论文检索

Sonal Kumar, Šimon Sedláček, Vaibhavi Lokegaonkar, Fernando López, Wenyi Yu, Nishit Anand, Hyeonggon Ryu, Lichang Chen, Maxim Plička, Miroslav Hlaváček 等

Audio comprehension—including speech, non-speech sounds, and music—is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio understanding to qualify as generally intelligent. However, evaluating auditory intelligence comprehensively remains challenging. To address this gap, we introduce MMAU-Pro, the most comprehensive and rigorously curated benchmark for assessing audio intelligence in AI systems. MMAU-Pro contains 5,305 instances, where each instance has one or more audios paired with human expert-generated question-answer pairs, spanning speech, sound, music, and their combinations. Unlike existing benchmarks, MMAU-Pro evaluates auditory intelligence across 49 unique skills and multiple complex dimensions, including long-form audio comprehension, spatial audio reasoning, multi-audio understanding, among others. All questions are meticulously designed to require deliberate multi-hop reasoning, including both multiple-choice and open-ended response formats. Importantly, audio data is sourced directly ``from the wild" rather than from existing datasets with known distributions. We evaluate 22 leading open-source and proprietary multimodal AI models, revealing significant limitations: even state-of-the-art models such as Gemini 2.5 Flash and Audio Flamingo 3 achieve only 57.33% and 45.9% accuracy, respectively, approaching random performance in multiple categories. Our extensive analysis highlights specific shortcomings and provides novel insights, offering actionable perspectives for the community to enhance future AI systems' progression toward audio general intelligence.

Sunwoo Kim, Soo Yong Lee, Kyungho Kim, Hyunjin Hwang, Jaemin Yoo, Kijung Shin

Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal—especially in non-homophilic graphs—since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.

Kwang In Kim

Label errors can significantly degrade model performance, making effective mechanisms crucial. Active error correction (AEC) addresses this by prioritizing data points for human re-labeling where corrections are expected to have significant impact. We extend AEC to distributed collaborative learning, where clients hold local data and a central server allocates labeling resources. Existing AEC methods assume centralized access and do not generalize to distributed settings. To overcome this, we use neural network weight gradients from client updates as proxies for local data and apply a Gaussian process in gradient space to strategically select clients for correction. Our method identifies gradient inconsistencies and encourages diversity through a computationally efficient rank-one Cholesky update. Experiments on eight benchmark datasets demonstrate the effectiveness of our approach.

Faizan Farooq Khan, Joseph K J, Koustava Goswami, Mohamed Elhoseiny, Balaji Vasan Srinivasan

Design generation, in its essence, is a step-by-step process where designers progressively refine and enhance their work through careful modifications. Despite this fundamental characteristic, existing approaches mainly treat design synthesis as a single-step generation problem, significantly underestimating the inherent complexity of the creative process. To bridge this gap, we propose a novel problem setting called Step-by-step Layered Design Generation, that tasks a machine learning model to generate a design, adhering to a sequence of instructions from a designer. Leveraging the recent advancements in Multi-modal LLMs, we propose SLEDGE: Step-by-step LayEred Design GEnerator to model each update to a design as an atomic layered change over its previous state, while being grounded on the instruction.To complement our new problem setting, we introduce a new evaluation suite, including a dataset and a benchmark. Our exhaustive experimental analysis and comparison with state-of-the-art approaches adapted to our new setup bring out the efficacy of our approach. We hope our work will attract attention to this pragmatic and under-explored research area.

Tao Jiang, Zichuan Lin, Lihe Li, Yi-Chen Li, Cong Guan, Lei Yuan, Zongzhang Zhang, Yang Yu, Deheng Ye

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents' current sub-trajectories, inform decision-making. During decentralized execution, we introduce a novel memory mechanism that effectively balances test-time online data with offline memory. Based on the constructed memory, we propose a hybrid utility score that incorporates both individual- and team-level returns, ensuring credit assignment across agents. Extensive experiments on cooperative MARL benchmarks, including Level-Based Foraging (LBF) and SMAC (v1/v2), show that MAICC enables faster adaptation to unseen tasks compared to existing methods.

