Represenation
-
Terrain Costmap Generation via Scaled Preference Conditioning
2025-11-14 18:04:20Luisa Mao, Garret Warnell, Peter Stone, Joydeep BiswasAbstract
Successful autonomous robot navigation in off-road domains requires the ability to generate high-quality terrain costmaps that are able to both generalize well over a wide variety of terrains and rapidly adapt relative costs at test time to meet mission-specific needs. Existing approaches for costmap generation allow for either rapid test-time adaptation of relative costs (e.g., semantic segmentation methods) or generalization to new terrain types (e.g., representation learning methods), but not both. In this work, we present scaled preference conditioned all-terrain costmap generation (SPACER), a novel approach for generating terrain costmaps that leverages synthetic data during training in order to generalize well to new terrains, and allows for rapid test-time adaptation of relative costs by conditioning on a user-specified scaled preference context. Using large-scale aerial maps, we provide empirical evidence that SPACER outperforms other approaches at generating costmaps for terrain navigation, with the lowest measured regret across varied preferences in five of seven environments for global path planning.
Abstract (translated)
URL
https://arxiv.org/abs/2511.11529
PDF
-
Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities
2025-11-14 17:34:20Yiyun Zhou, Mingjing Xu, Jingwei Shi, Quanjiang Li, Jingyuan ChenAbstract
Tactile sensing offers rich and complementary information to vision and language, enabling robots to perceive fine-grained object properties. However, existing tactile sensors lack standardization, leading to redundant features that hinder cross-sensor generalization. Moreover, existing methods fail to fully integrate the intermediate communication among tactile, language, and vision modalities. To address this, we propose TLV-CoRe, a CLIP-based Tactile-Language-Vision Collaborative Representation learning method. TLV-CoRe introduces a Sensor-Aware Modulator to unify tactile features across different sensors and employs tactile-irrelevant decoupled learning to disentangle irrelevant tactile features. Additionally, a Unified Bridging Adapter is introduced to enhance tri-modal interaction within the shared representation space. To fairly evaluate the effectiveness of tactile models, we further propose the RSS evaluation framework, focusing on Robustness, Synergy, and Stability across different methods. Experimental results demonstrate that TLV-CoRe significantly improves sensor-agnostic representation learning and cross-modal alignment, offering a new direction for multimodal tactile representation.
Abstract (translated)
URL
https://arxiv.org/abs/2511.11512
PDF
-
Large-scale modality-invariant foundation models for brain MRI analysis: Application to lesion segmentation
2025-11-14 13:56:07Petros Koutsouvelis, Matej Gazda, Leroy Volmer, Sina Amirrajab, Kamil Barbierik, Branislav Setlak, Jakub Gazda, Peter DrotarAbstract
The field of computer vision is undergoing a paradigm shift toward large-scale foundation model pre-training via self-supervised learning (SSL). Leveraging large volumes of unlabeled brain MRI data, such models can learn anatomical priors that improve few-shot performance in diverse neuroimaging tasks. However, most SSL frameworks are tailored to natural images, and their adaptation to capture multi-modal MRI information remains underexplored. This work proposes a modality-invariant representation learning setup and evaluates its effectiveness in stroke and epilepsy lesion segmentation, following large-scale pre-training. Experimental results suggest that despite successful cross-modality alignment, lesion segmentation primarily benefits from preserving fine-grained modality-specific features. Model checkpoints and code are made publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2511.11311
PDF
-
MOON Embedding: Multimodal Representation Learning for E-commerce Search Advertising
2025-11-14 13:49:56Chenghan Fu, Daoze Zhang, Yukang Lin, Zhanheng Nie, Xiang Zhang, Jianyu Liu, Yueran Liu, Wanxian Guan, Pengjie Wang, Jian Xu, Bo ZhengAbstract
We introduce MOON, our comprehensive set of sustainable iterative practices for multimodal representation learning for e-commerce applications. MOON has already been fully deployed across all stages of Taobao search advertising system, including retrieval, relevance, ranking, and so on. The performance gains are particularly significant on click-through rate (CTR) prediction task, which achieves an overall +20.00% online CTR improvement. Over the past three years, this project has delivered the largest improvement on CTR prediction task and undergone five full-scale iterations. Throughout the exploration and iteration of our MOON, we have accumulated valuable insights and practical experience that we believe will benefit the research community. MOON contains a three-stage training paradigm of "Pretraining, Post-training, and Application", allowing effective integration of multimodal representations with downstream tasks. Notably, to bridge the misalignment between the objectives of multimodal representation learning and downstream training, we define the exchange rate to quantify how effectively improvements in an intermediate metric can translate into downstream gains. Through this analysis, we identify the image-based search recall as a critical intermediate metric guiding the optimization of multimodal models. Over three years and five iterations, MOON has evolved along four critical dimensions: data processing, training strategy, model architecture, and downstream application. The lessons and insights gained through the iterative improvements will also be shared. As part of our exploration into scaling effects in the e-commerce field, we further conduct a systematic study of the scaling laws governing multimodal representation learning, examining multiple factors such as the number of training tokens, negative samples, and the length of user behavior sequences.
