AAAI 2026 论文列表

Multi-view clustering aims to uncover shared semantics and complementary information across different views. However, the inherent heterogeneity among views poses significant challenges to effective collaborative modeling and information integration. While recent studies have introduced distillation-based mechanisms to enhance cross-view consistency and alleviate heterogeneity, these approaches often rely on manually defined knowledge transfer paths or fixed fusion weights, which are inflexible in handling complex and dynamic view relationships in practice. To address this issue, we propose HOARD: a novel framework for Hierarchical crOss-view Alignment for multi-view clusteRing via Decoupled information distillation. HOARD structurally decouples multi-view representations into shared and specific components, and performs hierarchical alignment. Specifically, we introduce a granular-ball contrastive alignment to enhance the semantic consistency of shared features, and a prototype collaborative transmission alignment strategy to align specific features while preserving view-specific structural characteristics. Moreover, we design an information distillation unit to adaptively model cross-view knowledge transfer in both feature spaces. An attention mechanism is further employed to integrate shared and specific information. Extensive experiments on benchmark datasets demonstrate that HOARD significantly improves alignment quality and clustering performance, achieving state-of-the-art results.

The neural-enhanced video streaming (NeVS) has been an emerging technique to integrate neural models into video codecs for higher streaming efficiency. The state-of-the-art methods, e.g., DeNC and Gemino, typically compress videos in RGB space and restore video quality via a neural enhancement model hosted on the external media server. However, these methods are not always accessible in resource-constrained edge environments due to their heavy reliance on the media server's computation, which undermines end-to-end performance and restricts NeVS's usage boundary. This limitation raises an interesting question: is it possible to make NeVS lightweight so that all neural codec operations can be handled directly by clients' edge devices? In this paper, we present the answer yes and develop a new plug-and-play module called DeNC++, which significantly improves the compression-restoration-overhead trade-off over existing methods. Our core design philosophy is to wrap all the codec operations within a latent semantic space, in which the original high-dimensional visual signals are efficiently embedded into low-dimensional semantic representations. With this fundamental transformation, DeNC++'s neural encoder introduces the triple semantic-bitwidth-resolution compression to effectively lower the streaming traffic. Meanwhile, we make DeNC++'s neural decoder aware of the perceptual loss caused by its encoder and design tiny generative models to guarantee high restoration quality. We also strictly restrict the runtime computational overhead and accelerate the neural enhancement process, making DeNC++ compatible with commodity edge devices. Real-world evaluations reveal that DeNC++ consistently provides higher restoration quality while achieving 24-55 times higher compression ratio and 5-7 times end-to-end speedup over the latest NeVS solutions.

Multimodal large language models (MLLMs), which integrate language and visual cues for problem-solving, are crucial for advancing artificial general intelligence (AGI). However, current benchmarks for measuring the intelligence of MLLMs suffer from limited scale, narrow coverage, and unstructured knowledge, offering only static and undifferentiated evaluations. To bridge this gap, we introduce MDK12-Bench, a large-scale multidisciplinary benchmark built from real-world K–12 exams spanning six disciplines with 141K instances and 6,225 knowledge points organized in a six-layer taxonomy. Covering five question formats with difficulty and year annotations, it enables comprehensive evaluation to capture the extent to which MLLMs perform over four dimensions: 1) difficulty levels, 2) temporal (cross-year) shifts, 3) contextual shifts, and 4) knowledge-driven reasoning. We propose a novel dynamic evaluation framework that introduces unfamiliar visual, textual, and question form shifts to challenge model generalization while improving benchmark objectivity and longevity by mitigating data contamination. We further evaluate knowledge-point reference-augmented generation (KP-RAG) to examine the role of knowledge in reasoning. Key findings reveal limitations in current MLLMs in multiple aspects and provide guidance for enhancing model reasoning, robustness, and AI-assisted education.

Text-attributed heterogeneous graphs (TAHGs), characterized by nodes interconnected through diverse relationships and enriched with textual descriptions, are prevalent in numerous real-world applications. Recent advancements in integrating pre-trained language models (PLMs) and large language models (LLMs) with heterogeneous graph neural networks (HGNNs) have enhanced learning on TAHGs. However, the absence of standardized benchmark datasets tailored to TAHGs has impeded further progress. To bridge this gap, we propose the Text-attributed Heterogeneous Graphs Benchmark (THGB), a comprehensive collection of heterogeneous graphs from diverse domains, with each node enriched by relevant text attributes. Alongside dataset construction, we conduct extensive benchmark experiments using various graph learning methods, including GNN, PLM-GNN, and LLM-GNN approaches, for node classification and link prediction tasks. We evaluated model performance across supervised, few-shot, and zero-shot learning scenarios to assess their ability to leverage limited and unseen data. Our experiments highlight THGB's potential to improve the integration of heterogeneous structural and textual information. By providing curated datasets, robust evaluation protocols, and baseline implementations, THGB introduces a standardized benchmark and solid groundwork for TAHGs research.

