3D Encoder

Semantic occupancy prediction gives an embodied agent a voxel-level account of where space is free, occupied, and semantically meaningful. In RGB-D pipelines such as EmbodiedScan, the image encoder is often left as a default module, even though its features are the visual evidence later sampled into the 3D grid. We study this design choice directly. A central finding is that changing the 2D backbone improves occupancy accuracy more than several carefully designed occupancy architectures or modules. We keep the main RGB-D projection, depth branch, and occupancy head fixed, and replace only the image backbone. The compared encoders are CLIP-ResNet, CLIP-ViT, BLIP2, and DINOv2. Under the controlled setting, the measured mIoU changes substantially: DINOv2 obtains 30.55%, BLIP2 obtains 29.49%, CLIP-ViT obtains 24.33%, and CLIP-ResNet obtains 17.41%. The stronger encoders also exceed the original EmbodiedScan ResNet-50 baseline without modifying the downstream 3D fusion pipeline. Class-level results give a more detailed picture: DINOv2 is stronger on many layout and structural categories, whereas BLIP2 remains close on several object-centered classes. CLIP-ViT improves clearly over CLIP-ResNet, showing that the way CLIP features are exposed as dense tokens matters for voxel lifting. These results indicate that the image backbone is not a secondary engineering detail in embodied semantic occupancy, but a major source of variation in the final 3D prediction.

Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance. At its core, RegRet integrates a Region-Aware Encoder to capture detailed regional features while balancing them with the global background context. To further enhance the fine-grained understanding and discriminability of representations, we design a multi-stage training pipeline that includes detailed localized captioning and regional contrastive learning tasks. In addition, considering the absence of region-level contrastive training data and the limited diversity of evaluation tasks in current benchmarks, we introduce the REGMB benchmark. It comprises 225k contrastive pairs, covering four multimodal retrieval tasks. Extensive experiments validate the effectiveness of our approach. RegRet outperforms strong baselines in the zero-shot setting. Further training with contrastive learning leads to an average improvement of more than 20% on both REGMB and public benchmarks, while achieving comparable or better results on global-level retrieval tasks.

Masked reconstruction is widely used for EEG foundation models, but optimizing reconstruction on low-SNR waveforms does not necessarily produce the most useful latent representation. We introduce MANAS-2, a new EEG foundation model that combines a Raw-Band Hybrid (RBH) masked autoencoder with Constrained Reconstruction (ConRec), a physics-motivated regularizer. RBH jointly reconstructs temporal waveform patches and compact spectral-band targets, while ConRec acts only on the temporal decoder output, penalizing differences in RMS energy between adjacent short windows of the reconstructed waveform. ConRec is intended to shape the encoder by biasing it toward the organization of oscillatory-envelope information. Across seven held-out EEG datasets, adding ConRec to an otherwise identical RBH model increases frozen ridge recovery of six-band spectral power from mean R^2=0.860 to 0.906 and recovery of inter-patch band-energy dynamics from R^2=0.283 to 0.354, while temporal waveform information remains highly recoverable from the frozen latents. Applied to a temporal-only masked autoencoder, ConRec also improves frozen downstream transfer and frequency-dependent latent geometry despite receiving no spectral targets: i.e., the effects of ConRec are architecture-independent. MANAS-2 also outperforms leading EEG Foundation Models on most downstream knowledge-transfer tasks. From the effects of ConRec, we see that a physically motivated constraint imposed through the decoder can make for a more spectrally organized and transferable latent space. MANAS-2 therefore provides a new EEG foundation model built around constrained reconstruction as a mechanism for shaping representation--rather than reconstruction--quality.

Auditory attention decoding (AAD) identifies the attended speaker from physiological signals, supporting neuro-steered hearing devices and natural human-machine interaction. Electroencephalography (EEG) is the dominant modality for AAD but provides incomplete evidence in naturalistic audio-visual scenes, motivating EEG and electrooculography (EOG) fusion. Existing approaches remain limited by weak cross-modal interaction, inefficient temporal modeling, and low robustness to sample variations. To address the limitations, we propose RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for AAD. RAMamba-Net employs a Mamba-enhanced band-aware convolutional Transformer to capture band-specific EEG patterns and long-range temporal dynamics. A dual-branch temporal-spatial encoder models EOG temporal and inter-channel dependencies. Cross-modal attention enables explicit modality interaction. Then, a reliability-aware module is introduced to estimate sample-wise modality weights for feature and prediction consistency, thereby enhancing multimodal fusion. Experiments on two AAD benchmarks demonstrate that RAMamba-Net effectively exploits complementary EEG-EOG information, yielding accuracy gains of 5.76% over unimodal baselines, together with more robust decoding and discriminative representations. Further analyses show that explicit cross-modal interaction improves multimodal alignment, while the reliability-aware module suppresses unreliable modality evidence and is robust to signal perturbation and parameter variation.

Accurate long-term trajectory prediction for maritime vessels is essential for safety and logistical efficiency. While deep learning models, particularly Transformers, have shown promise in processing Automatic Identification System (AIS) data, they often struggle with the quadratic computational complexity of self-attention and the loss of accuracy over extended forecasting horizons. This study proposes TempTPI, a novel prediction framework that integrates an Informer-based encoder with a multi-channel temporal encoding mechanism. The Informer architecture leverages a ProbSparse self-attention mechanism to reduce computational overhead and focus on the most significant dependencies, while the temporal encoder utilizes Fourier-like frequency expansions to capture cyclic patterns (hourly, daily, and seasonal) in vessel behavior. We evaluate our model against the state-of-the-art TPTrans architecture using AIS data from Danish waters. Experimental results demonstrate that TempTPI consistently outperforms existing methods across prediction windows of 1 to 5 hours. Notably, at a 5-hour horizon, the proposed model achieves a 55% improvement in Mean Squared Error (MSE), offering a robust solution for long-range maritime situational awareness.

SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observations. Existing latent diffusion approaches typically inherit a predetermined autoencoder, although reconstruction fidelity can vary substantially across codecs and modalities. Because the latent codec affects the round-trip preservation of both SAR conditions and EO targets, codec selection constitutes a fundamental design choice; nevertheless, existing methods largely rely on codecs pretrained on natural images. To remedy this, we introduce ReFlowSET, a conditional latent flow-matching framework that selects its codec through a joint SAR--EO reconstruction audit. Rather than inheriting a heavyweight pretrained generator, ReFlowSET trains a substantially smaller conditional DiT from scratch in the selected latent space, using dual-stream SAR conditioning followed by joint feature refinement. To provide semantic guidance for this from-scratch training, intermediate noisy-EO features are aligned with clean target-EO representations extracted by a frozen vision foundation model. This alignment is used only during training and introduces no additional inference cost. Experiments on QXS-SAROPT and SAR2Opt demonstrate state-of-the-art performance across diverse perceptual fidelity and distributional metrics. Code and pretrained weights are publicly available at https://github.com/KAIST-VICLab/ReFlowSET.