Ziheng Jia, Jiaying Qian, Zicheng Zhang, Zijian Chen, Xiongkuo Min

Reinforcement fine-tuning (RFT) is a proliferating paradigm for LMM training. Analogous to high-level reasoning tasks, RFT is similarly applicable to low-level vision domains, including image quality assessment (IQA). Existing RFT-based IQA methods typically use rule-based output rewards to verify the model's rollouts but provide no reward supervision for the "think” process, leaving its correctness and efficacy uncontrolled. Furthermore, these methods typically fine-tune directly on downstream IQA tasks without explicitly enhancing the model’s native low-level visual quality perception, which may constrain its performance upper bound. In response to these gaps, we propose the multi‐stage RFT IQA framework (Refine-IQA). In Stage-1, we build the Refine-Perception-20K dataset (with 12 main distortions, 20,907 locally-distorted images, and over 55K RFT samples) and design multi-task reward functions to strengthen the model’s visual quality perception. In Stage-2, targeting the quality scoring task, we introduce a probability difference reward involved strategy for "think" process supervision. The resulting Refine-IQA Series Models achieve outstanding performance on both perception and scoring tasks—and, notably, our paradigm activates a robust "think” (quality interpretating) capability that also attains exceptional results on the corresponding quality interpreting benchmark.

Ziheng Jia, Zicheng Zhang, Xiaorong Zhu, Chunyi Li, Jinliang Han, Xiaohong Liu, Guangtao Zhai, Xiongkuo Min

The data scaling law has significantly enhanced large multi-modal models (LMMs) performance across various downstream tasks. However, in the domain of perceptual video quality assessment (VQA), the potential of data scaling remains unprecedented due to the scarcity of labeled resources and the insufficient scale of datasets. To address this, we propose OmniVQA, a framework designed to efficiently build high-quality, machine-dominated synthetic multi-modal instruction databases (MIDBs) for VQA. We then scale up to create OmniVQA-Chat-400K, the largest dataset in the VQA field concurrently. Our focus is on the technical and aesthetic quality dimensions, with abundant in-context instruction data to provide fine-grained VQA knowledge. Additionally, we build the OmniVQA-MOS-20K dataset to enhance the model's quantitative quality rating capabilities. We then introduce a complementary training strategy that effectively leverages the knowledge from datasets for different tasks. Furthermore, we propose the OmniVQA-FG (fine-grain)-Benchmark to evaluate the fine-grained performance of models. Our results demonstrate that our models achieve state-of-the-art performance in both tasks.

Yifan Jia, Yuntao Du, Kailin Jiang, Yuyang Liang, Qihan Ren, Yi Xin, Rui Yang, Fenze Feng, MingCai Chen, Hengyang Lu 等

Large Multimodal Models (LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation (RAG) frameworks, where the contextual information from external sources may contradict the model’s internal parametric knowledge, leading to unreliable outputs. However, existing benchmarks fail to reflect such realistic conflict scenarios. Most focus solely on intra-memory conflicts, while context-memory and inter-context conflicts remain largely unaddressed. Furthermore, commonly used factual knowledge-based evaluations are often overlooked, and existing datasets lack a thorough investigation into conflict detection capabilities.To bridge this gap, we propose MMKC-Bench, a benchmark designed to evaluate factual knowledge conflicts in both context-memory and inter-context scenarios. MMKC-Bench encompasses four types of multimodal knowledge conflicts and includes 1,881 knowledge instances and 3,997 images across 32 broad types, collected through automated pipelines with human verification. We evaluate four representative series of LMMs on both model behavior analysis and conflict detection tasks. Our findings show that while current LMMs are capable of recognizing knowledge conflicts, they tend to favor internal parametric knowledge over external evidence. We hope MMKC-Bench will foster further research in multimodal knowledge conflict and enhance the development of multimodal RAG systems.