We introduce a novel framework for privacy-preserving multi-party neural network training over ℤ_(2^k) with semi-honest security in the honest-majority setting. Our work utilizes Shamir secret sharing scheme over Galois rings GR(2^k, d) and is scalable in the number of participants. Our primary contribution is a generalization of existing data packing techniques used in private training through Reverse Multiplication-Friendly Embedding (RMFE), which enables a higher packing density and thus more efficient SIMD-style parallel computation. Notably, our work is the first to support a general form of RMFE, lifting a common restriction from previous approaches. To holistically optimize the training process, we further integrate mixed-circuit techniques to be fully compatible with our RMFE-based packing scheme. This enables our protocol to efficiently compute nonlinear functions, such as comparison, by leveraging bit-wise computations over GR(2, d). We consolidate these advances into an end-to-end parallel training framework. Experimental results on both fully connected and convolutional neural networks validate the practical performance advantages of our framework compared to existing methods.

While large vision-language models (VLMs) demonstrate impressive long-context understanding, their prevalent small branches fails on linguistics-photography alignment for limited window size. We discover that knowledge distillation improve students capability as compelementary to Rotary Position Embeddings (RoPE) on certain windows size (anchored from large models). Building on this insight, we propose LAid, which explicitly targets the transfer of long-range attention mechanisms through two complementary components: (1) a progressive distance-weighted attention matching that dynamically emphasizes longer position differences during training, and (2) a learnable RoPE response gain modulation that selectively amplifies position sensitivity where needed. Extensive experiments across multiple model families demonstrate that LAid-distilled models achieve up to 3.2× longer effective context windows compared to baseline small models, while maintaining or improving performance on standard VL benchmarks. Spectral analysis also suggests that LAid successfully preserves crucial low-frequency attention components that conventional methods fail to transfer. Our work not only provides practical techniques for building more efficient long-context VLMs but also offers theoretical insights into how positional understanding emerges and transfers during distillation.

Traffic prediction plays an important role in urban management. However, existing methods rely on centralized traffic data, which may raise privacy concerns. Federated traffic prediction offers a promising solution for clients (e.g., traffic management administrations) in different regions to collaboratively train models in a distributed manner without exposing private data. Nonetheless, data isolation inherently breaks the correlations between nodes (i.e., traffic sensors collecting data) from different regions, which leads to the missing inter-client dependency. Consequently, current works either fail to capture the missing inter-client dependency or compromise data privacy to recover the inter-client dependency. To address this issue, we propose a novel Federated method which recovers the inter-client dependency with HIdden global componeNTs (FedHINT). We find that the traffic data from different local regions actually contain hidden global components that reflect cross-regional traffic changes. Therefore, our FedHINT aims to extract hidden global components from each client to generate proxy nodes that represent global information, which are then utilized to recover the inter-client dependency. To be specific, we employ an attention module, which is guided by the shared global queries to capture hidden global components from local traffic data, to generate proxy nodes. Subsequently, our FedHINT adaptively learns the correlations between proxy nodes and local nodes through a global encoder. During this process, the global information in proxy nodes compensate for the loss of information from cross-regional nodes, which thereby recovers the missing inter-client dependency. Intensive experiments on multiple datasets demonstrate that our FedHINT significantly outperforms the state-of-the-art methods, with an average decrease of 3.73 and 4.81 on MAE and RMSE, respectively.

Online continual learning requires models to learn from non‑stationary data streams while retaining prior knowledge. We identify an overlooked phenomenon—knowledge fragility—where correctly learned instances are rapidly forgotten after minor parameter updates. Our analysis attributes this fragility to a temporal–spatial dual mechanism: temporal instability, high-frequency parameter oscillations cause forgetting to outpace adaptation; and spatial vulnerability, fragile instances lie in sharp, high‑curvature regions of the loss landscape that are extremely sensitive to optimization noise. These insights motivate PDFK (Perturbing to Defend Fragile Knowledge), a unified framework that defends fragile knowledge along both dimensions. Temporally, we apply exponential moving averaging to smooth parameter evolution and stabilize long‑term memory. Spatially, we inject minimal structured perturbations with a consistency constraint to flatten sharp regions and enhance robustness. PDFK requires no task‑boundary annotations. Extensive experiments demonstrate that PDFK substantially improves knowledge retention and outperforms strong baselines under diverse and challenging continual learning settings.