We present \textbf{DreamX-Phi 1.0}, an action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations. Yet realism alone does not guarantee faithfulness: a convincing rollout can still move the wrong arm or lose the manipulated object. To ensure the prediction respects each arm's commanded path, we inject per-arm $\mathrm{SE}(3)$ transformations into attention via \textbf{PRoPE-style geometric encoding}, preserving arm identity and rigid-motion structure. Action control alone does not fully constrain scene geometry or the evolution of small manipulated objects. We therefore add a lightweight \textbf{depth branch} for scene-level geometry and use \textbf{SAM3 masks} with a frozen \textbf{V-JEPA teacher} to maintain object consistency throughout grasping. We further distill the multi-step generator into a few-step student via distribution-matching distillation for efficient deployment. At the time of writing, \model{} achieves first place on Track1 and second place on Track2 of the WorldArena~2.0 Challenge. Our model and code will be publicly available.

Human-to-robot (H2R) object handover is a fundamental capability for human-robot collaboration, yet progress is hindered by the scarcity of large-scale, human-centric datasets and the significant sim-to-real gap. To address these challenges, we introduce Hand2Bot, an RGB-D video dataset that provides rich contextual information such as body posture and facial expressions, specifically collected for handover scenarios with real-world noise patterns. We further propose PassGen, a generative pipeline that leverages stable video diffusion and an Intention-Aware Temporal Face Encoder to synthesize realistic handover sequences while ensuring hand-object consistency. To bridge the sim-to-real gap, we implement a morphology-based depth editing strategy that replicates realistic sensor noise found in physical depth maps. Experimental evaluations demonstrate that our framework achieves high intention identification accuracy and low false trigger rates in both ablation studies and real-world deployment on a physical robot platform. Our results confirm that training on PassGen allows for robust zero-shot transfer and earlier intention anticipation compared to traditional hand-centric baselines, effectively enabling socially aware robotic behavior in shared workspaces.

Heterogeneous RF sensing differs substantially in feature structure, spatial layout, and temporal scale, making existing models difficult to reuse across devices, environments, and RF modalities. We propose FSTC-Encoder, which unifies heterogeneous RF representation learning through feature, spatial, and temporal correlation modeling. Structure-aware feature encoding accommodates different signal structures, set-based spatial encoding aggregates variable observations, and hierarchical temporal encoding jointly captures local variations and long-range dependencies. Across sensing tasks and modalities, FSTC-Encoder retains the same spatial--temporal backbone architecture while varying only the feature configuration and task head. Across Widar3.0, CSI-Bench, and XRF55, FSTC-Encoder achieves 92.15% mean Accuracy under multi-factor cross-domain protocols, ranks first on three of four additional sensing tasks, remains consistently strong across WiFi, millimeter-wave radar, and RFID, and reduces the cross-modality performance gap from 18.85% to 12.93% through cross-RF learning. These results demonstrate that FSTC-Encoder achieves high domain robustness, task generality, and modality extensibility.

Self-supervised 3D medical foundation models are increasingly used as general-purpose feature extractors, yet their sensitivity to MRI artifacts remains poorly understood. We present a controlled evaluation of representation robustness across five pretrained 3D encoders spanning different architectures, objectives, pretraining domains, and dataset scales. Using BraTS-Africa cases with four MRI sequences, we generate seven frequency- and image-domain artifacts at five predefined corruption settings. Robustness is assessed using linear centered kernel alignment (CKA), RankMe, and UMAP, complemented by an independent segmentation-consistency analysis. We find that robustness is strongly model- and artifact-dependent. 3DINO exhibits the most consistently stable representations, while BrainIAC is highly sensitive to several corruptions; NeuroVFM, BrainFM, and Neuro-SimCLR show intermediate but distinct artifact-specific profiles. Across many conditions, CKA decreases substantially while RankMe remains comparatively stable, indicating that artifacts often distort representation geometry without causing dimensional collapse. Segmentation consistency also degrades under corruption, particularly for ghosting and Rician noise, but aligns only partially with representation-level robustness. These findings show that larger-scale or domain-specific pretraining alone does not guarantee artifact invariance and motivate explicit robustness evaluation before deploying 3D foundation models in heterogeneous MRI settings.

Large language model agents need to perceive human behavior in physical environments. Millimeter-wave (mmWave) radar provides a privacy-friendly and contactless sensing modality, but radar observations are difficult to align with language. Existing radar-language methods often rely on synthetic data or lack explicit supervision for human body structure and motion. We present mmMind, a radar-language model that uses synchronized 3D pose as training-only supervision. A spatio-temporal radar encoder is pretrained to capture body configuration and motion dynamics, after which the pose head is removed so that inference requires radar alone. The learned radar representations are then aligned with an LLM for behavior captioning and spatio-temporal question answering. We also introduce mmMind-Bench, a real-world mmWave-language benchmark containing 17.9 hours of recordings from 23 participants across seven indoor environments. Experiments on captioning, question answering, and unseen-action generalization show that mmMind consistently outperforms existing radar-language baselines, while ablations confirm the importance of pose-guided pretraining.

Recent advances in proposal-free Video Moment Retrieval (VMR) have highlighted the effectiveness of Static Scene Graphs (SSGs). By modeling objects and their relations at the frame level, SSGs enrich retrieval-oriented video representations. However, integrating SSGs into VMR remains constrained by two inherent limitations: (1) Lack of Temporal Dynamics. SSGs fail to model how objects and their relationships evolve over time, leading to the loss of essential temporal dependencies in video representation; and (2) Lack of Explicit Temporal Span Encoding. SSGs do not explicitly encode the duration of relationships, making precise localization challenging. To address these limitations, we propose Temporal Bipartite Scene Graph Network (TBSG-Net)---to the best of our knowledge, the first Dynamic Scene Graph (DSG) based proposal-free VMR model. Specifically, TBSG-Net leverages DSGs to extract event-centric graph representations of the input video, enabling the modeling of object interactions over time and thus addressing limitation (1). These DSGs are then processed by a novel Dynamic Scene Graph Embedding (DSG-E) module to capture both Temporal Span and spatio-temporal information. First, DSG-E utilizes a TBSG Constructor to transform DSGs into TBSGs, explicitly encoding objects, relationships, and time spans to tackle limitation (2). Second, the resultant TBSGs are passed into a hybrid TBSG Encoder that integrates a Transformer variant for global event modeling and a Graph Convolutional Network for detailed relational reasoning, ultimately producing a more comprehensive spatio-temporal representation. Our experiments demonstrate substantial improvements of TBSG-Net over all baselines.

Automated Sign Language Recognition for under-represented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this gap: the only available bench-mark, CASL-W60, has a best reported accuracy of 69.93%, and we show that the common heuristic of fine-tuning high-resource models fails to close it. This failure stems from two compounding factors: the limited scale of available CASL data and the significant lexical and visual domain gap between CASL and large-scale corpora such as WLASL, which renders pre-trained representations largely uninformative. To address this, we propose TransSLR, a lightweight Temporal Transformer Encoder trained from scratch on 64-frame normalized pose sequences, with average pooling and a classification head. By operating on geometric keypoint representations rather than raw RGB, TransSLR achieves signer-independent generalization without relying on visual appearance. On the CASL-W60 benchmark, TransSLR establishes a new state-of-the-art accuracy of 80.39%, surpassing the prior best by +10.46%. Beyond accuracy, our encoder-only design significantly reduces computational overhead, making deployment feasible in resource-constrained environments. We conduct extensive experiments on the CASL-W60 benchmark, comparing against RGB-based and multimodal baselines, and demonstrate that TransSLR achieves state-of-the-art performance.

Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning. Most existing solutions introduce extra 3D prior inputs or external spatial encoders, which increase complexity and degrade the underlying VLMs' general-purpose capabilities after spatial fine-tuning. To this end, we propose a parameter-efficient \textit{\textbf{Spatio}-vision \textbf{L}anguage \textbf{M}odels (SpatioLM)}, that enhances spatial intelligence without extra 3D prior inputs or third-party spatial encoders. Concretely, we design a plug-and-play and non-invasive spatio-vision module that elicits the spatial knowledge inherent in VLMs. Furthermore, we innovatively leverage pseudo depth and camera information as supervision to guide the model in learning physically coherent representations. Extensive experiments show that SpatioLM achieves significant improvements in diverse tasks, including spatial perception and understanding while effectively limiting the degradation of general capabilities. Notably, the model achieves an impressive score of 71.6 on the VSI-Bench (the first model to surpass 70). In addition, it attains competitive performance when transferred to embodied manipulation tasks. Code is available at \href{https://github.com/xiaomi-research/spatio-lm}{\faGithub~spatio-lm}.

Model-based active flow control requires predictive models that are accurate, stable, and fast enough for real-time optimisation. In controlled wake flows, this is often achieved through Reduced-Order Models (ROMs) that first compress high-dimensional velocity snapshots into a latent space and then learn a time- stepping predictor for the dynamics in the latent space. Here, we study how the choice of the spatial encoder affects the predictability of the resulting latent coordinates for wake flows under control inputs. Using two actuated 2D wake configurations, a simplified truck wake and the fluidic pinball, we compare Proper Orthogonal Decomposition (POD) against nonlinear Convolutional Autoencoders (CAEs) and two types of variational autoencoders for compression, and evaluate several temporal predictors based on Long Short-Term Memory networks. CAEs achieve higher compression efficiency and sharper short-term reconstructions, but they produce latent dynamics that are more irregular and with broadband spectral content. As a consequence, long-horizon forecasts degrade faster and show a higher probability of catastrophic divergence than POD-based models. POD yields smoother latent trajectories that are easier to learn and extrapolate, leading to more reliable predictions beyond the short- term regime. These results reveal a clear trade-off between compactness and forecast accuracy, and suggest that the stability of the latent dynamics prediction can outweigh maximal compression. This is particularly relevant for control strategies rooted in forecasts of the dynamics, such as model predictive control and reinforcement learning. The findings provide practical guidance for designing actuation-aware, hardware-feasible predictive ROMs for real-time flow control.

Millimeter-wave (mmWave) radar enables privacy-preserving and illumination-robust human motion reconstruction, but training generalizable models typically requires costly paired radar-motion recordings. Simulation can scale such supervision, yet even physics-based simulators cannot fully reproduce real-world multipath, clutter, hardware-specific response statistics, or distance-dependent resolution degradation, leaving a sim-to-real gap. We present mmSimPrior, a simulation-pretrained framework that factorizes transferable knowledge into signal, motion, and radar-to-motion mapping priors. To learn transferable signal and motion priors, we pretrain a multimodal radar encoder with a physics-informed domain-randomization curriculum designed to mitigate the sim-to-real gap by approximating real-world propagation- and acquisition-level variations, while a joint-temporal tokenizer learns a discrete prior over plausible human motion. A dual-mode mapping module predicts either motion-code distributions for structurally constrained zero-shot reconstruction or continuous motion parameters for flexible adaptation from limited real data. We further construct a 4.2M-frame, 31K-sequence dataset suite and introduce a No-Overlap Setting that prevents any exact subject-environment-location-motion tuple from appearing in both the adaptation and test sets. Experiments on mmSimPrior-Real and RT-Pose demonstrate consistent gains: with only 24 paired real sequences, mmSimPrior-Reg reduces MPJPE by 24.7-39.0% over the strongest baseline across the three environments, while mmSimPrior-Cls reduces zero-shot MPJPE by 8.5% without fine-tuning.

Remote sensing offers an unparalleled vantage point for observing the Earth's long-term surface evolution, yet it demands that a model not only perceive land cover at isolated moments, but also track changes, memorize evolution histories, and reason across time and space. However, existing studies lack a systematic evaluation that dissects these distinct competencies. To fill this gap, we introduce ChronoBench, a multidimensional benchmark that decomposes this task into four progressive cognitive levels (i.e., Land Cover Perception, Temporal Recognition, Long-Term Memory, and Spatio-Temporal Reasoning). The ChronoBench comprises 12 sub-tasks and 17,689 rigorously validated QA (Question-Answer) pairs. Extensive evaluations reveal that mainstream MLLMs fall drastically behind human experts, with Long-Term Memory emerging as the most critical bottleneck. Motivated by this finding, we further propose GeoChrono, an MLLM with enhanced capabilities for tracing, memorizing, and reasoning about long-term geographic evolution. Leveraging the physical prior that geographic parcels remain spatially fixed while their semantics evolve, we design a Temporal Trajectory Encoder~(TempEnc) that constructs per-location temporal trajectories for dedicated land cover evolution modeling, and we introduce a Coarse-to-Fine Token Compressor~(C2FComp) that adaptively preserves dynamic regions while compressing the static background. To support training, we also construct ChronoInstruct, a 104K-sample instruction-tuning dataset spanning all competency levels for training. GeoChrono achieves state-of-the-art performance on ChronoBench, surpassing the leading commercial MLLMs by over 20%, while C2FComp reduces visual tokens by over 56% while retaining GeoChrono's 94.6% performance. The code and data will be available at https://github.com/IntelliSensing/GeoChrono

Pediatric electronic health records capture developmentally structured clinical trajectories, yet their potential for generative healthcare foundation models remains largely unexplored. Here we present TEDDY (Temporal Event Decoder for Disease in Youth), a 1.84-million-parameter decoder transformer trained on approximately 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY models longitudinal diagnosis trajectories and visit timing. Predictions were made before visit codes were revealed, limited to first occurrences, and evaluated against sex- and age-matched controls. Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%, outperforming same-data DenseNet (50.0%), CNN (57.2%), RNN (60.1%), and LSTM (62.7%) baselines on 96-99% of tasks. Performance held across sex and age and was strongest among lower-prevalence diagnoses; 202 of the 225 rarest conditions (90%) had 95% confidence intervals above chance. Predictive signal remained detectable more than two years before first recorded diagnosis, with median AUCs of 59.7% in the unrestricted analysis and 64.4% in a fixed-cohort sensitivity analysis. In asthma and attention-deficit/hyperactivity disorder benchmarks, AUCs were 79.3% and 84.7%, compared with 62.7% and 71.7% for the strongest comparators, including a general-purpose language model three orders of magnitude larger. Visit-timing predictions had a 3.0-day mean absolute restricted mean survival-time error over 365 days, although median and long-tail return intervals remained miscalibrated. Together, these results establish pediatric diagnostic histories as a substrate for compact generative models supporting broad, rare-disease, and long-horizon risk forecasting without population-scale data or billion-parameter models.

Interfacing with Biological Neural Networks (BNNs) requires encoding information into stimulation patterns that can be effectively processed and that enable the underlying system to adapt. Nevertheless, the role of stimulation encoding remains poorly understood. In this work, we compare multiple encoding strategies, including rate-based, phase-based, burst-based, and time-to-first-spike temporal encodings, in a closed-loop neural classification task using cultured BNNs. We encode visual inputs as spatiotemporal stimulation patterns delivered via a Multi-Electrode Array (MEA) and evaluate classification performance for each encoding scheme. We find that burst-based temporal encoding yields the highest observed performance, achieving up to 95.6 % accuracy in a binary classification task, compared to substantially lower performance from rate- and phase-based approaches. We further show that performance is highly sensitive to the spatial distribution of stimulation, with suboptimal electrode selection significantly degrading accuracy. These findings indicate that effective interfacing with biological neural systems requires the joint optimization of temporal and spatial encoding strategies, and highlight temporal encoding as a key design dimension for bio-digital computing.

