Multi-modal point cloud completion aims to recover complete 3D geometric structures from partial observations by integrating auxiliary data. Although image-guided techniques are well-established, the potential of natural language as a source of high-level semantic cues remains under-explored. Therefore, effectively introducing natural language and synergizing it with the image modality to assist 3D structure recovery is key to breaking current performance bottlenecks. To address this, we propose Query-Aware Gating Gramian Alignment (QGGA), a framework for multi-modal completion. QGGA employs a novel query-dependent bidirectional attention mechanism to dynamically filter information flows between modalities and adaptively regulate fusion intensity. To facilitate alignment among the three heterogeneous modalities, we utilize the volume of the parallelotope spanned by multi-modal local features as a consistency metric, constraining geometric alignment by minimizing this volume. Finally, the fused and aligned features are fed into a coarse-to-fine decoder to first predict a coarse point cloud and then progressively recover the complete shape through stepwise upsampling and refinement. Furthermore, we construct ShapeNet-ViPC-Desc, a benchmark dataset enriched with detailed text descriptions. Experimental results demonstrate that QGGA achieves new state-of-the-art (SOTA) performance on this benchmark. The source code is freely accessible at https://github.com/whysq/QGGA.
论文检索
输入标题、作者或关键词，从 990 篇学术成果中精准定位
Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations. However, owing to the reliance on frequency truncation to maintain learning efficiency of FNOs, empirical studies suggest that FNOs exhibit spectral bias toward low-frequency information, which may hinder the learning capability especially for certain PDEs with strong high-frequency oscillations. To address this limitation, we propose SirenFNO, a novel framework that leverages sinusoidal representation networks (SIRENs) to learn implicit neural representations and performs mode-wise kernel parameterization. Our SIREN parameterization learns a full-grid spectrum with a constant and discretization-independent parameter count, thereby eliminating the need for frequency truncation. We further extend SirenFNO with functional tensor decompositions to enhance parameter and learning efficiency. Empirical results show that our SirenFNO consistently outperforms FNO with approximately 4 to 15 times parameter reductions with preserved discretization invariance, and our functional decomposition variants obtain performance improvements with a maximum of 73 times fewer parameters across multiple PDE benchmarks.
Multi-view learning aims to enhance performance by integrating information from multiple sources. While different views offer complementary perspectives, extracting consistent and discriminative representations remains a significant challenge due to discrepancies in representation and presence of noise. Existing methods typically separate the denoising and alignment processes, mapping the denoised heterogeneous views to a shared subspace for alignment. This means that noise may propagate or even amplify during the alignment stage, ultimately leading to suboptimal solutions. To address this issue, we propose center-guided spectral diffusion, which replaces traditional alignment with generative modeling. This method avoids noise propagation in multi-view alignment process and prevents multi-view features be aligned to the noise subspace during fusion process. Specifically, we first performs unconditional diffusion in both the feature space and a low-rank spectral space to learn a stable consensus centre anchor. This anchor is then used to condition a guided generative diffusion process, enabling the model to generate more consistent and realistic sample representations. By combining conditional and unconditional diffusion, the proposed method alleviates the noise amplification problem commonly found in traditional alignment methods. Experimental results show that the proposed method outperforms state-of-the-art methods on several datasets.
Graph Neural Networks (GNNs) are widely used in high-stakes decision-making, where explanation robustness is crucial. Yet, even minor structural perturbations can drastically change explanations without changing predictions. Existing methods primarily characterize structural perturbations by their edit distance or budget, and enforce robustness through uniform constraints or averaging mechanisms over this perturbation set, which fail to capture the inherently direction-dependent effects of structural changes. In this paper, we propose GeoXGNN (Local Geometry Improves Explanation Robustness for Graph Neural Networks), a robust explanation framework that explicitly models the directional sensitivity of structural perturbations from a geometric perspective. GeoXGNN introduces local, direction-aware metrics in the node representation space to characterize how perturbations along different directions affect node embeddings and explanation outcomes. Based on the learned local metrics, GeoXGNN further enforces directional constraints, encouraging explanations to remain robust along high-sensitivity directions while preserving explanatory fidelity. Extensive experiments on multiple node-level and graph-level benchmark datasets demonstrate that GeoXGNN significantly improves explanation robustness over existing methods.
Temporal Knowledge Graph Reasoning (TKGR) aims at inferring missing (especially future) events from historical data. Current evaluation in TKGR uniformly weights all events, ignoring that most are trivial repetitions, which overestimate the true reasoning ability. Therefore, the rare outstanding events, whose prediction demands deeper reasoning, should be distinguished and emphasized. To this end, we propose a strikingness-aware evaluation framework, which introduces a rule-based strikingness measuring framework (RSMF) to quantify event strikingness by comparing its expected occurrence with peer events derived from temporal rules. Strikingness is then integrated as a weighting factor into metrics like weighted MRR and Hits@k. Experiments on four TKG benchmarks reveal: 1) All representative models perform worse as event strikingness increases, 2) Path-based methods excel on low-strikingness events and representation-based ones on high-strikingness events, 3) We design an ensemble method whose gains stem from fitting trivial events rather than reasoning improvement. Our framework provides a more rigorous evaluation, refocusing the field on predicting outstanding events.
