heritage preservation, architectural planning, etc. Compared to the traditional photogrammetric and NeRF-based solutions, recently, Gaussian fields-based methods have exhibited significant potential in generating surface meshes due to their time-efficient training and detailed 3D information preservation. However, most gaussian fields-based methods are trained with all image pixels, encompassing building and nonbuilding areas, which results in a significant noise for building meshes and degeneration in time efficiency. This paper proposes a novel framework, Masked Gaussian Fields (MGFs), designed to generate accurate surface reconstruction for building in a time-efficient way. The framework first applies EfficientSAM and COLMAP to generate multi-level masks of building and the corresponding masked point clouds. Subsequently, the masked gaussian fields are trained by integrating two innovative losses: a multi-level perceptual masked loss focused on constructing building regions and a boundary loss aimed at enhancing the details of the boundaries between different masks. Finally, we improve the tetrahedral surface mesh extraction method based on the masked gaussian spheres. Comprehensive experiments on UAV images demonstrate that, compared to the traditional method and several NeRF-based and Gaussian-based SOTA solutions, our approach significantly improves both the accuracy and efficiency of building surface reconstruction. Notably, as a byproduct, there is an additional gain in the novel view synthesis of building.

Runda Guan, Xiangqing Shen, Jiajun Zhang et al.

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller LLMs using costly process supervision that often overfits to a single solver API. Inspired by reinforcement learning with verifiable rewards, we propose Execution-Verified Optimization Modeling (EVOM), an execution-verified learning framework that treats a mathematical programming solver as a deterministic, interactive verifier. Given a natural-language problem and a target solver, EVOM generates solver-specific code, executes it in a sandboxed harness, and converts execution outcomes into scalar rewards, optimized with GRPO and DAPO in a closed-loop generate-execute-feedback-update process. This outcome-only formulation removes the need for process-level supervision, and enables cross-solver generalization by switching the verification environment rather than reconstructing solver-specific datasets. Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT, supports zero-shot solver transfer, and achieves effective low-cost solver adaptation by continuing training under the target solver backend.

Siwei Wu, Xiangqing Shen, Rui Xia

The nodes in the commonsense knowledge graph (CSKG) are normally represented by free-form short text (e.g., word or phrase). Different nodes may represent the same concept. This leads to the problems of edge sparsity and node redundancy, which challenges CSKG representation and completion. On the one hand, edge sparsity limits the performance of graph representation learning; On the other hand, node redundancy makes different nodes corresponding to the same concept have inconsistent relations with other nodes. To address the two problems, we propose a new CSKG completion framework based on Contrastive Pretraining and Node Clustering (CPNC). Contrastive Pretraining constructs positive and negative head-tail node pairs on CSKG and utilizes contrastive learning to obtain better semantic node representation. Node Clustering aggregates nodes with the same concept into a latent concept, assisting the task of CSKG completion. We evaluate our CPNC approach on two CSKG completion benchmarks (CN-100K and ATOMIC), where CPNC outperforms the state-of-the-art methods. Extensive experiments demonstrate that both Contrastive Pretraining and Node Clustering can significantly improve the performance of CSKG completion. The source code of CPNC is publicly available on \url{https://github.com/NUSTM/CPNC}.

Siyuan Feng, Ming Tu, Rui Xia et al.

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units, however graphemes may not be ideal for multilingual phonetic sharing. In this paper, we leverage International Phonetic Alphabet (IPA) based language-universal phonetic model to improve low-resource ASR performances, for the first time within the attention encoder-decoder architecture. We propose an adaptation method on the phonetic IPA model to further improve the proposed approach on extreme low-resource languages. Experiments carried out on the open-source MLS corpus and our internal databases show our approach outperforms baseline monolingual models and most state-of-the-art works. Our main approach and adaptation are effective on extremely low-resource languages, even within domain- and language-mismatched scenarios.

Fanfan Wang, Heqing Ma, Jianfei Yu et al.

The ability to understand emotions is an essential component of human-like artificial intelligence, as emotions greatly influence human cognition, decision making, and social interactions. In addition to emotion recognition in conversations, the task of identifying the potential causes behind an individual's emotional state in conversations, is of great importance in many application scenarios. We organize SemEval-2024 Task 3, named Multimodal Emotion Cause Analysis in Conversations, which aims at extracting all pairs of emotions and their corresponding causes from conversations. Under different modality settings, it consists of two subtasks: Textual Emotion-Cause Pair Extraction in Conversations (TECPE) and Multimodal Emotion-Cause Pair Extraction in Conversations (MECPE). The shared task has attracted 143 registrations and 216 successful submissions. In this paper, we introduce the task, dataset and evaluation settings, summarize the systems of the top teams, and discuss the findings of the participants.