Łukasz Janisiów, Marek Kochańczyk, Bartosz Michał Zieliński, Tomasz Danel

Molecular property prediction is a crucial task that guides the design of new compounds, including drugs and materials. While explainable artificial intelligence methods aim to scrutinize model predictions by identifying influential molecular substructures, many existing approaches rely on masking strategies that remove either atoms or atom-level features to assess importance via fidelity metrics. These methods, however, often fail to adhere to the underlying molecular distribution and thus yield unintuitive explanations. In this work, we propose counterfactual masking, a novel framework that replaces masked substructures with chemically reasonable fragments sampled from generative models trained to complete molecular graphs. Rather than evaluating masked predictions against implausible zeroed-out baselines, we assess them relative to counterfactual molecules drawn from the data distribution. Our method offers two key benefits: (1) molecular realism that underpins robust and distribution-consistent explanations, and (2) meaningful counterfactuals that directly indicate how structural modifications may affect predicted properties. We demonstrate that counterfactual masking is well-suited for benchmarking model explainers and yields more actionable insights across multiple datasets and property prediction tasks. Our approach bridges the gap between explainability and molecular design, offering a principled and generative path toward explainable machine learning in chemistry.

Zixian Huang, Chuan-Xian Ren

Diffusion models have achieved impressive generative performance across diverse domains such as image, video, and scientific data generation. However, fine-tuning these models for new tasks remains challenging due to their large scale, architectural diversity, and high sensitivity to hyperparameters—particularly learning rates. In this work, we propose Wasserstein-Aware Transfer (WAT), a principled and effective fine-tuning strategy grounded in diffusion trajectory analysis and optimal transport theory. Our key insight is that the distributional discrepancies between diffusion trajectories from different datasets decrease progressively over time and converge near the noise end. Based on this observation, we introduce a class-wise matching mechanism that minimizes the Wasserstein distance between class distributions of source and target datasets. This enables alignment at the class level without modifying the standard fine-tuning pipeline. To further enhance knowledge retention, we propose a novel sampling strategy that linearly combines class-conditional outputs from both pretrained and fine-tuned models. This method is simple yet effective, requiring negligible computational overhead while preserving domain-specific and generalizable knowledge. Extensive experiments across seven diverse benchmarks demonstrate that WAT reliably enhances generation quality under distribution shifts, outperforming competitive baselines. These results underscore its robustness and affirm the potential of optimal transport as a principled basis for knowledge transfer in diffusion models.

Zhenyuan Huang, Hui Zhang, Wenzhong Tang, Haijun Yang

Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference method that integrates both invariant and variant features. FedSDWC infers causal semantic representations by modeling the weak causal influence between invariant and variant features, effectively overcoming the limitations of existing invariant learning methods in accurately capturing invariant features and directly constructing causal representations. This approach significantly enhances FL's ability to generalize and detect OOD data. Theoretically, we derive FedSDWC's generalization error bound under specific conditions and, for the first time, establish its relationship with client prior distributions. Moreover, extensive experiments conducted on multiple benchmark datasets validate the superior performance of FedSDWC in handling covariate and semantic shifts. For example, FedSDWC outperforms FedICON, the next best baseline, by an average of 3.04% on CIFAR-10 and 8.11% on CIFAR-100.

Renjun Huang, Han Xiao, Bingqing Li, Baili Zhang, Jianhua Lyu

Time series forecasting plays a critical role across a wide range of domains. Recently, an increasing number of Transformer-based forecasting models have emerged, achieving remarkably competitive performance. However, real-world time series data often exhibit complex multi-scale periodicities, which are not well-suited for modeling by the original Transformer architecture originally developed for NLP tasks. To address this limitation, we propose the Hierarchical Multi-scale Time Series Transformer (HMformer), employing a novel and sophisticated framework specifically designed for multi-scale time series forecasting. Specifically, HMformer incorporates a hierarchical cross-scale mixing mechanism that progressively aggregates temporal information from fine to coarse granularities, a scale-adaptive feature expansion design enhancing the extraction of high-level temporal semantics, and a multi-branch complementary prediction strategy for effectively integrating diverse temporal patterns. Collectively, these components enable HMformer to capture intricate, multi-scale temporal dynamics while retaining the Transformer’s inherent strength in modeling long-range dependencies. Extensive experiments conducted on multiple real-world benchmark datasets—encompassing both long-term and short-term forecasting tasks—demonstrate that HMformer achieves state-of-the-art performance.