Neural operators have shown great potential in solving a family of Partial Differential Equations (PDEs) by modeling the mappings between input and output functions. Fourier Neural Operator (FNO) implements global convolutions via parameterizing the integral operators in Fourier space. However, it often results in over-smoothing solutions and fails to capture local details and high-frequency components. To address these limitations, we investigate incorporating the spatial-frequency localization property of Wavelet transforms into the Transformer architecture. We propose a novel Wavelet Attention (WA) module with linear computational complexity to efficiently learn locality-aware features. Building upon WA, we further develop the Spectral Attention Operator Transformer (SAOT), a hybrid spectral Transformer framework that integrates WA’s localized focus with the global receptive field of Fourier-based Attention (FA) through a gated fusion block. Experimental results demonstrate that WA significantly mitigates the limitations of FA and outperforms existing Wavelet-based neural operators by a large margin. By integrating the locality-aware and global spectral representations, SAOT achieves state-of-the-art performance on six operator learning benchmarks and exhibits strong discretization-invariant ability.

Bimanual dexterous manipulation is a critical yet underexplored area in robotics. Its high-dimensional action space and inherent task complexity present significant challenges for policy learning, and the limited task diversity in existing benchmarks hinders general-purpose skill development. Existing approaches largely depend on reinforcement learning, often constrained by intricately designed reward functions tailored to a narrow set of tasks. In this work, we present a novel approach for efficiently learning diverse bimanual dexterous skills from abundant human demonstrations. Specifically, we introduce BiDexHD, a framework that unifies task construction from existing bimanual datasets and employs teacher-student policy learning to address all tasks. The teacher learns state-based policies using a general two-stage reward function across tasks with shared behaviors, while the student distills the learned multi-task policies into a vision-based policy. With BiDexHD, scalable learning of numerous bimanual dexterous skills from auto-constructed tasks becomes feasible, offering promising advances toward universal bimanual dexterous manipulation. Experiments on TACO tool-using dataset spanning 141 tasks across 6 categories demonstrate a task fulfillment rate of 74.59% on trained tasks and 51.07% on unseen tasks. We further transfer BiDexHD to 11 ARCTIC collaborative tasks and achieve an average of 80.49% task fulfillment rate on trained tasks and 65.99% on unseen task. All empirical results demonstrate the effectiveness and competitive zero-shot generalization capabilities of BiDexHD.

Many optimization tasks involve streaming data with unknown concept drifts, posing a significant challenge as Streaming Data-Driven Optimization (SDDO). Existing methods, while leveraging surrogate model approximation and historical knowledge transfer, are often under restrictive assumptions such as fixed drift intervals and fully environmental observability, limiting their adaptability to diverse dynamic environments. We propose TRACE, a TRAnsferable Concept-drift Estimator that effectively detects distributional changes in streaming data with varying time scales. TRACE leverages a principled tokenization strategy to extract statistical features from data streams and models drift patterns using attention-based sequence learning, enabling accurate detection on unseen datasets and highlighting the transferability of learned drift patterns. Further, we showcase TRACE's plug-and-play nature by integrating it into a streaming optimizer, facilitating adaptive optimization under unknown drifts. Comprehensive experimental results on diverse benchmarks demonstrate the superior generalization, robustness, and effectiveness of our approach in SDDO scenarios.

The application of vision-language models in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised fine-tuning on existing datasets often leads to poor generalization on unseen modalities and tasks, while reinforcement learning, a promising alternative, is stymied by the lack of reliable reward signals in this data-scarce domain. To address this challenge, we propose a Generative Reward Learning framework that establishes a self-improving training cycle. The framework jointly develops a data generator and a reward model, enabling the automated and continuous creation of high-quality multimodal medical data that serves as an effective training source for post-training. Our experiments demonstrate that supervised fine-tuning using the generated data already surpasses models trained on large-scale human-curated datasets. More importantly, when the generated data is further leveraged for reinforcement learning via Group Relative Policy Optimization, the resulting model achieves state-of-the-art cross-modality and cross-task generalization, significantly outperforming specialized reinforcement-learning-based methods. Notably, a compact model trained under this framework attains performance competitive with foundation models containing more than an order of magnitude more parameters. These results suggest a new paradigm for data-efficient learning in high-stakes medical domains, shifting the bottleneck from data scarcity to data generation and unlocking the potential of reinforcement learning for building robust and generalizable medical AI systems.