Qitao Tan, Sung-En Chang, Rui Xia et al.

Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings. However, this seemingly promising approach faces a significant and long-ignored challenge. ZO requires generating a substantial number of Gaussian random numbers, which poses significant difficulties and even makes it infeasible for hardware platforms, such as FPGAs and ASICs. In this paper, we identify this critical issue, which arises from the mismatch between algorithm and hardware designers. To address this issue, we proposed PeZO, a perturbation-efficient ZO framework. Specifically, we design random number reuse strategies to significantly reduce the demand for random number generation and introduce a hardware-friendly adaptive scaling method to replace the costly Gaussian distribution with a uniform distribution. Our experiments show that PeZO reduces the required LUTs and FFs for random number generation by 48.6\% and 12.7\%, and saves at maximum 86\% power consumption, all without compromising training performance, making ZO optimization feasible for on-device training. To the best of our knowledge, we are the first to explore the potential of on-device ZO optimization, providing valuable insights for future research.

Xiangqing Shen, Fanfan Wang, Rui Xia

LLMs have demonstrated remarkable capabilities in complex reasoning tasks, yet they often suffer from hallucinations and lack reliable factual grounding. Meanwhile, knowledge graphs (KGs) provide structured factual knowledge but lack the flexible reasoning abilities of LLMs. In this paper, we present Reason-Align-Respond (RAR), a novel framework that systematically integrates LLM reasoning with knowledge graphs for KGQA. Our approach consists of three key components: a Reasoner that generates human-like reasoning chains, an Aligner that maps these chains to valid KG paths, and a Responser that synthesizes the final answer. We formulate this process as a probabilistic model and optimize it using the Expectation-Maximization algorithm, which iteratively refines the reasoning chains and knowledge paths. Extensive experiments on multiple benchmarks demonstrate the effectiveness of RAR, achieving state-of-the-art performance with Hit@1 scores of 93.3% and 91.0% on WebQSP and CWQ respectively. Human evaluation confirms that RAR generates high-quality, interpretable reasoning chains well-aligned with KG paths. Furthermore, RAR exhibits strong zero-shot generalization capabilities and maintains computational efficiency during inference.

Zilu Dong, Xiangqing Shen, Zinong Yang et al.

Current knowledge editing methods for large language models (LLMs) struggle to maintain logical consistency when propagating ripple effects to associated facts. We propose ChainEdit, a framework that synergizes knowledge graph-derived logical rules with LLM logical reasoning capabilities to enable systematic chain updates. By automatically extracting logical patterns from structured knowledge bases and aligning them with LLMs' internal logics, ChainEdit dynamically generates and edits logically connected knowledge clusters. Experiments demonstrate an improvement of more than 30% in logical generalization over baselines while preserving editing reliability and specificity. We further address evaluation biases in existing benchmarks through knowledge-aware protocols that disentangle external dependencies. This work establishes new state-of-the-art performance on ripple effect while ensuring internal logical consistency after knowledge editing.

Jamie McGowan, Wei Sheng Lai, Weibin Chen et al.

In many domains, the most successful AI models tend to be the largest, indeed often too large to be handled by AI players with limited computational resources. To mitigate this, a number of compression methods have been developed, including methods that prune the network down to high sparsity whilst retaining performance. The best-performing pruning techniques are often those that use second-order curvature information (such as an estimate of the Fisher information matrix) to score the importance of each weight and to predict the optimal compensation for weight deletion. However, these methods are difficult to scale to high-dimensional parameter spaces without making heavy approximations. Here, we propose the FishLeg surgeon (FLS), a new second-order pruning method based on the Fisher-Legendre (FishLeg) optimizer. At the heart of FishLeg is a meta-learning approach to amortising the action of the inverse FIM, which brings a number of advantages. Firstly, the parameterisation enables the use of flexible tensor factorisation techniques to improve computational and memory efficiency without sacrificing much accuracy, alleviating challenges associated with scalability of most second-order pruning methods. Secondly, directly estimating the inverse FIM leads to less sensitivity to the amplification of stochasticity during inversion, thereby resulting in more precise estimates. Thirdly, our approach also allows for progressive assimilation of the curvature into the parameterisation. In the gradual pruning regime, this results in a more efficient estimate refinement as opposed to re-estimation. We find that FishLeg achieves higher or comparable performance against two common baselines in the area, most notably in the high sparsity regime when considering a ResNet18 model on CIFAR-10 (84% accuracy at 95% sparsity vs 60% for OBS) and TinyIM (53% accuracy at 80% sparsity vs 48% for OBS).