Xuemin Hu, Shen Li, Yingfen Xu, Bo Tang, Long Chen

Offline reinforcement learning (RL) can learn policies from pre-collected offline datasets without interacting with the environment, but it suffers from the issue of out-of-distribution (OOD). Recent methods use the generative adversarial paradigm to learn policies, but easily fail to handle the conflict of fooling the discriminator and maximizing expected returns. In this paper, we propose a novel offline RL method named Distribution-Matching Generator-based Diffusion Policies (DMGDP). A distribution matching-based policy learning method is first developed, where the diffusion serves as the policy generator, to handle the conflict of fooling the discriminator and maximizing expected returns. Furthermore, a policy confidence mechanism based on discriminator regularization is designed to prevent the agent from taking OOD actions, with the aim of robust generative adversarial learning. We conducted extensive experiments on the D4RL benchmarks, and the results demonstrate that DMGDP outperforms state-of-the-art methods.

Chunyu Hu, Tianyin Liao, Yicheng Sui, Ran Zhang, Xiao Wang, Ziwei Zhang

Conditional molecular generation, aiming to generate 2D and 3D molecules that satisfy given properties, has achieved remarkable progress, thanks to the advances in deep generative models such as graph diffusion. However, existing methods generally assume that the given conditions for training and testing are consistent, failing to handle the realistic challenge when there exist distribution shifts between training and testing conditions. Invariant learning is a mainstream paradigm for addressing distribution shifts, but fusing invariant learning principles with conditional molecular generation faces three core challenges: (1) existing invariant learning methods focus on discriminative tasks and cannot be directly adapted to molecule generative tasks; (2) how to distinguish between invariant subgraph and variant subgraph of a molecule graph, which is treated as an integrated input; (3) how to fuse invariant subgraphs, variant subgraphs, and property conditions for effective generation. To tackle these challenges, we propose Invariant Conditional MOLecular generation (IC-MOL), a framework that combines invariant learning with graph diffusion to improve the generalization ability of conditional molecular generation under distribution shifts. Specifically, we first disentangle molecular graphs into invariant and variant subgraphs while maintaining SE(3) equivariance, an important inductive bias for molecular generation. On this basis, we further design a two-phase graph diffusion generation model. In the first phase, we generate an invariant molecular consistent with the target property. In the second phase, we propose a cross-attention mechanism to fuse variant subgraph representations and property conditions to guide the generation of complete molecules while maintaining property alignment. Extensive experiments on the benchmark dataset show that IC-MOL consistently outperforms state-of-the-art baselines across six property conditions under distribution shifts.

Zhengzhang Hou, Zhanshan Li, Yanbo Liu, Geoff Nitschke, You Lu, Ximing Li

Data augmentation is an intuitive solution to increase the diversity of training instances in the machine learning community. Mixup is acknowledged as an effective and efficient mix-based data augmentation method, following a linear alignment assumption that the linear interpolations of features align the corresponding linear interpolations of labels. Unfortunately, this assumption can be violated in many complex scenarios, resulting in augmented instances with noisy labels, especially for regression problems. To solve this problem, we propose an easy-to-implement mixup method, namely DEnosing MIXUP (DE-mixup), which iteratively corrects the noisy response targets by leveraging an auxiliary noise estimation task with mixup deep features. Additionally, we suggest an efficient optimization method with alternating direction method of multipliers. We compare DE-mixup with the existing mixup variants and other prevalent data augmentation methods across benchmark regression datasets. Empirical results indicate the effectiveness of DE-mixup under the in-distribution and out-of-distribution cases.

Ming-Yi Hong, You-Chen Teng, Shao-En Lin, Chih-Yu Wang, Che Lin

Graph pooling has gained significant progress in recent years as an effective solution for graph-level property classification tasks. With the emergence of research on Heterogeneous Information Networks (HINs), this paper argues that graph-level datasets for graph classification should be treated as HINs rather than homogeneous graphs to enhance information aggregation. We propose HINPool, a novel and general graph pooling framework for graph-level property classification with HINs. First, we devise a systematic HIN construction procedure from the original data to capture complex interactions. Next, we introduce a type-aware heterogeneous graph pooling method featuring a Type-Aware Selector (TAS) to select essential nodes and a Readout Aggregator (RA) to fuse critical information into a graph-level representation. Finally, a cross-layer fusion function is applied to combine the output embeddings from each graph pooling layer, creating a final graph representation for downstream classification tasks. Our approach achieves near state-of-the-art performance on widely used graph classification benchmark datasets, demonstrating significant improvements in four out of five datasets. This work redefines the strategy for graph-level property classification with HGNNs and heterogeneous graph pooling to model intricate relationships, enhancing performance without requiring extensive domain-specific knowledge.