Abstract (translated)
URL
https://arxiv.org/abs/2511.11305
PDF
-
LANE: Lexical Adversarial Negative Examples for Word Sense Disambiguation
2025-11-14 12:37:20Jader Martins Camboim de S\'a, Jooyoung Lee, C\'edric Pruski, Marcos Da SilveiraAbstract
Fine-grained word meaning resolution remains a critical challenge for neural language models (NLMs) as they often overfit to global sentence representations, failing to capture local semantic details. We propose a novel adversarial training strategy, called LANE, to address this limitation by deliberately shifting the model's learning focus to the target word. This method generates challenging negative training examples through the selective marking of alternate words in the training set. The goal is to force the model to create a greater separability between same sentences with different marked words. Experimental results on lexical semantic change detection and word sense disambiguation benchmarks demonstrate that our approach yields more discriminative word representations, improving performance over standard contrastive learning baselines. We further provide qualitative analyses showing that the proposed negatives lead to representations that better capture subtle meaning differences even in challenging environments. Our method is model-agnostic and can be integrated into existing representation learning frameworks.
Abstract (translated)
URL
https://arxiv.org/abs/2511.11234
PDF
-
PROMISE: Prompt-Attentive Hierarchical Contrastive Learning for Robust Cross-Modal Representation with Missing Modalities
2025-11-14 06:39:24Jiajun Chen, Sai Cheng, Yutao Yuan, Yirui Zhang, Haitao Yuan, Peng Peng, Yi ZhongAbstract
Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities are missing or unavailable. This degradation primarily stems from inconsistent representation learning between complete multimodal data and incomplete modality scenarios. Existing approaches typically address missing modalities through relatively simplistic generation methods, yet these approaches fail to adequately preserve cross-modal consistency, leading to suboptimal performance. To overcome this limitation, we propose a novel multimodal framework named PROMISE, a PROMpting-Attentive HIerarchical ContraStive LEarning approach designed explicitly for robust cross-modal representation under conditions of missing modalities. Specifically, PROMISE innovatively incorporates multimodal prompt learning into a hierarchical contrastive learning framework, equipped with a specially designed prompt-attention mechanism. This mechanism dynamically generates robust and consistent representations for scenarios where particular modalities are absent, thereby effectively bridging the representational gap between complete and incomplete data. Extensive experiments conducted on benchmark datasets, along with comprehensive ablation studies, clearly demonstrate the superior performance of PROMISE compared to current state-of-the-art multimodal methods.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10997
PDF
-
Language-Guided Graph Representation Learning for Video Summarization
2025-11-14 04:35:48Wenrui Li, Wei Han, Hengyu Man, Wangmeng Zuo, Xiaopeng Fan, Yonghong TianAbstract
With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturing global dependencies in video content and accommodating multimodal user customization. Moreover, temporal proximity between video frames does not always correspond to semantic proximity. To tackle these challenges, we propose a novel Language-guided Graph Representation Learning Network (LGRLN) for video summarization. Specifically, we introduce a video graph generator that converts video frames into a structured graph to preserve temporal order and contextual dependencies. By constructing forward, backward and undirected graphs, the video graph generator effectively preserves the sequentiality and contextual relationships of video content. We designed an intra-graph relational reasoning module with a dual-threshold graph convolution mechanism, which distinguishes semantically relevant frames from irrelevant ones between nodes. Additionally, our proposed language-guided cross-modal embedding module generates video summaries with specific textual descriptions. We model the summary generation output as a mixture of Bernoulli distribution and solve it with the EM algorithm. Experimental results show that our method outperforms existing approaches across multiple benchmarks. Moreover, we proposed LGRLN reduces inference time and model parameters by 87.8% and 91.7%, respectively. Our codes and pre-trained models are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10953
PDF
-
Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Image Segmentation
2025-11-14 04:15:34Xingyue Zhao, Wenke Huang, Xingguang Wang, Haoyu Zhao, Linghao Zhuang, Anwen Jiang, Guancheng Wan, Mang YeAbstract
Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue by leveraging model representations (e.g., mean feature vectors) to correct local training; however, they often face two key limitations: 1) Incomplete Contextual Representation Learning: Current approaches primarily focus on final-layer features, overlooking critical multi-level cues and thus diluting essential context for accurate segmentation. 2) Layerwise Style Bias Accumulation: Although utilizing representations can partially align global features, these methods neglect domain-specific biases within intermediate layers, allowing style discrepancies to build up and reduce model robustness. To address these challenges, we propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment. Specifically, we introduce a frequency-domain adaptive style recalibration into prototype construction that not only decouples content-style representations but also learns optimal style parameters, enabling more robust domain-invariant prototypes. Furthermore, we design a context-aware dual-level prototype alignment method that extracts domain-invariant prototypes from different layers of both encoder and decoder and fuses them with contextual information for finer-grained representation alignment. Extensive experiments on two public datasets demonstrate that our method exhibits remarkable performance.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10945
PDF
-
CLIP4VI-ReID: Learning Modality-shared Representations via CLIP Semantic Bridge for Visible-Infrared Person Re-identification
2025-11-13 13:46:04Xiaomei Yang, Xizhan Gao, Sijie Niu, Fa Zhu, Guang Feng, Xiaofeng Qu, David CamachoAbstract
This paper proposes a novel CLIP-driven modality-shared representation learning network named CLIP4VI-ReID for VI-ReID task, which consists of Text Semantic Generation (TSG), Infrared Feature Embedding (IFE), and High-level Semantic Alignment (HSA). Specifically, considering the huge gap in the physical characteristics between natural images and infrared images, the TSG is designed to generate text semantics only for visible images, thereby enabling preliminary visible-text modality alignment. Then, the IFE is proposed to rectify the feature embeddings of infrared images using the generated text semantics. This process injects id-related semantics into the shared image encoder, enhancing its adaptability to the infrared modality. Besides, with text serving as a bridge, it enables indirect visible-infrared modality alignment. Finally, the HSA is established to refine the high-level semantic alignment. This process ensures that the fine-tuned text semantics only contain id-related information, thereby achieving more accurate cross-modal alignment and enhancing the discriminability of the learned modal-shared representations. Extensive experimental results demonstrate that the proposed CLIP4VI-ReID achieves superior performance than other state-of-the-art methods on some widely used VI-ReID datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10309
PDF
-
How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders
2025-11-13 08:51:29Yiming Tang, Abhijeet Sinha, Dianbo LiuAbstract
Although recent generative models are remarkably capable of producing instruction-following and realistic outputs, they remain prone to notable physical plausibility failures. Though critical in applications, these physical plausibility errors often escape detection by existing evaluation methods. Furthermore, no framework exists for automatically identifying and interpreting specific physical error patterns in natural language, preventing targeted model improvements. We introduce Matryoshka Transcoders, a novel framework for the automatic discovery and interpretation of physical plausibility features in generative models. Our approach extends the Matryoshka representation learning paradigm to transcoder architectures, enabling hierarchical sparse feature learning at multiple granularity levels. By training on intermediate representations from a physical plausibility classifier and leveraging large multimodal models for interpretation, our method identifies diverse physics-related failure modes without manual feature engineering, achieving superior feature relevance and feature accuracy compared to existing approaches. We utilize the discovered visual patterns to establish a benchmark for evaluating physical plausibility in generative models. Our analysis of eight state-of-the-art generative models provides valuable insights into how these models fail to follow physical constraints, paving the way for further model improvements.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10094
PDF
-
Multivariate Gaussian Representation Learning for Medical Action Evaluation
2025-11-13 08:01:58Luming Yang, Haoxian Liu, Siqing Li, Alper YilmazAbstract
Fine-grained action evaluation in medical vision faces unique challenges due to the unavailability of comprehensive datasets, stringent precision requirements, and insufficient spatiotemporal dynamic modeling of very rapid actions. To support development and evaluation, we introduce CPREval-6k, a multi-view, multi-label medical action benchmark containing 6,372 expert-annotated videos with 22 clinical labels. Using this dataset, we present GaussMedAct, a multivariate Gaussian encoding framework, to advance medical motion analysis through adaptive spatiotemporal representation learning. Multivariate Gaussian Representation projects the joint motions to a temporally scaled multi-dimensional space, and decomposes actions into adaptive 3D Gaussians that serve as tokens. These tokens preserve motion semantics through anisotropic covariance modeling while maintaining robustness to spatiotemporal noise. Hybrid Spatial Encoding, employing a Cartesian and Vector dual-stream strategy, effectively utilizes skeletal information in the form of joint and bone features. The proposed method achieves 92.1% Top-1 accuracy with real-time inference on the benchmark, outperforming the ST-GCN baseline by +5.9% accuracy with only 10% FLOPs. Cross-dataset experiments confirm the superiority of our method in robustness.