Wenjie Zheng, Qiming Xie, Zengzhi Wang et al.

Recently, multimodal depression recognition for clinical interviews (MDRC) has recently attracted considerable attention. Existing MDRC studies mainly focus on improving task performance and have achieved significant development. However, for clinical applications, model transparency is critical, and previous works ignore the interpretability of decision-making processes. To address this issue, we propose an Explainable Multimodal Depression Recognition for Clinical Interviews (EMDRC) task, which aims to provide evidence for depression recognition by summarizing symptoms and uncovering underlying causes. Given an interviewer-participant interaction scenario, the goal of EMDRC is to structured summarize participant's symptoms based on the eight-item Patient Health Questionnaire depression scale (PHQ-8), and predict their depression severity. To tackle the EMDRC task, we construct a new dataset based on an existing MDRC dataset. Moreover, we utilize the PHQ-8 and propose a PHQ-aware multimodal multi-task learning framework, which captures the utterance-level symptom-related semantic information to help generate dialogue-level summary. Experiment results on our annotated dataset demonstrate the superiority of our proposed methods over baseline systems on the EMDRC task.

Yuhang Wu, Xiangqing Shen, Fanfan Wang et al.

Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream generation process. This isolation leads to a fundamental misalignment: documents identified as topically relevant by information retrieval metrics often fail to provide the actual utility required by the LLM for precise answer generation. To bridge this gap, we introduce ReRanking Preference Optimization (RRPO), a reinforcement learning framework that directly aligns reranking with the LLM's generation quality. By formulating reranking as a sequential decision-making process, RRPO optimizes for context utility using LLM feedback, thereby eliminating the need for expensive human annotations. To ensure training stability, we further introduce a reference-anchored deterministic baseline. Extensive experiments on knowledge-intensive benchmarks demonstrate that RRPO significantly outperforms strong baselines, including the powerful list-wise reranker RankZephyr. Further analysis highlights the versatility of our framework: it generalizes seamlessly to diverse readers (e.g., GPT-4o), integrates orthogonally with query expansion modules like Query2Doc, and remains robust even when trained with noisy supervisors.

Rui Xia, Dan Jiang, Quan Zhang et al.

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive and time-consuming. Consequently, unsupervised temporal action localization (UTAL) has gained popularity. However, current methods face two main challenges: 1) Classification pre-trained features overly focus on highly discriminative regions; 2) Solely relying on visual modality information makes it difficult to determine contextual boundaries. To address these issues, we propose a CLIP-assisted cross-view audiovisual enhanced UTAL method. Specifically, we introduce visual language pre-training (VLP) and classification pre-training-based collaborative enhancement to avoid excessive focus on highly discriminative regions; we also incorporate audio perception to provide richer contextual boundary information. Finally, we introduce a self-supervised cross-view learning paradigm to achieve multi-view perceptual enhancement without additional annotations. Extensive experiments on two public datasets demonstrate our model's superiority over several state-of-the-art competitors.

Jinyuan Li, Ziyan Li, Han Li et al.