Jaeseung Heo, MoonJeong Park, Dongwoo Kim

Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce posterior label smoothing, a novel method for transductive node classification that derives soft labels from a posterior distribution conditioned on neighborhood labels. The likelihood and prior distributions are estimated from the global statistics of the graph structure, allowing our approach to adapt naturally to various graph properties. We evaluate our method on 10 benchmark datasets using eight baseline models, demonstrating consistent improvements in classification accuracy. The following analysis demonstrates that soft labels mitigate overfitting during training, leading to better generalization performance, and that pseudo-labeling effectively refines the global label statistics of the graph.

Zhixia He, Chen Zhao, Minglai Shao, Xintao Wu, Xujiang Zhao, Dong Li, Qin Tian, Linlin Yu

Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection performance by integrating both visual and textual modalities. In this context, negative prompts are introduced to emphasize the dissimilarity between image features and prompt content. However, these prompts often include a broad range of non-ID features, which may result in suboptimal outcomes due to the capture of overlapping or misleading information. To address this issue, we propose Positive and Negative Prompt Supervision, which encourages negative prompts to capture inter-class features and transfers this semantic knowledge to the visual modality to enhance OOD detection performance. Our method begins with class-specific positive and negative prompts initialized by large language models (LLMs). These prompts are subsequently optimized, with positive prompts focusing on features within each class, while negative prompts highlight features around category boundaries. Additionally, a graph-based architecture is employed to aggregate semantic-aware supervision from the optimized prompt representations and propagate it to the visual branch, thereby enhancing the performance of the energy-based OOD detector. Extensive experiments on two benchmarks, CIFAR-100 and ImageNet-1K, across eight OOD datasets and five different LLMs, demonstrate that our method outperforms state-of-the-art baselines.

Shenghong He, Chao Yu, Qian Lin, Yile Liang, Donghui Li, Xuetao Ding

As a data-driven learning approach, model-based offline reinforcement learning (MORL) aims to learn a policy by exploiting a dynamics model derived from an existing dataset. Applying conservative quantification to the dynamics model, most existing works on MORL generate trajectories that approximate the real data distribution to facilitate policy learning. However, these methods typically overlook the influence of historical information on environmental dynamics, thus generating unreliable trajectories that fail to align with the true data distribution. In this paper, we propose a new MORL algorithm called Reliability-guaranteed and Reward-seeking Transformer (RT). RT can avoid generating unreliable trajectories through the calculation of cumulative reliability of the trajectories, which is a weighted variational distance between the generated trajectory distribution and the true data distribution. Moreover, by sampling candidate actions with high rewards, RT can efficiently generate high-reward trajectories from the existing offline data, thereby further facilitating policy learning. We theoretically prove the performance guarantees of RT in policy learning, and empirically demonstrate its effectiveness against state-of-the-art model-based methods on several offline benchmark tasks and a large-scale industrial dataset from an on-demand food delivery platform.

Bo Han, Zhuoming Li, Xiaoyu Wang, Yaxin Hou, Hui Liu, Junhui Hou, Yuheng Jia

Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model’s performance. While pseudo-labeling has become a dominant strategy in SSMLL, most existing methods assign equal weights to all pseudo-labels regardless of their quality, which can amplify the impact of noisy or uncertain predictions and degrade the overall performance. In this paper, we theoretically verify that the optimal weight for a pseudo-label should reflect its correctness likelihood. Empirically, we observe that on the same dataset, the correctness likelihood distribution of unlabeled data remains stable, even as the number of labeled training samples varies. Building on this insight, we propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights. We further introduce a dual-thresholding mechanism to separate confident and ambiguous regions: confident samples are pseudo-labeled and weighted accordingly, while ambiguous ones are explored by unsupervised contrastive learning. Experiments conducted on multiple benchmark datasets verify that our method achieves consistent improvements, surpassing state-of-the-art methods by up to 4.27%.