Abstract (translated)
URL
https://arxiv.org/abs/2511.10060
PDF
-
Multiple Treatments Causal Effects Estimation with Task Embeddings and Balanced Representation Learning
2025-11-12 23:36:41Yuki Murakami, Takumi Hattori, Kohsuke KubotaAbstract
The simultaneous application of multiple treatments is increasingly common in many fields, such as healthcare and marketing. In such scenarios, it is important to estimate the single treatment effects and the interaction treatment effects that arise from treatment combinations. Previous studies have proposed using independent outcome networks with subnetworks for interactions, or combining task embedding networks that capture treatment similarity with variational autoencoders. However, these methods suffer from the lack of parameter sharing among related treatments, or the estimation of unnecessary latent variables reduces the accuracy of causal effect estimation. To address these issues, we propose a novel deep learning framework that incorporates a task embedding network and a representation learning network with the balancing penalty. The task embedding network enables parameter sharing across related treatment patterns because it encodes elements common to single effects and contributions specific to interaction effects. The representation learning network with the balancing penalty learns representations nonparametrically from observed covariates while reducing distances in representation distributions across different treatment patterns. This process mitigates selection bias and avoids model misspecification. Simulation studies demonstrate that the proposed method outperforms existing baselines, and application to real-world marketing datasets confirms the practical implications and utility of our framework.
Abstract (translated)
URL
https://arxiv.org/abs/2511.09814
PDF
-
Compression then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding
2025-11-11 17:23:02Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui ZhouAbstract
Vision-language models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval, clustering, and classification. An effective embedding is expected to comprehensively preserve the semantic content of the input while simultaneously emphasizing features that are discriminative for downstream tasks. Recent approaches demonstrate that VLMs can be adapted into competitive embedding models via large-scale contrastive learning, enabling the simultaneous optimization of two complementary objectives. We argue that the two aforementioned objectives can be decoupled: a comprehensive understanding of the input facilitates the embedding model in achieving superior performance in downstream tasks via contrastive learning. In this paper, we propose CoMa, a compressed pre-training phase, which serves as a warm-up stage for contrastive learning. Experiments demonstrate that with only a small amount of pre-training data, we can transform a VLM into a competitive embedding model. CoMa achieves new state-of-the-art results among VLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08480
PDF
-
Bid Farewell to Seesaw: Towards Accurate Long-tail Session-based Recommendation via Dual Constraints of Hybrid Intents
2025-11-11 16:00:58Xiao Wang, Ke Qin, Dongyang Zhang, Xiurui Xie, Shuang LiangAbstract
Session-based recommendation (SBR) aims to predict anonymous users' next interaction based on their interaction sessions. In the practical recommendation scenario, low-exposure items constitute the majority of interactions, creating a long-tail distribution that severely compromises recommendation diversity. Existing approaches attempt to address this issue by promoting tail items but incur accuracy degradation, exhibiting a "see-saw" effect between long-tail and accuracy performance. We attribute such conflict to session-irrelevant noise within the tail items, which existing long-tail approaches fail to identify and constrain effectively. To resolve this fundamental conflict, we propose \textbf{HID} (\textbf{H}ybrid \textbf{I}ntent-based \textbf{D}ual Constraint Framework), a plug-and-play framework that transforms the conventional "see-saw" into "win-win" through introducing the hybrid intent-based dual constraints for both long-tail and accuracy. Two key innovations are incorporated in this framework: (i) \textit{Hybrid Intent Learning}, where we reformulate the intent extraction strategies by employing attribute-aware spectral clustering to reconstruct the item-to-intent mapping. Furthermore, discrimination of session-irrelevant noise is achieved through the assignment of the target and noise intents to each session. (ii) \textit{Intent Constraint Loss}, which incorporates two novel constraint paradigms regarding the \textit{diversity} and \textit{accuracy} to regulate the representation learning process of both items and sessions. These two objectives are unified into a single training loss through rigorous theoretical derivation. Extensive experiments across multiple SBR models and datasets demonstrate that HID can enhance both long-tail performance and recommendation accuracy, establishing new state-of-the-art performance in long-tail recommender systems.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08378
