论文检索

Computer Vision · Everything Else

Ling Li, Changjie Chen, Yuyan Wang, Jiaqing Lyu, Kenglun Chang, Yiyun Chen, Zhidong Deng

In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach often overlooks the rich temporal dependencies between adjacent frames. We propose a novel 3D human pose estimation input method: the sparse interleaved input to address this. This method leverages images captured from different camera views at various time points (e.g., View 1 at time $t$ and View 2 at time $t+\delta$), allowing our model to capture rich spatio-temporal information and effectively boost performance. More importantly, this approach offers two key advantages: First, it can theoretically increase the output pose frame rate by N times with N cameras, thereby breaking through single-view frame rate limitations and enhancing the temporal resolution of the production. Second, using a sparse subset of available frames, our method can reduce data redundancy and simultaneously achieve better performance. We introduce the DenseWarper model, which leverages epipolar geometry for efficient spatio-temporal heatmap exchange. We conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Results demonstrate that our method, utilizing only sparse interleaved images as input, outperforms traditional dense multi-view input approaches and achieves state-of-the-art performance.

Computer Vision · Everything Else

Jianglin Lu, Simon Jenni, Kushal Kafle, Jing Shi, Handong Zhao, Yun Fu

Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user queries. Such queries are typically only one or two words long, rendering them semantically ambiguous, prone to collisions across diverse visual interpretations, and lacking explicit control over the quality of retrieved images. To address these issues, we propose a new paradigm of quality-controllable retrieval, which enriches short queries with contextual details while incorporating explicit notions of image quality. Our key idea is to leverage a generative language model as a query completion function, extending underspecified queries into descriptive forms that capture fine-grained visual attributes such as pose, scene, and aesthetics. We introduce a general framework that conditions query completion on discretized quality levels, derived from relevance and aesthetic scoring models, so that query enrichment is not only semantically meaningful but also quality-aware. The resulting system provides three key advantages: 1) flexibility, it is compatible with any pretrained vision-language model (VLMs) without modification; 2) transparency, enriched queries are explicitly interpretable by users; and 3) controllability, enabling retrieval results to be steered toward user-preferred quality levels. Extensive experiments demonstrate that our proposed approach significantly improves retrieval results and provides effective quality control, bridging the gap between the expressive capacity of modern VLMs and the underspecified nature of short user queries. Our code is available at https://github.com/Jianglin954/QCQC.

Computer Vision · Classification and Understanding

Pavel Suma, Giorgos Kordopatis-Zilos, Yannis Kalantidis, Giorgos Tolias

Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, making generalization to unseen data critical. We introduce ELViS, an image-to-image similarity model that generalizes effectively to unseen domains. Unlike conventional approaches, our model operates in similarity space rather than representation space, promoting cross-domain transfer. It leverages local descriptor correspondences, refines their similarities through an optimal transport step with data-dependent gains that suppress uninformative descriptors, and aggregates strong correspondences via a voting process into an image-level similarity. This design injects strong inductive biases, yielding a simple, efficient, and interpretable model. To assess generalization, we compile a benchmark of eight datasets spanning landmarks, artworks, products, and multi-domain collections, and evaluate ELViS as a re-ranking method. Our experiments show that ELViS outperforms competing methods by a large margin in out-of-domain scenarios and on average, while requiring only a fraction of their computational cost.

Computer Vision · Classification and Understanding

Shiyu Xuan, Dongkai Wang, Zechao Li, Jinhui Tang

Zero-shot Human-object interaction (HOI) detection aims to locate humans and objects in images and recognize their interactions. While advances in open-vocabulary object detection provide promising solutions for object localization, interaction recognition (IR) remains challenging due to the combinatorial diversity of interactions. Existing methods, including two-stage methods, tightly couple IR with a specific detector and rely on coarse-grained vision-language model (VLM) features, which limit generalization to unseen interactions. In this work, we propose a decoupled framework that separates object detection from IR and leverages multi-modal large language models (MLLMs) for zero-shot IR. We introduce a deterministic generation method that formulates IR as a visual question answering task and enforces deterministic outputs, enabling training-free zero-shot IR. To further enhance performance and efficiency by fine-tuning the model, we design a spatial-aware pooling module that integrates appearance and pairwise spatial cues, and a one-pass deterministic matching method that predicts all candidate interactions in a single forward pass. Extensive experiments on HICO-DET and V-COCO demonstrate that our method achieves superior zero-shot performance, strong cross-dataset generalization, and the flexibility to integrate with any object detectors without retraining. Code will be released.