Existing multi-modal automatic modulation recognition (AMR) methods primarily focus on exploiting multi-view representations of raw signal data to improve performance, but still struggle to effectively model and exploit high-level human prior knowledge. Although recent studies attempt to introduce large language models (LLMs) to integrate the textual modality, most of them merely treat LLMs as feature extractors, without further exploiting the LLM's potential. To this end, we propose a knowledge-enhanced multi-modal automatic modulation recognition framework based on large language model (AMR-LLM). Specifically, we first specially design an AMR instruction construction mechanism based on knowledge to activate the LLM's potential for signal perception, which designates the LLM as a signal domain expert, introduces human prior knowledge as a supplement, and exploits the unique physical information of each data sample as connection guidance. Then, to enable the LLM to directly perceive digital signals, we introduce a progressive multi-modal fusion strategy mapping signal features into the space of LLMs. Experimental results on multiple benchmark datasets demonstrate that AMR-LLM achieves approximately 5% higher accuracy than current state-of-the-art methods. Moreover, it achieves the current domain performance with only 30% of the data.
As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and code debugging. However, existing local model-agnostic explanation methods face a critical dilemma in these scenarios: feature-based methods suffer from attribution dilution due to high feature dimensionality, which prevents them from providing faithful explanations. In this paper, we propose Focus-LIME, a coarse-to-fine framework designed to restore the tractability of surgical interpretation. Focus-LIME utilizes a proxy model to curate the perturbation neighborhood, allowing the target model to perform fine-grained attribution exclusively within the optimized context. Empirical evaluations on long-context benchmarks demonstrate that our method makes surgical explanations practical and provides faithful explanations to users.
Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is particularly acute in highly homogeneous scenarios that require fine-grained discrimination over complex compositional semantics. However, under sparse supervision, models overfit to salient yet insufficient cues, leading to shortcut learning and degraded compositional discrimination. To resolve this, we propose COAL (Counterfactual and Observation-enhanced Alignment Learning), a framework that advances RMOT beyond isolated structural optimization through knowledge regularization. First, we introduce Explicit Semantic Injection (ESI) via a VLM to densify the observation space and enhance instance discriminability. Second, leveraging LLM reasoning, we propose Counterfactual Learning (CFL) to augment supervision, enforcing strict attribute verification for robust compositional recognition. These strategies are unified within a Hierarchical Multi-Stream Integration (HMSI) architecture, which distills external knowledge into domain-specific discriminative representations. Experiments on Refer-KITTI and Refer-KITTI-V2 benchmarks validate COAL's efficacy. Notably, it surpasses the state-of-the-art by 7.28% HOTA on the highly challenging Refer-KITTI-V2. These results demonstrate the effectiveness of knowledge regularization for resolving the sparsity–discriminability paradox in RMOT.
Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer. An extended version with full appendices is available at https://arxiv.org/abs/2605.04916.
Online EEG decoding is pivotal for real-world Brain-Computer Interfaces (BCIs) but confronts significant challenges arising from continuous distribution shifts, including both inter- and intra-subject variations. Existing Unsupervised Continual Domain Adaptation (UCDA) methods typically rely on rigid hard boundaries such as subject switch labels or fixed batch sizes to trigger adaptation. Meanwhile, some online EEG decoding methods that utilize detected shifts as soft boundaries are ill-suited for unsupervised scenarios and lack effective distribution alignment strategies. To address these issues, we propose a novel Prototype-driven online EEG Decoding framework (PRED). PRED incorporates a Subject Shift Detector (SSD) based on policy stability to reliably identify latent domain shifts unsupervisedly, thereby constructing adaptive soft boundaries. Furthermore, we design a Prototype-guided Shift Correction (PSC) mechanism that leverages a multi-granular memory structure to guide distribution alignment while preserving semantic stability. Experiments on three public datasets confirm that PRED achieves superior plasticity and stability, and demonstrates significant futurity, i.e., the capability of forward transfer to a subject's future samples.