Grounded Multimodal Named Entity Recognition (GMNER) task aims to identify named entities, entity types and their corresponding visual regions. GMNER task exhibits two challenging attributes: 1) The tenuous correlation between images and text on social media contributes to a notable proportion of named entities being ungroundable. 2) There exists a distinction between coarse-grained noun phrases used in similar tasks (e.g., phrase localization) and fine-grained named entities. In this paper, we propose RiVEG, a unified framework that reformulates GMNER into a joint MNER-VE-VG task by leveraging large language models (LLMs) as connecting bridges. This reformulation brings two benefits: 1) It enables us to optimize the MNER module for optimal MNER performance and eliminates the need to pre-extract region features using object detection methods, thus naturally addressing the two major limitations of existing GMNER methods. 2) The introduction of Entity Expansion Expression module and Visual Entailment (VE) module unifies Visual Grounding (VG) and Entity Grounding (EG). This endows the proposed framework with unlimited data and model scalability. Furthermore, to address the potential ambiguity stemming from the coarse-grained bounding box output in GMNER, we further construct the new Segmented Multimodal Named Entity Recognition (SMNER) task and corresponding Twitter-SMNER dataset aimed at generating fine-grained segmentation masks, and experimentally demonstrate the feasibility and effectiveness of using box prompt-based Segment Anything Model (SAM) to empower any GMNER model with the ability to accomplish the SMNER task. Extensive experiments demonstrate that RiVEG significantly outperforms SoTA methods on four datasets across the MNER, GMNER, and SMNER tasks.

Max W. Y. Lam, Qiao Tian, Tang Li et al.

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7% or 99.6% forward passes in MusicLM, respectively, for sampling 10s or 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation. Our samples are available at https://Efficient-MeLoDy.github.io/.

Siyuan Feng, Ming Tu, Rui Xia et al.

We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for unlabeled speech, and use these pseudo labels to guide hidden-unit BERT (HuBERT) based speech pretraining in a phonetically-informed manner. The experiments on the Multilingual Speech (MLS) Corpus show that the proposed approach consistently outperforms the standard HuBERT on all the target languages. Moreover, on 3 of the 4 languages, comparing to the standard HuBERT, the approach performs better, meanwhile is able to save supervised training data by 1.5k hours (75%) at most. Our approach outperforms most of the state of the arts, with much less pretraining data in terms of hours and language diversity. Compared to XLSR-53 and a retraining based multilingual method, our approach performs better with full and limited finetuning data scenarios.

Fanfan Wang, Zixiang Ding, Rui Xia et al.

Emotion cause analysis has received considerable attention in recent years. Previous studies primarily focused on emotion cause extraction from texts in news articles or microblogs. It is also interesting to discover emotions and their causes in conversations. As conversation in its natural form is multimodal, a large number of studies have been carried out on multimodal emotion recognition in conversations, but there is still a lack of work on multimodal emotion cause analysis. In this work, we introduce a new task named Multimodal Emotion-Cause Pair Extraction in Conversations, aiming to jointly extract emotions and their associated causes from conversations reflected in multiple modalities (text, audio and video). We accordingly construct a multimodal conversational emotion cause dataset, Emotion-Cause-in-Friends, which contains 9,272 multimodal emotion-cause pairs annotated on 13,509 utterances in the sitcom Friends. We finally benchmark the task by establishing a baseline system that incorporates multimodal features for emotion-cause pair extraction. Preliminary experimental results demonstrate the potential of multimodal information fusion for discovering both emotions and causes in conversations.

Dongyang Dai, Yuanzhe Chen, Li Chen et al.

With the increasing popularity of speech synthesis products, the industry has put forward more requirements for personalized speech synthesis: (1) How to use low-resource, easily accessible data to clone a person's voice. (2) How to clone a person's voice while controlling the style and prosody. To solve the above two problems, we proposed the Hieratron model framework in which the prosody and timbre are modeled separately using two modules, therefore, the independent control of timbre and the other characteristics of audio can be achieved while generating speech. The practice shows that, for very limited target speaker data in the wild, Hieratron has obvious advantages over the traditional method, in addition to controlling the style and language of the generated speech, the mean opinion score on speech quality of the generated speech has also been improved by more than 0.2 points.

Keke Wang, Xudong Mao, Hao Wu et al.

This paper describes the ByteDance speaker diarization system for the fourth track of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). The VoxSRC-21 provides both the dev set and test set of VoxConverse for use in validation and a standalone test set for evaluation. We first collect the duration and signal-to-noise ratio (SNR) of all audio and find that the distribution of the VoxConverse's test set and the VoxSRC-21's test set is more closer. Our system consists of voice active detection (VAD), speaker embedding extraction, spectral clustering followed by a re-clustering step based on agglomerative hierarchical clustering (AHC) and overlapped speech detection and handling. Finally, we integrate systems with different time scales using DOVER-Lap. Our best system achieves 5.15\% of the diarization error rate (DER) on evaluation set, ranking the second at the diarization track of the challenge.