The sim-to-real gap, where agents trained in a simulator face significant performance degradation during testing, is a fundamental challenge in reinforcement learning. Extensive works adopt the framework of distributionally robust RL, to learn a policy that acts robustly under worst case environment shift. Within this framework, our objective is to devise algorithms that are sample efficient with interactive data collection and large state spaces. By assuming d-rectangularity of environment dynamic shift, we identify a fundamental hardness result for learning in online Markov game, and address it by adopting minimum value assumption. Then, a novel least square value iteration type algorithm, DR-CCE-LSI, with exploration bonus devised specifically for multiple agents, is proposed to find an epsilon-approximate robust Coarse Correlated Equilibrium(CCE). To obtain sample efficient learning, we find that: when the feature mapping function satisfies certain properties, our algorithm, DR-CCE-LSI, is able to achieve epsilon-approximate CCE with a regret bound of O(dH min(H, 1/ min(sigma_i)) sqrt(K)), where K is the number of interacting episodes, H is the horizon length, d is the feature dimension, and sigma_i represents the uncertainty level of player i. Our work introduces the first sample-efficient algorithm for this setting, matches the best result so far in single agent setting, and achieves minimax optimal sample complexity in terms of the feature dimension d. Meanwhile, we also conduct simulation study to validate the efficacy of our algorithm in learning a robust equilibrium.

Post-training quantization (PTQ) offers an efficient approach to compressing large language models (LLMs), significantly reducing memory access and computational costs. Existing compensation-based weight calibration methods often rely on a second-order Taylor expansion to model quantization error, under the assumption that the first-order term is negligible in well-trained full-precision models. However, we reveal that the progressive compensation process introduces accumulated first-order deviations between latent weights and their full-precision counterparts, making this assumption fundamentally flawed. To address this, we propose FOEM, a novel PTQ method that explicitly incorporates first-order gradient terms to improve quantization error compensation. FOEM approximates gradients by performing a first-order Taylor expansion around the pre-quantization weights. This yields an approximation based on the difference between latent and full-precision weights as well as the Hessian matrix. When substituted into the theoretical solution, the formulation eliminates the need to explicitly compute the Hessian, thereby avoiding the high computational cost and limited generalization of backpropagation-based gradient methods. This design introduces only minimal additional computational overhead. Extensive experiments across a wide range of models and benchmarks demonstrate that FOEM consistently outperforms the classical GPTQ method. In 3-bit weight-only quantization, FOEM reduces the perplexity of Llama3-8B by 17.3% and increases the 5-shot MMLU accuracy from 53.8% achieved by GPTAQ to 56.1%. Moreover, FOEM can be seamlessly combined with advanced techniques such as SpinQuant, delivering additional gains under the challenging W4A4KV4 setting and further narrowing the performance gap with full-precision baselines, surpassing existing state-of-the-art methods.

Accurate muscle-mass assessment is crucial for staging and managing sarcopenia, yet existing methods suffer from modality-specific limitations and weak integration of muscle function indicators. To solve these limitations, we propose a Dual-source Features Graph for Sarcopenia Evaluation (DFGSE) to synergize high- and low-energy whole-body Dual-energy X-ray Absorptiometry (DXA) images, local high-energy DXA images, and blood-borne biochemical markers. Specifically, the feature extraction module employs dual-energy feature extraction to disentangle soft-tissue and skeletal cues from low-energy images, while skeleton-aware detection extracts joint features from high-energy images. It yields global and local DXA embeddings, complemented by blood-test representations. In the relevance exploration module, inter- and intra-modality correlations are computed via bilinear transformations to form adjacency matrices for the global, local, and blood modality representations. These matrices seed the Multi-type Multi-relation Graph Convolutional Network (MMGCN) – the core of the relation learning module – which captures both direct and indirect interactions among modalities through relation-aware message passing. Finally, the graph-fused representations are used by a muscle-mass prediction head trained with cross-entropy loss. Experiments on the public MURA dataset and two independent sarcopenia cohorts demonstrate that DFGSE consistently outperforms machine learning and state-of-the-art graph-based methods, in terms of four evaluation metrics for classification task.