Hao Wang, Yu Liu, Daniel Biggs, Haoru Wang, Jiandong Yu, Ping Huang

Simulating interactions between deformable bodies is vital in fields like material science, mechanical design, and robotics. While learning-based methods with Graph Neural Networks (GNNs) are effective at solving complex physical systems, they encounter scalability issues when modeling deformable body interactions. To model interactions between objects, pairwise global edges have to be created dynamically, which is computationally intensive and impractical for large-scale meshes. To overcome these challenges, drawing on insights from geometric representations, we propose an Adaptive Spatial Tokenization (AST) method for efficient representation of physical states. By dividing the simulation space into a grid of cells and mapping unstructured meshes onto this structured grid, our approach naturally groups adjacent mesh nodes. We then apply a cross-attention module to map the sparse cells into a compact, fixed-length embedding, serving as tokens for the entire physical state. Self-attention modules are employed to predict the next state over these tokens in latent space. This framework leverages the efficiency of tokenization and the expressive power of attention mechanisms to achieve accurate and scalable simulation results. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in modeling deformable body interactions. Notably, it remains effective on large-scale simulations with meshes exceeding 100,000 nodes, where existing methods are hindered by computational limitations. Additionally, we contribute a novel large-scale dataset encompassing a wide range of deformable body interactions to support future research in this area.

Adrita Das, Dantong Zhu

State Space Models (SSMs), including Mamba, commonly suffer from two failure modes: recency bias, where the model biases strongly toward recent inputs, and over-smoothing, where hidden states become indistinguishable with depth. The paper argues that these issues originate from the learned state-transition matrix $A_t$, whose memory-decay values collapse into a narrow range, limiting the diversity of timescales the model can represent. To mitigate this, the authors introduce polarization, where one dimension of $A_t$ is fixed to serve as a perfect long-term memory channel and another as a pure short-term memory channel, while all other dimensions remain learnable. This enforces both a stable non-decaying pathway and a rapidly resetting pathway, preventing the system from collapsing into uniformly slow or fast decay behavior. Through associative-recall experiments, the polarized Mamba variants demonstrate substantially improved long-context retrieval. Overall, the findings indicate that standard parameterizations of $A_t$ fail to preserve sufficient memory diversity, whereas polarization offers a simple and effective mechanism for stabilizing long-range information flow in SSMs.

Computer Vision · Classification and Understanding

Ziteng Wei, Qiang He, Feifei Chen, Ranjie Duan, Xiaodan Li, Bin Li, YueFeng Chen, Hui Xue', Hai Jin, Yun Yang

Large Vision Transformers (ViTs) must often be compressed before they can be deployed on resource-constrained edge devices. However, many edge devices require only part of the *all-classes* knowledge of a pre-trained ViT in their corresponding application scenarios. This is overlooked by existing compression methods. Lightweight models produced by these methods retain a substantial amount of class-irrelevant knowledge and suffer suboptimal performance on target classes. To address this, we analyze the knowledge distribution of ViT and reveal a knowledge disentanglement within it: neurons in the feed-forward network (FFN) modules encode class-specific knowledge, while the multi-head attention (MHA) modules capture class-agnostic patterns. Building on this insight, we introduce Vulcan, a pruning-oriented post-training method for deriving compact class-specific models from a pre-trained ViT under given resource budgets. Vulcan follows a novel *train-then-prune* paradigm, which introduces redundancy into ViTs deliberately by collapsing FFN neurons onto those with the highest class-specific activations and by enforcing low-rankness in MHA weights. This design mitigates the irreversible knowledge loss of direct pruning, so that the post-trained model can be compressed into a compact one with negligible performance loss. Notably, the derived edge ViTs not only achieve significant reductions in size and computation but also even surpass the original ViTs in performance on specific classes. Comprehensive experiments with five base ViTs covering three representative visual tasks on four datasets demonstrate that Vulcan-derived ViTs outperform the base ViTs on class-specific tasks by up to 15.12\% in accuracy, with only 20\%–40\% of their sizes. Compared with state-of-the-art structured pruning methods, Vulcan improves class-specific accuracy by up to 13.92\%. Code is available at [Vulcan](https://github.com/CGCL-codes/Vulcan).