Qiuqiang Kong, Haohe Liu, Xingjian Du et al.

Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods require noisy and clean speech pairs for training. We propose a speech enhancement framework that can be trained with large-scale weakly labelled AudioSet dataset. Weakly labelled data only contain audio tags of audio clips, but not the onset or offset times of speech. We first apply pretrained audio neural networks (PANNs) to detect anchor segments that contain speech or sound events in audio clips. Then, we randomly mix two detected anchor segments containing speech and sound events as a mixture, and build a conditional source separation network using PANNs predictions as soft conditions for speech enhancement. In inference, we input a noisy speech signal with the one-hot encoding of "Speech" as a condition to the trained system to predict enhanced speech. Our system achieves a PESQ of 2.28 and an SSNR of 8.75 dB on the VoiceBank-DEMAND dataset, outperforming the previous SEGAN system of 2.16 and 7.73 dB respectively.

Zhen Wu, Chengcan Ying, Fei Zhao et al.

Aspect-oriented Fine-grained Opinion Extraction (AFOE) aims at extracting aspect terms and opinion terms from review in the form of opinion pairs or additionally extracting sentiment polarity of aspect term to form opinion triplet. Because of containing several opinion factors, the complete AFOE task is usually divided into multiple subtasks and achieved in the pipeline. However, pipeline approaches easily suffer from error propagation and inconvenience in real-world scenarios. To this end, we propose a novel tagging scheme, Grid Tagging Scheme (GTS), to address the AFOE task in an end-to-end fashion only with one unified grid tagging task. Additionally, we design an effective inference strategy on GTS to exploit mutual indication between different opinion factors for more accurate extractions. To validate the feasibility and compatibility of GTS, we implement three different GTS models respectively based on CNN, BiLSTM, and BERT, and conduct experiments on the aspect-oriented opinion pair extraction and opinion triplet extraction datasets. Extensive experimental results indicate that GTS models outperform strong baselines significantly and achieve state-of-the-art performance.

Dongyang Dai, Li Chen, Yuping Wang et al.

With the popularity of deep neural network, speech synthesis task has achieved significant improvements based on the end-to-end encoder-decoder framework in the recent days. More and more applications relying on speech synthesis technology have been widely used in our daily life. Robust speech synthesis model depends on high quality and customized data which needs lots of collecting efforts. It is worth investigating how to take advantage of low-quality and low resource voice data which can be easily obtained from the Internet for usage of synthesizing personalized voice. In this paper, the proposed end-to-end speech synthesis model uses both speaker embedding and noise representation as conditional inputs to model speaker and noise information respectively. Firstly, the speech synthesis model is pre-trained with both multi-speaker clean data and noisy augmented data; then the pre-trained model is adapted on noisy low-resource new speaker data; finally, by setting the clean speech condition, the model can synthesize the new speaker's clean voice. Experimental results show that the speech generated by the proposed approach has better subjective evaluation results than the method directly fine-tuning pre-trained multi-speaker speech synthesis model with denoised new speaker data.

Rui Xia, Zixiang Ding

Emotion cause extraction (ECE), the task aimed at extracting the potential causes behind certain emotions in text, has gained much attention in recent years due to its wide applications. However, it suffers from two shortcomings: 1) the emotion must be annotated before cause extraction in ECE, which greatly limits its applications in real-world scenarios; 2) the way to first annotate emotion and then extract the cause ignores the fact that they are mutually indicative. In this work, we propose a new task: emotion-cause pair extraction (ECPE), which aims to extract the potential pairs of emotions and corresponding causes in a document. We propose a 2-step approach to address this new ECPE task, which first performs individual emotion extraction and cause extraction via multi-task learning, and then conduct emotion-cause pairing and filtering. The experimental results on a benchmark emotion cause corpus prove the feasibility of the ECPE task as well as the effectiveness of our approach.

Rui Xia, Mengran Zhang, Zixiang Ding

The emotion cause extraction (ECE) task aims at discovering the potential causes behind a certain emotion expression in a document. Techniques including rule-based methods, traditional machine learning methods and deep neural networks have been proposed to solve this task. However, most of the previous work considered ECE as a set of independent clause classification problems and ignored the relations between multiple clauses in a document. In this work, we propose a joint emotion cause extraction framework, named RNN-Transformer Hierarchical Network (RTHN), to encode and classify multiple clauses synchronously. RTHN is composed of a lower word-level encoder based on RNNs to encode multiple words in each clause, and an upper clause-level encoder based on Transformer to learn the correlation between multiple clauses in a document. We furthermore propose ways to encode the relative position and global predication information into Transformer that can capture the causality between clauses and make RTHN more efficient. We finally achieve the best performance among 12 compared systems and improve the F1 score of the state-of-the-art from 72.69\% to 76.77\%.