Diffusion models have demonstrated remarkable success in image generation, yet a persistent challenge remains: the bias between model predictions and the target distribution. In this paper, we propose a Bidirectional Noise Injection framework for enhancing diffusion models, implemented via Coordinated Input-Output Perturbation (CIOP). Our approach mitigates this bias by randomly applying synchronized noise injection to both the model inputs and the prediction targets during the training stage. This stochastic, synchronized noise injected acts as a smoothing mechanism that effectively reduces the 2-Wasserstein distance between the predicted and target distributions, as substantiated by our theoretical analysis based on optimal transport theory. Extensive experiments on multiple benchmark datasets and various generative tasks demonstrate that our method improves generation quality and training efficiency without incurring additional computational cost. Furthermore, the design of CIOP enables seamless integration with existing diffusion model improvements and advanced frameworks, thereby broadening its applicability. These results highlight the potential of Bidirectional Noise Injection via CIOP to alleviate bias in diffusion-based generative models across a wide range of settings.

Multimodal Large Language Models (MLLMs) have demonstrated impressive progress in single-image grounding and general multi-image understanding. Recently, some methods begin to address multi-image grounding. However, they are constrained by single-target localization and limited types of practical tasks, due to the lack of unified modeling for generalized grounding tasks. Therefore, we propose GeM-VG, an MLLM capable of Generalized Multi-image Visual Grounding. To support this, we systematically categorize and organize existing multi-image grounding tasks according to cognitive demands and introduce the MG-Data-240K dataset, addressing the limitations of existing datasets regarding target quantity and image relation. To tackle the challenges of robustly handling diverse multi-image grounding tasks, we further propose a hybrid reinforcement finetuning strategy that integrates chain-of-thought (CoT) reasoning and direct answering, considering their complementary strengths. This strategy adopts an R1-like algorithm guided by a carefully designed rule-based reward, effectively enhancing the model’s overall perception and reasoning capabilities. Extensive experiments demonstrate the superior generalized grounding capabilities of our model. For multi-image grounding, it outperforms the previous leading MLLMs by 2.0% and 9.7% on MIG-Bench and MC-Bench, respectively. In single-image grounding, it achieves a 9.1% improvement over the base model on ODINW. Furthermore, our model retains strong capabilities in general multi-image understanding.

Three-dimensional atomic arrangements of biomolecules are key to demystifying biological functions. The rapid expansion of accessible structural data, driven by advances in AI for science, highlights the critical challenge of efficiently modeling large-scale biomolecular structures, which are high-dimensional systems shaped by biological assembly principles. To address this, we introduce BiHiTo, a multi-level Biomolecular Hierarchy-inspired Tokenizer that intrinsically mimics natural biological assembly hierarchies. Specifically, we design a multi-codebook quantizer that mirrors the natural hierarchy of biomolecular structure, enabling simultaneous capture of representations spanning atomic motifs to global conformational variations. This hierarchical alignment markedly improves the biological interpretability and reconstruction fidelity of biomolecular structure.Extensive experiments demonstrate that BiHiTo delivers state-of-the-art performance and robust generalization across molecular dynamics trajectories and macromolecular complexes, facilitating advances in structure generation and dynamic conformation exploration. In the reconstruction of the CASP14 and OOD test set FastFolding protein multi-conformation data, our method achieves a 17% and 51% reduction in RMSD compared to Bio2Token, respectively.

Cross-Domain Decentralized Graph Learning (CD-DGL) is a promising paradigm that enables efficient, privacy-preserving collaboration among multiple parties to unlock the value of cross-domain graph data. However, it faces two fundamental challenges. First, inconsistent label spaces across domains drive local models to learn domain-specific biases, which means domain-invariant topological knowledge extraction beyond label constraints is difficult. Second, existing domain topology shift and heterogeneous model architectures make direct model aggregation infeasible. To address these issues, we first use Extended Persistent Homology (EPH) to reveal and quantify the problem of domain topology shift induced by the cross-domain setting. Building on this insight, we present Decentralized Graph Learning with Topology-Aware Knowledge Fusion (DGTF), a novel framework designed to facilitate positive topological knowledge transfer in CD-DGL. Our framework achieves this by integrating two core strategies: first, a contrastive learning-based approach to extract task-agnostic topological knowledge, and second, a topology-aware, model-independent knowledge fusion method to effectively integrate this topological information. Extensive experiments conducted under various cross-domain and model-heterogeneous settings validate the superiority and effectiveness of our proposed framework.