Recent advances in humanoid robotics have highlighted the importance of deployable loco-manipulation skills. Dribbling a soccer ball while evading active opponents requires simultaneous balance, precise ball control, and awareness of a dynamic adversary under onboard sensing and real-time constraints. Existing approaches typically separate perception and motion, which can be effective in controlled settings but may fail under occlusions, fast ball movements, and complex opponent interactions, since perception is not directly optimized for control. We propose an integrated approach in which a temporal depth encoder is embedded into a reinforcement learning policy through a task-specific projection layer. We apply this framework to a simulated Booster T1 humanoid robot and show that it is possible to learn vision-based, opponent-aware dribbling directly from depth observations, without explicit state estimation or privileged scene information. The learned policy achieves 100% success in nominal target-driven dribbling and 96% success with a single static obstacle, while reaching 46% success against an actively moving ball-attacker opponent. These results demonstrate that the proposed framework supports robust vision-based dribbling in nominal and moderately dynamic settings, and provides a strong foundation for handling more challenging moving-adversary scenarios.

We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state trajectories of four open-weight transformer language models spanning four post-training regimes: no training (Gemma-4-E4B base), multimodal RLHF (Gemma-4-E4B-it), RL distillation (DeepSeek-R1-Distill-Qwen-7B), and SFT (Qwen2.5-7B-Instruct). Three prompt conditions (an identity-specifying axis prompt, a length-matched generic-assistant prompt, and a 26-token vanilla baseline) are compared via five geometric metrics, principally the 1-Wasserstein distance between edge-wise distributions of Ollivier-Ricci curvature on k-NN trajectory graphs. Claims rest on trajectory-level permutation tests with multiple geometric controls (teacher-forced content controls, temporal-chain vs k-NN topology, ABT-projected k-NN, angular vs Euclidean graph construction, B=5000 permutations on borderline statistics). The central finding is a qualitative reorganization of identity encoding across the instruction-tuning boundary: in the base model the fingerprint is direction-coded (separation 0.034, p=0.002 under angular k-NN); in the multimodal instruction-tuned model it migrates into the magnitude (angular separation collapses to p=0.439 while Euclidean survives at p=0.042, and the mean norm of the first generated state inverts its length-ordering, being lowest for the identity prompt). This direction-to-magnitude reorganization is specific to the multimodal instruction-tuning regime, absent under RL distillation and SFT. A teacher-forced control attributes ~30% of the free-running cosine signal to prompt-driven effects. We position W_1 on edge-wise Ollivier-Ricci distributions on k-NN trajectory graphs as a methodological contribution of independent interest.

Accurate forecasting of cellular network traffic is essential for network planning, resource allocation, and quality-of-service assurance in modern mobile communication systems. Real-world traffic often exhibits bursty endogenous dynamics and disturbances triggered by external urban events, which makes reliable prediction highly challenging. Most existing spatiotemporal traffic forecasting methods primarily focus on intrinsic traffic patterns or structural relationships within a single modality, and rarely model burst behavior together with exogenous contextual signals. To address this issue, we propose \textbf{MSPF-Net}, a multimodal cellular traffic forecasting framework that integrates external contextual information. Specifically, MSPF-Net consists of a Spatiotemporal-Frequency Traffic Encoder for capturing temporal, spatial, and spectral traffic patterns, a Peak Enhancement Module for extracting burst-aware representations of sudden spikes, a News Context Representation Module for encoding urban news streams into exogenous contextual embeddings, and a Dynamic Fusion Prediction Module for adaptively integrating these heterogeneous signals to generate forecasts. Experiments on the Milano, Trento, and LTE traffic datasets demonstrate that jointly modeling traffic dynamics, burst patterns, and news contextual signals can effectively improve forecasting performance.

Self-supervised learning (SSL) shows strong potential for cross-dataset transfer by improving feature representation and generalization. However, its application to EEG-based emotion recognition remains largely unexplored. Existing SSL methods struggle to capture the intricate spatiotemporal dependencies of EEG signals under varying channel configurations, extract fine-grained representations resilient to noise, and derive global features that generalize well across subjects. To address these challenges, we propose Masked Generative-Contrastive Representation Learning (MGCRL), a novel SSL framework specifically designed for EEG-based emotion recognition. Built upon a region-aware spatiotemporal encoder, MGCRL integrates generative and contrastive learning to achieve both fine-grained and global discriminative representations for cross-dataset generalization. MGCRL introduces three key designs: 1) a spatiotemporal encoder that incorporates region-based graph convolution to capture localized spatial and functional relationships, enhancing region-specific feature learning and mitigating the impact of varying EEG channel configurations across datasets; 2) a generative learning mechanism based on the joint embedding predictive architecture (JEPA) that utilizes masked features to capture noise robustness fine-grained representations, improving the model's capability to characterize subtle emotional states; and 3) a contrastive learning strategy that leverages masked and original features to learn temporally stable and cross-subject-invariant representations across the same stimuli, boosting emotion discrimination and cross-subject generalization. Under these designs, MGCRL exhibits remarkable ability to learn universal representation. Extensive experiments involving pretraining on the large FACED dataset and fine-tuning on multiple SEED-series datasets demonstrate the effectiveness of MGCRL.

Reconstructing 4D animals from monocular videos is challenging due to large inter-species variation, complex articulations, and the lack of reliable templates. Existing approaches typically rely on either strict category-specific priors that restrict generalization, or unconstrained generative models that sacrifice input fidelity. To bridge this gap, we present a progressive test-time optimization framework built on 3D Gaussian Splatting for high-fidelity 4D animal reconstruction from a single video. Our key insight is that a coarse shape prior suffices when coupled with a progressive strategy that disentangles articulated pose from non-rigid deformation. Specifically, we employ a symmetry-aware temporal encoding that exploits bilateral cues while absorbing camera estimation drift and a part-conditioned deformation mechanism guided by learnable part anchors and a learnable skinning field. Extensive experiments demonstrate that our approach generalizes robustly across diverse species, achieving superior geometric accuracy, temporal consistency, and visual fidelity compared to existing baselines, even under severe prior mismatch.

Geolocation encoders, which map geographic coordinates to learned representations, are emerging as an effective means of capturing visual and non-visual characteristics from a latitude-longitude pair alone. However, existing approaches project coordinates onto fixed bases (e.g., spherical harmonics), allocating representational capacity uniformly and devoting equal resources to the open ocean and to a developing city. We introduce Tessellating the Earth (TTE), a location encoder built from learnable Spherical Voronoi partitions that concentrates representational capacity where it is needed in a fully differentiable, end-to-end manner. Each Voronoi site carries its own embedding and migrates during training toward discriminative areas. To bridge the gap between local spatial structure and global semantic understanding, we introduce \emph{global semantic tokens}: a set of shared learnable concept tokens that distill semantic knowledge from the satellite imagery into a compact vocabulary the location encoder can reference at inference, enabling geographically distant sites covering similar environments to share semantics. TTE sets a new state of the art for location encoders across a suite of geospatial classification and regression tasks, and achieves the strongest results when used as a geographic prior for fine-grained species classification on iNaturalist-2018. Code, and weights are available at https://github.com/mvrl/TTE.