Computer Vision · Classification and Understanding

Hongquan Liu, ChenyuGuo Guo, Yixin Ren, Jihong Guan, Shuigeng Zhou

Semi-supervised federated learning (SSFL) has emerged as an effective approach to leverage unlabeled data distributed across multiple data owners for improving model generalization. Existing SSFL methods typically assume that labeled and unlabeled data share the same label space. However, in realistic federated scenarios, unlabeled data often contain categories absent from the labeled set, i.e., outliers, which can severely degrade the performance of SSFL algorithms. In this paper, we address this under-explored issue, formally propose the open-set semi-supervised federated learning (OSSFL) problem, and develop the first OSSFL framework, FedOpenMatch. Our method adopts a one-vs-all (OVA) classifier as the outlier detector, equipped with logit adjustment to mitigate inlier-outlier imbalance and a gradient stop mechanism to reduce feature interference between the OVA and inlier classifiers. In addition, we introduce the logit consistency regularization loss, yielding more robust performance. Extensive experiments on standard benchmarks across diverse data settings demonstrate the effectiveness of FedOpenMatch, which significantly outperforms the baselines.

Theory · Interpretability and Visualization

Felipe Urrutia, Jorge Salas, Alexander Kozachinskiy, Cristian Calderon, Hector Pasten, Cristobal Rojas

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded using Positional Encodings (PEs). One such popular PE, namely Rotary PE (RoPE), has been widely used due to its empirical success. Recently, it has been argued that part of RoPE's success emerges from its ability to encode robust positional and semantic information using large and small frequencies, respectively. In this work, we perform a deeper dive into the positional versus symbolic dichotomy of attention heads behavior, both at the theoretical and empirical level. We provide general definitions of what it means for a head to behave positionally or symbolically, prove that these are two mutually exclusive behaviors and develop a metric to quantify them. We apply our framework to analyze Transformer-based LLMs using RoPE and find that all heads exhibit a strong correspondence between behavior and frequency use. Finally, we introduce canonical tasks designed to be either purely positional or symbolic, and demonstrate that the Transformer performance causally relates to the ability of attention heads to leverage the appropriate frequencies. In particular, we show that we can control the Transformer performance by controlling which frequencies the attention heads can access. Altogether, our work provides a detailed understanding of RoPE, and how its properties relate to model behavior.

Computer Vision · Classification and Understanding

Chengjie Ge, Yufeng Peng, Zihao Li, Qiyu Kang, Xueyang Fu, Xuhao Li, Qixin ZHANG, Ren Junhao, Zheng-Jun Zha

Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy efficiency and biological realism. Most existing SNNs are based on neural dynamics such as the (leaky) integrate-and-fire (IF/LIF) models, which are described by *first-order* ordinary differential equations (ODEs) with Markovian characteristics. This means the potential state at any time depends solely on its immediate past value, potentially limiting network expressiveness. Empirical studies of real neurons, however, reveal long-range correlations and fractal dendritic structures, suggesting non-Markovian behavior better modeled by *fractional-order* ODEs. Motivated by this, we propose a *fractional-order* spiking neural network (f-SNN) framework that strictly generalizes integer-order SNNs and captures long-term dependencies in membrane potential and spike trains via fractional dynamics, enabling richer temporal patterns. We also release an open-source toolbox to support the f-SNN framework, applicable to diverse architectures and real-world tasks. Experimentally, fractional adaptations of established SNNs into the f-SNN framework achieve superior accuracy, comparable energy efficiency, and improved robustness to noise, underscoring the promise of f-SNNs as an effective extension of traditional SNNs.