PDF
-
TurkEmbed: Turkish Embedding Model on NLI & STS Tasks
2025-11-11 15:54:52\"Ozay Ezerceli, Gizem G\"um\"u\c{s}\c{c}eki\c{c}ci, Tu\u{g}ba Erko\c{c}, Berke \"Ozen\c{c}Abstract
This paper introduces TurkEmbed, a novel Turkish language embedding model designed to outperform existing models, particularly in Natural Language Inference (NLI) and Semantic Textual Similarity (STS) tasks. Current Turkish embedding models often rely on machine-translated datasets, potentially limiting their accuracy and semantic understanding. TurkEmbed utilizes a combination of diverse datasets and advanced training techniques, including matryoshka representation learning, to achieve more robust and accurate embeddings. This approach enables the model to adapt to various resource-constrained environments, offering faster encoding capabilities. Our evaluation on the Turkish STS-b-TR dataset, using Pearson and Spearman correlation metrics, demonstrates significant improvements in semantic similarity tasks. Furthermore, TurkEmbed surpasses the current state-of-the-art model, Emrecan, on All-NLI-TR and STS-b-TR benchmarks, achieving a 1-4\% improvement. TurkEmbed promises to enhance the Turkish NLP ecosystem by providing a more nuanced understanding of language and facilitating advancements in downstream applications.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08376
PDF
-
Hybrid Quantum-Classical Selective State Space Artificial Intelligence
2025-11-11 15:26:57Amin Ebrahimi, Farzan HaddadiAbstract
Hybrid Quantum Classical (HQC) algorithms constitute one of the most effective paradigms for exploiting the computational advantages of quantum systems in large-scale numerical tasks. By operating in high-dimensional Hilbert spaces, quantum circuits enable exponential speed-ups and provide access to richer representations of cost landscapes compared to purely classical methods. These capabilities are particularly relevant for machine learning, where state-of-the-art models especially in Natural Language Processing (NLP) suffer from prohibitive time complexity due to massive matrix multiplications and high-dimensional optimization. In this manuscript, we propose a Hybrid Quantum Classical selection mechanism for the Mamba architecture, designed specifically for temporal sequence classification problems. Our approach leverages Variational Quantum Circuits (VQCs) as quantum gating modules that both enhance feature extraction and improve suppression of irrelevant information. This integration directly addresses the computational bottlenecks of deep learning architectures by exploiting quantum resources for more efficient representation learning. We analyze how introducing quantum subroutines into large language models (LLMs) impacts their generalization capability, expressivity, and parameter efficiency. The results highlight the potential of quantum-enhanced gating mechanisms as a path toward scalable, resource-efficient NLP models, in a limited simulation step. Within the first four epochs on a reshaped MNIST dataset with input format (batch, 784, d_model), our hybrid model achieved 24.6% accuracy while using one quantum layer and achieve higher expressivity, compared to 21.6% obtained by a purely classical selection mechanism. we state No founding
Abstract (translated)
URL
https://arxiv.org/abs/2511.08349
PDF
-
Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning
2025-11-11 13:38:23Chenyu Hu, Xiaotong Li, Hao Zhu, Biao HouAbstract
Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The core of this issue is the disruption of the point cloud's intrinsic directional characteristics caused by rotational perturbations. Recent methods attempt to implicitly model rotational equivariance and invariance, preserving directional information and propagating it into deep semantic spaces. Yet, they often fall short of fully exploiting the multiscale directional nature of point clouds to enhance feature representations. To address this, we propose the Direction-Perceptive Vector Network (DiPVNet). At its core is an atomic dot-product operator that simultaneously encodes directional selectivity and rotation invariance--endowing the network with both rotational symmetry modeling and adaptive directional perception. At the local level, we introduce a Learnable Local Dot-Product (L2DP) Operator, which enables interactions between a center point and its neighbors to adaptively capture the non-uniform local structures of point clouds. At the global level, we leverage generalized harmonic analysis to prove that the dot-product between point clouds and spherical sampling vectors is equivalent to a direction-aware spherical Fourier transform (DASFT). This leads to the construction of a global directional response spectrum for modeling holistic directional structures. We rigorously prove the rotation invariance of both operators. Extensive experiments on challenging scenarios involving noise and large-angle rotations demonstrate that DiPVNet achieves state-of-the-art performance on point cloud classification and segmentation tasks. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2511.08240