Adversarial training is effective on balanced datasets, but its robustness degrades under long-tailed class distributions, where tail classes suffer high robust error and unstable decision boundaries. We propose \emph{Manifold-Constrained Adversarial Training (MCAT)}, a unified framework that enforces the semantic validity of adversarial examples by penalizing deviations from class-conditional manifolds in feature space, while promoting balanced geometric separation across classes via an ETF-inspired regularization. We provide theoretical results that link geometric separation to lower bounds on adversarially robust margins, and show that manifold-constrained adversarial risk upper-bounds robust risk on high-density semantic regions. Extensive experiments on standard long-tailed benchmarks demonstrate consistent improvements in overall, balanced, and tail-class adversarial robustness. The codes and appendix are available on https://github.com/yneversky/MCAT.
The primary challenge in incremental learning for deep neural networks (DNNs) lies in balancing memory stability with learning plasticity as they incrementally acquire new knowledge. Existing incremental learning methods typically require storing portions of old datasets or relying on specialized network architectures to achieve learning without forgetting. Recent neuroscience findings reveal that hippocampal sharp-wave ripples play critical roles in consolidating neocortex memory by internally triggering the reactivation of spontaneous neural circuits without external stimulus. Inspired by this biological mechanism, we propose an incremental learning method termed Sharp-Wave Ripples Learning (SWRL), a novel incremental learning framework composed of two functionally complementary modules: a neocortex-like network for long-term memory and a hippocampus-like model for rapid new-knowledge encoding. SWRL continuously integrates newly acquired knowledge from the hippocampus-like module into the neocortex-like network via a meta-weighted memory integration mechanism guided by internally generated SWR-like signals. Our framework is task-agnostic, architecture-agnostic, and exemplar-free. Experimental results on multiple public benchmarks demonstrate that SWRL achieves superior incremental learning performance under various scenarios across diverse DNN architectures, requiring no access to previous data or modifications to the base architecture. The code and appendix are both released at https://github.com/SYVAE/SWRL.
Continual unsupervised domain adaptation (UDA) for multi-domain cardiac image segmentation is crucial for clinical deployment under strict privacy constraints, where data from different centers cannot be stored or revisited. However, existing methods still suffer from catastrophic forgetting and training instability caused by noisy pseudo-labels and representation drift. In this study, we propose a novel continual UDA framework that enforces dual-level alignment at the input and feature levels. At the input level, the Domain-Style Adapting Generative Replay (DSA-GR) module employs trajectory-consistent diffusion distillation and style adaptation to synthesize high-fidelity, domain-consistent replay images without storing raw data. At the feature level, the Cross-domain Prototype-guided Feature Consolidation (CPFC) mechanism mitigates representation drift by maintaining a cross-domain prototype memory bank that aggregates features from the current and replay streams. These prototypes act as robust anchors for prototype-guided contrastive learning, rectifying the feature space and suppressing pseudo-label drift. Extensive experiments on two public datasets demonstrate that our framework consistently outperforms state-of-the-art methods. Code will be released at https://github.com/hlyf-xs/CUDA_Seg.
Generating high-quality synthetic tabular data, regarding fidelity, diversity, and utility, is crucial for many practical purposes. Recent tabular data synthesis methods, including two-stage generative modeling approaches, have achieved this with nearly perfect fidelity. However, we observe that there remains room for improving diversity, and we show that this limitation arises from an additional constraint imposed on the latent support. Our main contribution is that we effectively eliminate this redundant constraint by directly deriving the objective function from the KL-divergence between the ground-truth density and the generative model used for synthetic sample generation. We empirically demonstrate that our model, which relies on a single prior distribution, significantly improves the quality of the synthetic data, especially in terms of diversity. Our implementation code is available at https://anonymous.4open.science/r/SPT-1EE2/.
Learning from label-limited streams presents significant challenges, particularly when coupled with concept drift and dynamic class imbalance. Existing works often struggle to maintain a discriminative feature space under these constraints, biasing decision boundaries toward majority classes or outdated concepts. To address this, we propose a novel framework named Neural collapse Inspired Label-limited Evolving stream learning (NILE). Instead of utilizing learnable classifiers, NILE exploits Neural Collapse (NC) geometry to explicitly construct a Simplex Equiangular Tight Frame (ETF) as a fixed classifier, ensuring maximal inter-class separability to guide feature discriminability. To maintain this discrimination with limited labels, NILE employs hybrid active learning to prioritize uncertain and minority samples, and an NC-adapted semi-supervised mechanism to enhance representation learning. NILE further updates the classifier by dynamically adjusting the ETF structure, enabling continual adaptation to drifting concepts. Extensive experiments show that NILE can effectively guide features toward the NC state, significantly outperforming state-of-the-art baselines in nonstationary environments.