Applications · Language, Speech and Dialog

Jiahong Liu, Wenhao Yu, Quanyu Dai, Zhongyang Li, Jieming Zhu, Menglin Yang, Tat-Seng Chua, Irwin King

Personalization has become a pivotal field of study in contemporary intelligent systems. While large language models (LLMs) excel at general knowledge tasks, they often struggle with personalization, i.e., adapting their outputs to individual user expectations. Existing approaches that steer LLM behavior to meet users’ implicit preferences and behavior patterns, primarily relying on tune-free methods (e.g., RAG, PAG) or parameter fine-tuning methods (e.g., LoRA), face challenges in effectively balancing effectiveness and efficiency. Moreover, the mechanisms underlying personalized preferences remain underexplored. To address these challenges, we first uncover key patterns of user-specific information embedded in the representation space. Specifically, we find that (1) personalized information lies within a low-rank subspace represented by vectors, and (2) these vectors demonstrate both a collective shift shared across users and a personalized shift unique to each individual user. Building on these insights, we introduce PerFit, a novel two-stage solution that directly fine-tunes interventions in the hidden representation space by addressing both collective and user-specific shifts, thereby achieving precise steering of LLM with minimal parameter overhead. Experimental results demonstrate that \perfit delivers strong performance across six datasets while \cutting the number of parameters by an average of 92.3% compared to the state-of-the-art method.

Applications · Language, Speech and Dialog

Jiwei Tang, Shilei Liu, ZHICHENG ZHANG, Yujin Yuan, Libin Zheng, wenbo su, Bo Zheng

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression methods address these challenges by significantly reducing input length and eliminating redundancy. We propose COMI, a coarse-to-fine adaptive context compression framework that jointly optimizes for semantic relevance and diversity under high compression rates. We introduce Marginal Information Gain (MIG), a metric defined as the relevance of a unit to the input query minus its semantic redundancy with other units, guiding the compression process to prioritize information that is both relevant and low redundant. The framework operates in two stages: (1) Coarse-Grained Group Reallocation, where the context is partitioned into groups and dynamically assigned compression rates based on inter-group MIG, ensuring compression budgets align with information value distribution; and (2) Fine-Grained Token Merging, where tokens within each group are fused via an intra-group MIG-based weighting mechanism, thereby preserving key semantics while avoiding the accumulation of redundancy. Extensive experiments across question-answering (e.g., NaturalQuestions, 2WikiMQA, HotpotQA and NarrativeQA), summarization (e.g., MultiNews) with various backbones (e.g., LLaMA-2-7B, Qwen2-7B) show that COMI outperforms existing baselines by a large margin, e.g., approximately 25-point Exact Match (EM) improvement under 32x compression constraint with Qwen2-7B on NaturalQuestions

Computer Vision · Segmentation

Wentian Xu, Ziyun Liang, Harry Anthony, Yasin Ibrahim, Felix Cohen, Guang Yang, Konstantinos Kamnitsas

Interactive segmentation uses real-time user inputs, such as mouse clicks, to iteratively refine model predictions. Although not originally designed to address distribution shifts, this paradigm naturally lends itself to such challenges. In medical imaging, where distribution shifts are common, interactive methods can use user inputs to guide models towards improved predictions. Moreover, once a model is deployed, user corrections can be used to adapt the network parameters to the new data distribution, mitigating distribution shift. Based on these insights, we aim to develop a practical, effective method for improving the adaptive capabilities of interactive segmentation models to new data distributions in medical imaging. Firstly, we found that strengthening the model's responsiveness to clicks is important for the initial training process. Moreover, we show that by treating the post-interaction user-refined model output as pseudo-ground-truth, we can design a lean, practical online adaptation method that enables a model to learn effectively across sequential test images. The framework includes two components: (i) a Post-Interaction adaptation process, updating the model after the user has completed interactive refinement of an image, and (ii) a Mid-Interaction adaptation process, updating incrementally after each %user click. Both processes include a Click-Centered Gaussian loss that strengthens the model's reaction to clicks and enhances focus on user-guided, clinically relevant regions. Experiments on 5 fundus and 4 brain‑MRI databases show that our approach consistently outperforms existing methods under diverse distribution shifts, including unseen imaging modalities and pathologies. Code: https://github.com/WenTXuL/OAIMS

General Machine Learning · Probabilistic Methods

Aayush Mishra, Daniel Habermann, Marvin Schmitt, Stefan Radev, Paul-Christian Bürkner