PDF
-
Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models
2025-11-10 16:03:44Umberto Cappellazzo, Xubo Liu, Pingchuan Ma, Stavros Petridis, Maja PanticAbstract
Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition (AVSR). Despite this progress, current LLM-based approaches typically address each task independently, training separate models that raise computational and deployment resource use while missing potential cross-task synergies. They also rely on fixed-rate token compression, which restricts flexibility in balancing accuracy with efficiency. These limitations highlight the need for a unified framework that can support ASR, VSR, and AVSR while enabling elastic inference. To this end, we present Omni-AVSR, a unified audio-visual LLM that combines efficient multi-granularity training with parameter-efficient adaptation. Specifically, we adapt the matryoshka representation learning paradigm to efficiently train across multiple audio and visual granularities, reducing its inherent training resource use. Furthermore, we explore three LoRA-based strategies for adapting the backbone LLM, balancing shared and task-specific specialization. Experiments on LRS2 and LRS3 show that Omni-AVSR achieves comparable or superior accuracy to state-of-the-art baselines while training a single model at substantially lower training and deployment resource use. The model also remains robust under acoustic noise, and we analyze its scaling behavior as LLM size increases, providing insights into the trade-off between performance and efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07253
PDF
-
Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision
2025-11-10 12:53:32Yimei Zhang, Guojiang Shen, Kaili Ning, Tongwei Ren, Xuebo Qiu, Mengmeng Wang, Xiangjie KongAbstract
Region representation learning plays a pivotal role in urban computing by extracting meaningful features from unlabeled urban data. Analogous to how perceived facial age reflects an individual's health, the visual appearance of a city serves as its ``portrait", encapsulating latent socio-economic and environmental characteristics. Recent studies have explored leveraging Large Language Models (LLMs) to incorporate textual knowledge into imagery-based urban region representation learning. However, two major challenges remain: i)~difficulty in aligning fine-grained visual features with long captions, and ii) suboptimal knowledge incorporation due to noise in LLM-generated captions. To address these issues, we propose a novel pre-training framework called UrbanLN that improves Urban region representation learning through Long-text awareness and Noise suppression. Specifically, we introduce an information-preserved stretching interpolation strategy that aligns long captions with fine-grained visual semantics in complex urban scenes. To effectively mine knowledge from LLM-generated captions and filter out noise, we propose a dual-level optimization strategy. At the data level, a multi-model collaboration pipeline automatically generates diverse and reliable captions without human intervention. At the model level, we employ a momentum-based self-distillation mechanism to generate stable pseudo-targets, facilitating robust cross-modal learning under noisy conditions. Extensive experiments across four real-world cities and various downstream tasks demonstrate the superior performance of our UrbanLN.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07062
PDF
-
S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening
2025-11-10 11:57:47Bowei He, Bowen Gao, Yankai Chen, Yanyan Lan, Chen Ma, Philip S. Yu, Ya-Qin Zhang, Wei-Ying MaAbstract
Virtual screening (VS) is an essential task in drug discovery, focusing on the identification of small-molecule ligands that bind to specific protein pockets. Existing deep learning methods, from early regression models to recent contrastive learning approaches, primarily rely on structural data while overlooking protein sequences, which are more accessible and can enhance generalizability. However, directly integrating protein sequences poses challenges due to the redundancy and noise in large-scale protein-ligand datasets. To address these limitations, we propose \textbf{S$^2$Drug}, a two-stage framework that explicitly incorporates protein \textbf{S}equence information and 3D \textbf{S}tructure context in protein-ligand contrastive representation learning. In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone, combined with a tailored data sampling strategy to reduce redundancy and noise on both protein and ligand sides. In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module, while introducing an auxiliary binding site prediction task. This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement, thereby refining protein-ligand matching. Across multiple benchmarks, S$^2$Drug consistently improves virtual screening performance and achieves strong results on binding site prediction, demonstrating the value of bridging sequence and structure in contrastive learning.
Abstract (translated)
URL
https://arxiv.org/abs/2511.07006
PDF