Location encoders transform geographic coordinates into high dimensional embeddings for downstream machine learning, but it is unclear how well these representations capture interpretable spatial effects. We benchmark whether GeoShapley, a game-theoretic explainer that treats all location features as a single joint player, can recover spatially varying coefficients from models built on location-encoder embeddings. Eleven encoders from the TorchSpatial framework are evaluated against a synthetic process with known coefficients, across three scales (grid, county, global), with and without raw coordinates alongside the embedding, and under untrained and contrastively trained conditions. Measuring recovery as the correlation between estimated and true coefficients, we report how it varies with scale and encoder architecture and compare the embeddings against a raw-coordinate baseline. Recovery of the primary coefficient is consistently high across encoders, whereas recovery of a secondary coefficient is more scale-dependent, differing most at the global scale; the raw-coordinate baseline remains competitive throughout.

Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision. However, existing approaches typically either rely directly on explicit 3D inputs (e.g., point clouds or RGB-D sequences), or introduce an additional 3D geometry encoder to derive 3D-aware visual tokens from 2D images. Such designs structurally decouple 3D geometric perception from the rich 2D semantics learned via vision-language pre-training, hindering the development of a unified 3D vision-language representation. In this work, we propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder. Specifically, Occ-VLM reconstructs 3D scene occupancy as an auxiliary geometric prior, which is utilized to spatially associate foreground 2D tokens with 3D space. These tokens are then decoded by a Large Language Model (LLM) for unified scene understanding. Extensive experiments demonstrate that Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning: it attains state-of-the-art performance on multi-view occupancy prediction, while performing on par with 3D-input VLMs on 3D Visual Question Answering (VQA) and 3D dense captioning benchmarks.

Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning. Instead, OneCanvas aggregates patch features from all views onto a single equirectangular panoramic canvas. Namely, each patch is unprojected to a 3D world coordinate using its depth and camera pose, then placed on the canvas at the continuous longitude and latitude of that point as seen from the canvas origin, with no rasterization or aggregation across overlapping views. A 3D position embedding of the patch's metric coordinates is added to its feature, restoring the depth lost when collapsing the world position to an angular canvas coordinate. Patches from all frames thus share one spatial coordinate system with no fusion or major architectural modifications of the backbone. The pretrained VLM consumes this representation as if it were an ordinary image. Because the canvas can be centered on any pose of interest, the same representation directly supports situated reasoning from a specific viewpoint, a common requirement in robotics and embodied AI. Thanks to this representation, we can also introduce a spatial pretraining curriculum: by procedurally placing patch features of objects, drawn from real images, at chosen 3D world positions on an otherwise empty canvas, we generate on-the-fly supervision spanning a broad range of spatial reasoning tasks, with answer distributions controlled to reduce spatial reasoning shortcuts. OneCanvas achieves state-of-the-art accuracy on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using an order of magnitude less training compute than the strongest competing methods.

Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights. However, current architectures do not inherently provide such information. Specifically, guidance is needed on how current conditions must be modified to shift from a predicted outcome to a desired future scenario. Counterfactual explanations provide a natural framework for this task, as they represent minimal input changes that alter the model's prediction, indicating when and how intervention is required. Existing approaches rely on instance-wise optimization, leading to inconsistency across instances, high computational costs, and limited applicability in real-time settings. To address these limitations, we reformulate counterfactual generation for time series forecasting as the problem of learning a globally consistent intervention strategy, allowing counterfactuals to be generated through a single shared function. We propose Counterfactual Time Series Explanations (ConTex), a model-agnostic, decomposed architecture comprising a temporal context encoder and a conditional encoder, followed by two heads that capture interventions in terms of temporal relevance and modification strength. This structure overcomes the instability and inconsistency of instance-based approaches by producing targeted, interpretable interventions across time and feature dimensions in a single forward pass, making it suitable for real-time applications. Across multiple forecasting architectures and benchmark datasets, ConTex achieves state-of-the-art validity while generating sparse counterfactuals that minimize the number of necessary interventions. Additionally, our approach reduces computational cost by at least 12-36x compared to instance-wise generation and supports real-time inference at approximately 0.007 seconds.

The ability to react dynamically to tactile signals has long been considered crucial to agile human-level dexterity. Yet contemporary learning-based Vision-Language-Action (VLA) models for robotic manipulation generally either overlook the tactile modality or are limited to encoders with static cues, due in part to the scarcity of diverse training data and standardized evaluation, architectural constraints in current VLA models, and limitations of static tactile encoders. In this paper, we push the frontier of tactile-reactive manipulation by addressing all of these limitations. We propose a large-scale, 100-hour tactile-rich dataset collected via a novel, data-efficient recipe that prioritizes elementary motor primitives. To effectively exploit naturally high-frequency touch signals without sacrificing the existing capabilities of existing VLAs, we introduce a variable-rate Mixture-of-Transformers (MoT) architecture equipped with a novel temporal tactile VQ-VAE encoder. We demonstrate the effectiveness of tactile-reactive policies on 12 manipulation tasks requiring delicate force control and deformable object manipulation, achieving over 30% higher average success rate than the strongest baseline.

3D Gaussian Splatting (3DGS) has shown strong potential for high-fidelity talking head synthesis. However, enabling fine-grained, interpretable, and editable facial expression control remains fundamentally challenging due to intrinsic conflicts between speech-driven facial dynamics and explicit expression signals. Existing methods rely on implicit multimodal fusion, leading to spatial entanglement and temporal instability. We present EmoZone-Talker, a novel framework that reformulates audio-driven facial animation as a structured spatial-temporal coordination problem under cross-modal conflicts. Our approach introduces an explicit spatial disentanglement and temporal dynamics modeling of facial motion. Specifically, we propose Synergy Zones with Prioritized Attention Bias (SZ-PAB) to explicitly decouple modality contributions via region-wise constraints guided by anatomical priors, and a Channel-Independent Temporal AU Encoder (CIT-AE) to model temporally coherent AU dynamics. By integrating these representations into 3D Gaussian deformation, EmoZone-Talker enables precise and interpretable control over facial expressions. Extensive experiments demonstrate that our method improves expression controllability and realism, with notable gains in upper-face accuracy and temporal coherence, while preserving high rendering quality and accurate lip synchronization. Code will be publicly released to facilitate reproducibility and further research.

Tactile imaging seeks to reconstruct the internal structure of soft objects through touch sensing, with applications in medical diagnosis and robotic manipulation. Recent self-supervised learning approaches have shown promising results, but rely on global, unstructured representations and robot-controlled sensing, limiting generalization and practical use. We propose Local Encoder for Spatial Sensing (LESS), an object-centric tactile representation that exploits the local nature of touch. The tactile scene is modeled as a grid of recurrent encoders with local receptive fields, whose states are fused to reconstruct 2D or 3D images of internal structure. This compositional design enables strong generalization: models trained on single-inclusion phantoms accurately image objects with multiple inclusions and varying sizes. The local structure further supports spatial uncertainty estimation. In addition, we enable hand-held tactile imaging via external pose tracking and human-like palpation data, and extend tactile imaging to full 3D reconstruction.