Amortized Bayesian inference (ABI) with neural networks can solve probabilistic inverse problems orders of magnitude faster than classical methods. However, ABI is not yet sufficiently robust for widespread and safe application. When performing inference on observations outside the scope of the simulated training data, posterior approximations are likely to become highly biased, which cannot be corrected by additional simulations due to the bad pre-asymptotic behavior of current neural posterior estimators. In this paper, we propose a semi-supervised approach that enables training not only on labeled simulated data generated from the model, but also on unlabeled data originating from any source, including real data. To achieve this, we leverage Bayesian self-consistency properties that can be transformed into strictly proper losses that do not require knowledge of ground-truth parameters. We test our approach on several real-world case studies, including applications to high-dimensional time-series and image data. Our results show that semi-supervised learning with unlabeled data drastically improves the robustness of ABI in the out-of-simulation regime. Notably, inference remains accurate even when evaluated on observations far away from the labeled and unlabeled data seen during training.

Computer Vision · Vision Models & Multimodal

Hao Wu, Yingqi Fan, Dai Jinyang, Junlong Tong, Yunpu Ma, Xiaoyu Shen

The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning offers a promising solution, current methods misinterpret shallow layer functions and use rigid schedules, which fail to unlock the full efficiency potential. To address these issues, we propose HiDrop, a framework that aligns token pruning with the true hierarchical function of MLLM layers. HiDrop features two key innovations: (1) Late Injection, which bypasses passive shallow layers to introduce visual tokens exactly where active fusion begins; and (2) Concave Pyramid Pruning with an Early Exit mechanism to dynamically adjust pruning rates across middle and deep layers. This process is optimized via an inter-layer similarity measure and a differentiable top-$k$ operator. To ensure practical efficiency, HiDrop further incorporates persistent positional encoding, FlashAttention-compatible token selection, and parallel decoupling of vision computation to eliminate hidden overhead associated with dynamic token reduction. Extensive experiments show that HiDrop compresses $\sim$90\% visual tokens while matching the original performance and accelerating training by 1.72$\times$. Our work not only sets a new state-of-the-art for efficient MLLM training and inference but also provides valuable insights into the hierarchical nature of multimodal fusion. The code is released at https://github.com/EIT-NLP/HiDrop.

Computer Vision · Vision Models & Multimodal

SICHENG FAN, Qingyun Shi, Shengze Xu, Shengbo Cai, Tieyong Zeng, LI LING, Yanyi Shang, Dehan Kong

Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a more critical factor: the efficiency of compressing a large language model's (LLM) latent knowledge into actionable agent behavior. We introduce WebFactory, a novel, fully automated closed-loop reinforcement learning pipeline for GUI agents, systematically compressing LLM-encoded internet intelligence into efficient, grounded actions. Our pipeline features a process of scalable environment synthesis → knowledge-aware task generation → LLM-powered trajectory collection → decomposed reward RL training → systematic agent evaluation. Remarkably, our agent demonstrates exceptional data efficiency and generalization. Trained on synthetic data from only 10 websites within WebFactory, it achieves performance comparable to GUI agents trained on same amount of human-annotated data from a much larger set of environments. This superior performance is consistent across our internal offline and online transferring benchmarks, where our agent also significantly outperforms the base foundation model. We further provide critical insights into the "embodiment potential" of different LLM foundations, offering a new axis for model evaluation. This work presents a scalable and cost-effective paradigm for transforming passive internet knowledge into active, grounded intelligence, marking a critical step towards general-purpose interactive agents.

Computer Vision · Vision Models & Multimodal

Junyang Ji, Shengjun Zhang, Da Li, Yuxiao Luo, Yan Wang, Di Xu, Biao Yang, Wei Yuan, Fan Yang, Zhihai He 等