Zixiang Ding, Huihui He, Mengran Zhang et al.

Emotion cause identification aims at identifying the potential causes that lead to a certain emotion expression in text. Several techniques including rule based methods and traditional machine learning methods have been proposed to address this problem based on manually designed rules and features. More recently, some deep learning methods have also been applied to this task, with the attempt to automatically capture the causal relationship of emotion and its causes embodied in the text. In this work, we find that in addition to the content of the text, there are another two kinds of information, namely relative position and global labels, that are also very important for emotion cause identification. To integrate such information, we propose a model based on the neural network architecture to encode the three elements ($i.e.$, text content, relative position and global label), in an unified and end-to-end fashion. We introduce a relative position augmented embedding learning algorithm, and transform the task from an independent prediction problem to a reordered prediction problem, where the dynamic global label information is incorporated. Experimental results on a benchmark emotion cause dataset show that our model achieves new state-of-the-art performance and performs significantly better than a number of competitive baselines. Further analysis shows the effectiveness of the relative position augmented embedding learning algorithm and the reordered prediction mechanism with dynamic global labels.

Rui Xia, Vincent Y. F. Tan, Louis Filstroff et al.

We propose a novel ranking model that combines the Bradley-Terry-Luce probability model with a nonnegative matrix factorization framework to model and uncover the presence of latent variables that influence the performance of top tennis players. We derive an efficient, provably convergent, and numerically stable majorization-minimization-based algorithm to maximize the likelihood of datasets under the proposed statistical model. The model is tested on datasets involving the outcomes of matches between 20 top male and female tennis players over 14 major tournaments for men (including the Grand Slams and the ATP Masters 1000) and 16 major tournaments for women over the past 10 years. Our model automatically infers that the surface of the court (e.g., clay or hard court) is a key determinant of the performances of male players, but less so for females. Top players on various surfaces over this longitudinal period are also identified in an objective manner.

Saurav Sahay, Shachi H Kumar, Rui Xia et al.

Understanding Affect from video segments has brought researchers from the language, audio and video domains together. Most of the current multimodal research in this area deals with various techniques to fuse the modalities, and mostly treat the segments of a video independently. Motivated by the work of (Zadeh et al., 2017) and (Poria et al., 2017), we present our architecture, Relational Tensor Network, where we use the inter-modal interactions within a segment (intra-segment) and also consider the sequence of segments in a video to model the inter-segment inter-modal interactions. We also generate rich representations of text and audio modalities by leveraging richer audio and linguistic context alongwith fusing fine-grained knowledge based polarity scores from text. We present the results of our model on CMU-MOSEI dataset and show that our model outperforms many baselines and state of the art methods for sentiment classification and emotion recognition.

Guang-Neng Hu, Xin-Yu Dai, Feng-Yu Qiu et al.

Recommender systems (RSs) provide an effective way of alleviating the information overload problem by selecting personalized items for different users. Latent factors based collaborative filtering (CF) has become the popular approaches for RSs due to its accuracy and scalability. Recently, online social networks and user-generated content provide diverse sources for recommendation beyond ratings. Although {\em social matrix factorization} (Social MF) and {\em topic matrix factorization} (Topic MF) successfully exploit social relations and item reviews, respectively, both of them ignore some useful information. In this paper, we investigate the effective data fusion by combining the aforementioned approaches. First, we propose a novel model {\em \mbox{MR3}} to jointly model three sources of information (i.e., ratings, item reviews, and social relations) effectively for rating prediction by aligning the latent factors and hidden topics. Second, we incorporate the implicit feedback from ratings into the proposed model to enhance its capability and to demonstrate its flexibility. We achieve more accurate rating prediction on real-life datasets over various state-of-the-art methods. Furthermore, we measure the contribution from each of the three data sources and the impact of implicit feedback from ratings, followed by the sensitivity analysis of hyperparameters. Empirical studies demonstrate the effectiveness and efficacy of our proposed model and its extension.