Explicit 3D representations are attractive for manipulation because they expose object shape, workspace geometry, and robot-object relations in metric coordinates. However, sparse 3D encoders are often learned through downstream task objectives, tying the representation to a particular data distribution, policy architecture, and action parameterization. We introduce Sparse2Act, an observation-action alignment framework for pretraining sparse point-cloud encoders. The key idea is to use task-space end-effector actions as geometric supervision: masked sparse 3D tokens are trained to organize scene features around the workspace motion paired with the observation. After pretraining, only the encoder initialization is reused by downstream policies, allowing them to retain their own architectures and action spaces, including joint-space commands. On the LIBERO-10 benchmark, our method achieves 86.9% average success after 500 fine-tuning steps. The same pretrained encoder supports LIBERO-to-Meta-World cross-domain transfer, achieving 73.4% average success on the Meta-World-5 benchmark. Ablations on the objective and decoder capacity show that the gains come from the masked action-alignment signal and remain useful across downstream action decoders. In real-world experiments, simulation pretraining followed by limited real-data fine-tuning achieves an average success rate of 72.5% across four tasks, demonstrating effective sim-to-real transfer. These results suggest that robot actions can provide compact geometric supervision for reusable sparse 3D representations.

We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal correspondences. This geometry-only setting is challenging due to missing observations and ambiguous dynamics. While recent progress has largely relied on image-based methods, existing point-based approaches typically focus on single objects, assume relatively complete inputs, or require explicit correspondences. To address these limitations, we propose DynaTok, a point-based framework for correspondence-free 4D reconstruction from partial point cloud sequences without images. DynaTok encodes frames into compact latent tokens, aggregates incomplete observations over time with a Transformer-based spatiotemporal encoder, and decouples geometry and motion through residual tokens in a unified model. A flow-matching decoder then reconstructs complete, temporally consistent 4D point-cloud sequences conditioned on the latent tokens. Experiments on object- and scene-level benchmarks demonstrate improved reconstruction quality and temporal coherence from partial point cloud observations. Project page: https://wrchen530.github.io/dynatok/.

Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are consistently easier to decode than room factors; and sensitivity analysis under controlled perturbations shows heterogeneous responses to source and room variation. These results reveal systematic biases in current pretrained audio representations. SARL is released as an open-source benchmark for reproducible evaluation of spatial audio representations.

Open-set 3D recognition requires models that generalize to rare or unseen categories. Recent approaches address this by distilling language-vision knowledge into 3D encoders, typically relying on heavy 2D ViTs and aligning each point cloud with a single image or caption, thus anchoring representations to partial views. We propose aligning each point cloud with multiple images and textual descriptions to capture a more holistic understanding of 3D objects. To realize this idea, it is essential to design a loss function capable of jointly aligning a 3D instance with multiple matched signals, multi-view images and multiple texts, while separating positive aggregation from negative competition. We introduce such a function, termed the decoupled multi-positive contrastive loss. Our formulation enhances the loss's hardness-aware focus on challenging negatives, avoiding the "spotlight crowding" that occurs when many positives share the same softmax with all the negatives. Complementing this, we present a lightweight text adapter applied only to web captions, reducing the domain gap to curated annotations and enabling effective use of large-scale unsupervised text. Our model demonstrates state-of-the-art open-vocabulary performance on long-tail benchmarks, yielding substantial zero-shot improvements while sustaining high frame rates.

We demonstrate that nonlinear computing can be achieved with a single linear diffractive surface under coherent illumination. We introduce a compact encoder-decoder co-localization (E+D) architecture in which an input-dependent dynamic encoder and a static optimized decoder are integrated within the same phase-only diffractive plane. Following free-space propagation, coherent interference between the encoder and decoder fields, combined with intensity detection, generates programmable nonlinear input-output mappings without requiring nonlinear optical materials or multiple diffractive layers. We prove that the proposed E+D optical processor is a universal approximator for arbitrary real-valued band-limited nonlinear functions and identify the physical factors governing its approximation fidelity, including the decoder degrees-of-freedom, detector aperture, and axial propagation distance. Crucially, we demonstrate that introducing a trained, frozen phase bias to the encoder region systematically enhances functional expressivity, providing robustness against coarse phase quantization on spatial light modulators. Using this framework, we accurately synthesize diverse nonlinear functions, including commonly used neural network activation functions and complex-valued nonlinear functions. Finally, we experimentally validate the proposed approach using a visible-light optical set-up trained through in situ learning, demonstrating the parallel approximation of 9 nonlinear functions in a single optical forward pass. By collapsing nonlinear optical computation into a single diffractive surface, the E+D architecture substantially reduces hardware and alignment complexity while preserving powerful function-approximation capabilities, providing a compact and scalable framework for analog information processing.

This study addresses the partial-to-complete geometry reconstruction of deformable objects (DOs) from point-cloud observations toward precise DO manipulation. Recent DO reconstruction approaches often adopt implicit neural representations (INRs) to model continuous surfaces as well as capture structural variability. However, these methods typically rely on object-specific shape priors that improve training stability and limit generalization. To figure it out, we introduce ParCo-SDF, a two-stage partial-to-complete signed distance field (SDF) reconstruction framework consisting of temporal geometry encoding followed by FiLM-conditioned SDF prediction. The temporal encoder captures structural similarity across DO sequence, enabling prior-free stable training. FiLM-based conditioning preserves reconstruction expressivity while reducing network complexity. We evaluate the proposed method against a state-of-the-art DO surface reconstruction baseline on a rubber band manipulation dataset, demonstrating robust and high-fidelity reconstruction under severe occlusions.

Trajectory prediction methods have demonstrated remarkable capabilities in capturing complex motion patterns. However, existing methods rely on global state assumptions, suffer from insufficient belief inference under partial observability, and lack cognitive behavioral constraints in prediction. These limitations severely compromise both deployment feasibility and physical plausibility in real-world settings. In this work, we propose FEP-Diff, an agent-centric trajectory prediction framework grounded in the Free Energy Principle, aimed at achieving cognitively plausible predictions under realistic constraints. Specifically, a dual-branch spatiotemporal encoder extracts ego-motion dynamics and social interaction cues from local observations. Building upon this, a goal-conditioned belief learner infers multimodal latent belief distributions optimized via a free-energy objective, with a social consistency constraint on the local neighborhood graph to promote cognitive alignment among neighboring agents. Finally, a residual diffusion trajectory generator is conditioned on the learned belief representations with token-level proxy conditioning, producing precise and diverse future predictions. Extensive experiments on five public benchmarks demonstrate that FEP-Diff consistently outperforms state-of-the-art methods under restricted observability. Code: https://anonymous.4open.science/r/FEP-Diff-8876.

Accurate crop yield prediction is crucial for sustainable agriculture and global food security. While existing methods are predominantly developed for single-crop prediction, they often struggle to generalize across diverse crop types, without addressing the unique crop phenological responses that are dynamically modulated by complex weather patterns. In this paper, we propose PhenoYieldNet, a multi-crop yield prediction framework that learns crop-specific phenology by explicitly modeling their responses with temporal drivers. Specifically, we develop a crop-aware temporal decoder consisting of a Crop Phenology Bank (CPB) and a Crop Phenology Attention (CPA) module. The CPB integrates a set of learnable embeddings, which leverage a query to guide the CPA module to learn the most relevant phenology patterns for the specific crop. And the CPA module explicitly captures multi-scale trend and variation components to construct temporal contexts, enabling the model to dynamically adjust the attention across different phenological stages. To learn robust and generalizable features for multi-crop prediction, the encoder is initialized with a pre-trained foundation model, and further adapted via a self-supervised Temporal Contrastive Adaptation strategy to align with agricultural temporal dynamics. Extensive experiments conducted on multi-crop datasets indicate that our proposed method significantly outperforms state-of-the-art methods, exhibiting strong generalization capabilities across different regions and crops.

Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited viewpoint diversity during training, while motion-based detection approaches frequently fail to model fine-grained temporal relationships across consecutive motion windows. This paper introduces a novel two-stage action detection approach designed to improve both view-invariance and global temporal coherence properties. In the first stage, we extract motion features from augmented virtual viewpoints, solely used at training. Then, the second stage introduces a new view-invariant, multi-scale temporal encoder based on selective state-space sequence modelling to aggregate information across viewpoints and time scales. Experiments on PKU-MMD and BABEL benchmarks demonstrate that this approach significantly outperforms state-of-the-art methods in all considered splits. Code and trained models are available at: https://icb-vision-ai.github.io/HydraView-TAD

Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical bottlenecks: temporal non-causality in standard encoders that induces temporal confounding in non-stationary dynamics, and the absence of explicit channel saliency mechanisms that allows noise to contaminate the latent space. To address these challenges, we propose the Causal Attention and Spatio-temporal Encoder Network (CASE-NET), an architecture designed for structural manifold pre-conditioning. CASE-NET synergizes a Causal Temporal Encoder, which enforces physical arrow-of-time constraints via masked self-attention and causal convolutions, with an Adaptive Channel Recalibration module functioning as an information bottleneck to suppress detrimental noise. Comprehensive evaluations across six heterogeneous domains demonstrate that CASE-NET establishes new state-of-the-art benchmarks on four tasks, achieving a peak accuracy of 98.6% on the AWR dataset and superior robustness in non-stationary regimes.

4D automotive radar is indispensable for autonomous driving due to its low cost and robustness, yet its point cloud sparsity challenges 3D object detection. Existing 4D radar-camera fusion methods focus on complex fusion strategies, trading inference speed for marginal gains. This trade-off hinders real-time deployment due to heavy computation on dense feature maps. In contrast, feature extraction from sparse radar points is less time-consuming but remains under-explored. This work uncovers that simply enhancing radar feature extraction can achieve comparable or even higher performance than elaborate fusion modules, while maintaining real-time performance. Based on this finding, we propose RCGDet3D, which centers on radar feature encoding and simplifies multi-modal fusion. Its encoder inherits from the efficient Gaussian Splatting-based Point Gaussian Encoder (PGE) in RadarGaussianDet3D with two key improvements. First, the Ray-centric PGE (R-PGE) predicts Gaussian attributes in ray-aligned coordinate systems before unifying them to Bird's-Eye View (BEV) space, significantly improving geometric consistency and reducing learning difficulty by decoupling the coordinate transformation from representation learning. Second, a Semantic Injection (SI) module incorporates visual cues from images, producing more geometrically accurate and semantically enriched radar features. Experiments on View-of-Delft (VoD) and TJ4DRadSet show that RCGDet3D outperforms state-of-the-art methods in both accuracy and speed, setting a new benchmark for real-time deployment.

Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and maintaining topological consistency. Existing generative models such as GANs, NeRFs, and diffusion architectures often fail to produce editable manifolds directly usable in downstream design workflows. We present Sketch2MinSurf, a hybrid vision-language and geometric optimization framework that integrates vision-language guidance with minimal-surface theory to generate smooth and editable 3D surfaces from hand-drawn sketches. The core of our approach is a spatial-topological encoding that represents geometry as tuples of node coordinates and real/virtual edge skeletons, enabling stable topological control during generation. We further introduce the Sketch2MinSurf Structural Loss (S2MS-Loss), a reward-modulated objective that jointly constrains geometric reconstruction and topological coherence. On a test set of 100 sketches, Sketch2MinSurf achieves a topological similarity score of 0.844, outperforming existing sketch-to-shape baselines. The generated manifolds are directly editable and free from non-manifold artifacts. A public art installation at a university showcases the method's potential for human-intent-driven 3D form generation. The dataset and code are available at https://anonymous.4open.science/r/Sketch2MinSurf/.

Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image foundation models already provide powerful spatial representations. This raises an important question: can competitive video models be built by reusing these spatial representations and pre-training only for temporal reasoning? We take initial steps toward exploring a lightweight training paradigm that freezes a pre-trained image foundation model and trains only a recurrent temporal module to process streaming video. By reusing an image foundation model as a spatial encoder, this approach could significantly reduce the amount of video data and compute required compared to end-to-end video pre-training. In this work, we explore the feasibility of this approach before investing in computing for video pre-training. Our empirical findings across multiple video understanding tasks suggest that strong temporal performance can emerge without large-scale video pre-training, motivating future work on recurrent video foundation models obtained by pre-training a temporal module on top of a frozen image foundation model. Code: https://github.com/tue-mps/towards-video-image-frozen .

Because LiDAR sensors acquire point clouds with a fixed angular resolution, the resulting data can be systematically parameterized and efficiently compressed in the spherical coordinate system. Traditional spherical coordinate-based point cloud compression methods have demonstrated strong rate-distortion (RD) performance, with the predictive geometry coding (PredGeom) method in the geometry-based point cloud compression (G-PCC) standard being a prominent example. Although PredGeom includes an inter-frame prediction mode, it relies on a simple linear model, which limits its ability to capture complex motion patterns and structural dependencies. Meanwhile, existing learning-based compression methods in the spherical domain do not exploit inter-frame correlations to reduce geometry redundancy. To address these limitations, we propose a learning-based inter-frame predictive coding method, termed Inter-LPCM. For azimuth prediction, we employ a delta coding strategy based on the predefined angular resolution. To improve radius compression, we introduce an inter-frame radius predictive (Inter-RP) model that estimates the current point's radius using neighboring points from both the current frame and the registered reference frame. In addition, we design a lightweight attention-based prediction (LAEP) model to predict elevation angles by capturing long-range geometric correlations across different coordinates. For quantization, we propose an RD-optimized method to select quantization steps in the spherical coordinate system. For entropy coding, we design distinct models for each spherical coordinate component. These models are adapted to the statistical priors of each coordinate, enabling more accurate probability estimation. Our source code is publicly available at https://github.com/SDUChangSun/Inter-LPCM

Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic waveform morphology and learn a latent structure that captures cardiac and respiratory physiology. PPG generators trained with adversarial losses can produce plausible waveforms, but provide no inference path from a real signal to a latent representation. Variational autoencoders, on the other hand, map the PPG data to latent codes, although their decoders often blur systolic upstrokes and dampen amplitude and spectral details. Diffusion models improve waveform fidelity, but typically lack an inference path for reconstruction and physiological analysis. We propose VampPrior Latent Diffusion (VAMP-Diff), a jointly trained variational diffusion model that combines a temporal PPG encoder, a conditional one-dimensional diffusion decoder, and VampPrior regularization on a compact pooled latent. The model uses full temporal latent during diffusion reconstruction, giving the decoder access to beat timing and morphology while generating samples from learned VampPrior components instead of a fixed Gaussian prior. We demonstrate on the CapnoBase dataset that VAMP-Diff produces realistic PPG signals, reconstructs sharper physiological waveforms than Gaussian-prior baselines, preserves heart-rate information, maintains respiratory-rate consistency, and is sensitive to waveform corruptions through reconstruction error.