Composed video retrieval presents a complex challenge: retrieving a target video based on a source video and a textual modification instruction. This task demands fine-grained reasoning over multimodal transformations. However, existing benchmarks predominantly focus on vision–text alignment, largely overlooking the rich semantic signals embedded in audio—such as speech, music, and environmental sounds—which are often decisive for comprehensive video understanding. To bridge this gap, we introduce **OmniCVR**, a large-scale benchmark for omni-composed video retrieval that establishes vision, audio, and text as first-class modalities. OmniCVR is constructed via a scalable, automated pipeline integrating content-aware segmentation, omni-modal annotation, and a rigorous dual-validation protocol involving both large language models and human experts. The benchmark comprises vision-centric, audio-centric, and integrated queries, with the latter forming the majority to accurately reflect real-world multimodal complexity. Furthermore, we propose **AudioVLM2Vec**, an audio-aware extension of VLM2Vec. By incorporating explicit audio semantics, AudioVLM2Vec achieves state-of-the-art performance, highlighting fundamental limitations in the audio reasoning capabilities of current multimodal retrieval systems.

Computer Vision · Vision Models & Multimodal

Feng Yu, Xiangyu Wu, Yang Yang, Jianfeng Lu

Multimodal learning integrates data from diverse sensors to effectively harness information from different modalities. However, recent studies reveal that joint learning often overfits certain modalities while neglecting others, leading to performance inferior to that of unimodal learning. Although previous efforts have sought to balance modal contributions or combine joint and unimodal learning—thereby mitigating the degradation of weaker modalities with promising outcomes—few have examined the relationship between joint and unimodal learning from an information-theoretic perspective. In this paper, we theoretically analyze modality competition and propose a method for multimodal classification by maximizing the total correlation between multimodal features and labels. By maximizing this objective, our approach alleviates modality competition while capturing inter-modal interactions via feature alignment. Building on Mutual Information Neural Estimation (MINE), we introduce **T**otal **C**orrelation **N**eural **E**stimation (**TCNE**) to derive a lower bound for total correlation. Subsequently, we present TCMax, a hyperparameter-free loss function that maximizes total correlation through variational bound optimization. Extensive experiments demonstrate that TCMax outperforms state-of-the-art joint and unimodal learning approaches. Our code is available at https://anonymous.4open.science/r/TCMax_Experiments.

Computer Vision · Vision Models & Multimodal

Mouxiao Huang, Borui Jiang, Dehua Zheng, Hailin Hu, Kai Han, Xinghao Chen

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently disrupt spatial layouts and temporal continuity by disregarding positional relationships. In this work, we propose a novel encoding operator dubbed as **P**ositional **P**reservation **E**mbedding (**PPE**), which has the main hallmark of preservation of spatiotemporal structure during visual token compression. PPE explicitly introduces the disentangled encoding of 3D positions in the token dimension, enabling each compressed token to encapsulate different positions from multiple original tokens. Furthermore, we show that PPE can effectively support cascade clustering --- a progressive token compression strategy that leads to better performance retention. PPE is a parameter-free and generic operator that can be seamlessly integrated into existing token merging methods without any adjustments. Applied to state-of-the-art token merging framework, PPE achieves consistent improvements of 2\%~5\% across multiple vision-language benchmarks, including MMBench (general vision understanding), TextVQA (layout understanding) and VideoMME (temporal understanding). These results demonstrate that preserving positional cues is critical for efficient and effective MLLM reasoning. Our code is available at https://github.com/MouxiaoHuang/PPE

Computer Vision · Vision Models & Multimodal

Gijs Moens, Regina Beets-Tan, Eduardo Pooch

Convolutional Neural Networks (CNNs) rely on fixed-size kernels scanning local patches, which limits their ability to capture global context or long-range dependencies without very deep architectures. Vision Transformers (ViTs), in turn, provide global connectivity but lack spatial inductive bias, depend on explicit positional encodings, and remain tied to the initial patch size. Bridging these limitations requires a representation that is both structured and global. We introduce SONIC (Spectral Oriented Neural Invariant Convolutions), a continuous spectral parameterisation that models convolutional operators using a small set of shared, orientation-selective components. These components define smooth responses across the full frequency domain, yielding global receptive fields and filters that adapt naturally across resolutions. Across synthetic benchmarks, large-scale image classification, and 3D medical datasets, SONIC shows improved robustness to geometric transformations, noise, and resolution shifts, and matches or exceeds convolutional, attention-based, and prior spectral architectures with an order of magnitude fewer parameters. These results demonstrate that continuous, orientation-aware spectral parameterisations provide a principled and scalable alternative to conventional spatial and spectral operators.