Generative models continue to advance rapidly in both fidelity and diversity, posing increasing challenges for reliably distinguishing generated images from real ones. Existing reconstruction-based detection methods often rely on assumptions tied to specific generative models, which leads to limited cross-model generalization and substantial computational overhead. In this paper, we propose General Feature Reconstruction Error (GFRE), a fast and generalizable detection paradigm that leverages reconstruction behavior in a general-purpose representation space. Our key insight is that real and generated images exhibit consistently different reconstruction stability when projected into universal visual representations. Instead of tracing generator-specific artifacts, GFRE employs a lightweight autoencoder to model the reconstructability of image representations, producing a reconstruction signal that is inherently generator-agnostic and transferable across diverse generative processes. Extensive experiments on images synthesized by 18 different generative models demonstrate that GFRE consistently outperforms existing state-of-the-art methods, achieving a 4.70% improvement in detection accuracy and an 8.20% gain in cross-model generalization. Moreover, by avoiding costly generator inversion and diffusion-based reconstruction, GFRE reduces reconstruction error extraction time by up to 150x, enabling efficient and scalable deployment.
Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties. Markovian Reinforcement Learning (RL) can be inadequate for such tasks, while modeling them as non-Markovian reward decision processes (NMRDPs) enables agents to handle temporal dependencies. Existing approaches offer limited formal guarantees on both (near-)optimality and sample efficiency. We address both issues with QR-max, a novel model-based algorithm for NMRDPs with discrete actions that factorizes Markovian transition learning from non-Markovian reward handling via reward machines. To our knowledge, this is the first model-based RL algorithm for discrete-action NMRDPs that leverages this factorization to obtain PAC convergence to ε-optimal policies with polynomial sample complexity. We then extend QR-max to continuous state spaces with Bucket-QR-max, a SimHash-based discretizer that preserves the same factorized structure and achieves fast and stable learning without manual gridding or function approximation. We experimentally compare our method with state-of-the-art model-based RL approaches on environments of increasing complexity, showing substantially improved sample efficiency and greater robustness in finding optimal policies.
Reinforcement learning (RL) agents often struggle to generalize to new tasks and contexts without updating their parameters, mainly because their learned representations and policies are overfit to the specifics of their training environments. To boost agents' in-context RL (ICRL) ability, this work formulates ICRL as a two-agent emergent communication problem and introduces CORAL (Communicative Representation for Adaptive RL), a framework that learns a transferable communicative context by functionally separating latent representation learning from control. In CORAL, an Information Agent (IA) is pre-trained as a world model on a diverse distribution of tasks. Its objective is not direct return maximization, but world modeling and distilling its understanding into concise messages. The emergent communication protocol is shaped by a novel Causal Influence Loss, which measures the effect that the message has on the next action. During deployment, the previously trained IA serves as a fixed contextualizer for a new Control Agent (CA), which learns to solve tasks by interpreting the provided communicative context. Our experiments demonstrate that this approach enables the CA to achieve significant gains in sample efficiency and successfully perform zero-shot adaptation with the help of pre-trained IA in diverse online and offline environments, validating the efficacy of learning a transferable communicative representation.
The huge parameters and extensive training corpora of Large Language Models (LLMs) empower them to tackle complex tasks. Yet, their massive size incurs substantial inference costs, hindering deployment on resource‑constrained edge devices. Low‑bit quantization provides a way to compress models and improve their practicality for edge-side deployment. Nonetheless, many edge applications do not require the full generalization abilities of LLMs and instead only depend on their knowledge in specific domains. This paper introduces Gradient Enhancement Task Aware Post-training Quantization, i.e., GTAQ, to address the generalization issue. Concretely, GTAQ locates task‑critical weights via gradient‑based validation and retrieval, and then amplifies these salient weights. For that purpose, GTAQ preserves and strengthens weights related to the target tasks, enabling task‑aware uniform‑bit quantization. We extensively evaluate the LLaMA family of language models on WikiText, C4, and MMLU. Our experiments show that GTAQ consistently delivers notable performance improvements across tasks, surpassing both general‑purpose and task‑aware quantization baselines. At the same time, GTAQ yields more than 3.5× speedup in model inference and substantially cuts storage requirements. https://github.com/YihuaJerry/GTAQ.git.
Open-world test-time adaptation (OWTTA) is increasingly studied for its ability to adapt models at inference time in the presence of both domain discrepancy and semantic variance. Existing methods typically rely on either discriminative models or vision-language models (VLMs) alone, leaving their complementarity in OWTTA underexplored. In this paper, we propose a general framework that explicitly leverages the complementary strengths of discriminative models and VLMs to enable robust open-world test-time adaptation. We first define well-structured logits for OWTTA and provide a theoretical analysis that reveals the complementary properties of logits from discriminative models and VLMs. Building on a unified formulation, we then decompose OWTTA into two coupled modules: confidence-calibrated filtering (CCF), which provides an estimate of in-distribution membership, and semantic complementarity adaptation (SCA), which gives the refined predictions through complementary logit fusion. Extensive experiments across multiple benchmarks empirically confirm the logit complementarity between discriminative models and VLMs, and show that our method effectively leverages it to consistently improve performance.