Aim/Introduction: Distance-encoding biomorphic-informational neural network (DEBI-NN) is a recently proposed architecture in which connection weights are defined by the distances between neurons positioned in a Euclidian space. This approach drastically reduces the number of trainable parameters compared to classical neural networks in which weights are directly trained. The training process for DEBI-NN is based on a genetic algorithm (GA), rather than gradient descent (GD) which remains the prevailing optimization algorithm in deep learning. We aim to design and implement a GD learner for DEBI-NN and assess its performance compared to GA. Materials and Methods: We designed a spatial backpropagation scheme tailored to DEBI-NN and carried out a comparison between GD and GA for classification tasks, using a synthetic non-linear "two-moons" dataset, two clinical medical imaging radiomic datasets and a fetal cardiotocography dataset with a sample sizes ranging from n=85 to n=2126. Each optimizer was tuned through targeted hyperparameter searches adapted to each dataset. Results: Across all experiments, GA consistently produced superior decision boundaries and classification performance (Synthetic: 100% vs 83%; DLBCL: 83% vs 78%; HECKTOR: 80% vs 67%; Fetal: 81% vs 66%), whereas GD exhibited instability and failed to fully capture the non-linear patterns inherent to DEBI-NN's spatial encoding. The entangled gradients resulting from neuron interdependencies limit the effectiveness of classical backpropagation. Conclusion: These findings highlight fundamental limitations of gradient-based methods in architectures with highly interdependent spatial parameters and confirm the suitability of evolutionary strategies for training DEBI-NN.

Camera-conditioned video generation requires positional encoding that remains reliable under changes in camera motion, lens configuration, and scene structure. However, existing attention-level camera encodings either provide ray-only camera signals or rely on pinhole camera geometry, limiting their applicability to general camera control under the Unified Camera Model, including wide-angle and fisheye lenses. To address this limitation, we propose Curved Ray Expectation Positional Encoding (CRePE). CRePE represents each image token as a depth-aware positional distribution along its source ray, providing a Unified Camera Model-compatible positional encoding that captures the projected-path geometry induced by wide-angle and fisheye cameras. CRePE is implemented through a Geometric Attention Adapter added to frozen video DiTs, injecting token-wise scene-distance information into selected attention layers and stabilizing it with pseudo supervision from a monocular geometry foundation model. This design leads to more stable camera control and improves several geometry-aware and perceptual-quality metrics, while remaining competitive on video-quality metrics. Controlled positional-encoding ablations show a better overall average rank than a RayRoPE-style endpoint PE baseline, demonstrating the effectiveness of UCM-aware projected-path integration across diverse camera models. Furthermore, by extending the same positional-encoding pathway to external geometry control through Radial MixForcing, CRePE supports external radial-map control for scene-geometry-conditioned generation and source-video motion transfer beyond camera control.

A realistic view of the vehicle's surroundings is generally offered by camera sensors, which is crucial for environmental perception. Affordable radar sensors, on the other hand, are becoming invaluable due to their robustness in variable weather conditions. However, because of their noisy output and reduced classification capability, they work best when combined with other sensor data. Specifically, we address the challenge of multimodal sensor fusion by aligning radar and camera data in a unified domain, prioritizing not only accuracy, but also computational efficiency. Our work leverages the raw range-Doppler (RD) spectrum from radar and front-view camera images as inputs. To enable effective fusion, we employ a variational encoder-decoder architecture that learns the transformation of front-view camera data into the Bird's-Eye View (BEV) polar domain. Concurrently, a radar encoder-decoder learns to recover the angle information from the RD data that produce Range-Azimuth (RA) features. This alignment ensures that both modalities are represented in a compatible domain, facilitating robust and efficient sensor fusion. We evaluated our fusion strategy for vehicle detection and free space segmentation against state-of-the-art methods using the RADIal dataset.

Semantic communication (SC) aims to reduce transmission overhead by conveying task-relevant information rather than raw data. However, existing SC approaches for video largely focus on pixel-level reconstruction or rely on complex spatiotemporal pipelines, leading to excessive bandwidth usage and latency that are unsuitable for low-resource deployments. In this paper, we propose ChronoSC, a task-oriented semantic communication framework for Video Question Answering (VideoQA). ChronoSC introduces Chrono-Color Stacking, a lightweight and lossless projection scheme that encodes temporal video dynamics into a single static image, enabling extreme temporal compression before transmission. This compact semantic representation is transmitted using a lightweight Deep Joint Source-Channel Coding (DeepJSCC) transceiver and explicitly reconstructed at the receiver. Unlike latent-space methods, explicit visual reconstruction enables the direct reuse of pre-trained vision-language models; specifically, a pre-trained BLIP model is employed to infer answers from noisy, reconstructed chrono-images. Experiments on the CLEVRER dataset show that ChronoSC achieves up to 192 times bandwidth reduction compared to raw video transmission while maintaining high VideoQA accuracy.

Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.

Spike-based encodings are sparse and energy-efficient, but have largely been formulated probabilistically, disconnected from most signal processing literature. We recast spike encoders as time-causal wavelet frames with quantitative bandwidths and reconstruction error bounds. The proposed wavelets preserve the sparsity and locality of spiking representations, with reconstruction up to spike quantization and time discretization. We demonstrate reconstruction on ECG and audio datasets, achieving a normalized RMSE comparable to continuous wavelet transforms. The spiking wavelets map directly to neuromorphic hardware.

Large vision models (LVMs) have recently proven to be surprisingly effective time series forecasters, simply by rendering temporal data as images. This success, how ever, rests on a largely unexamined premise: the rendered time series images are sufficiently close to natural images for knowledge in pre-trained models to transfer effectively. We argue that two gaps still remain, i.e., spectral and structural gaps, fundamentally limiting the potential of LVMs for time series forecasting. Spectrally, we systematically reveal that rendered time series images exhibit a markedly shallower power spectrum than the natural images LVMs are pre-trained to recognize. Structurally, reshaping 1D temporal sequences into 2D grids fabricates spurious spatial adjacencies while severing genuine temporal continuities, misleading the spatial inductive biases of pre-trained LVMs. To bridge these gaps, we propose SSDA, a dual-branch network that spectrally and structurally adapts to unlock the full potential of LVMs for time series forecasting. At the data level, a Spectral Magnitude Aligner (SMA) applies 2D FFT to selectively enhance the magnitude spectrum toward natural-image statistics while preserving phase. At the model level, a Structural-Guided Low-Rank Adaptation (SG-LoRA) injects position-aware temporal encodings into patch embeddings and adapts at tention via low-rank updates. The two branches are further adaptively fused to produce the final forecast. Extensive experiments on seven real-world benchmarks demonstrate that SSDA consistently outperforms strong LVM- and LLM-based baselines under both full-shot and few-shot settings. Code is publicly available at https://anonymous.4open.science/r/SSDA-8C5B.

Wearable sensors enable the continuous acquisition of high-resolution physiological waveforms, such as photoplethysmography and accelerometry, under free-living conditions. However, inferring health-related phenotypes from these signals presents significant challenges due to high sampling frequencies, multimodal dependencies, and extreme sequence lengths (e.g., weeks of recordings), compounded by a scarcity of ground-truth labels. To address these challenges, existing self-supervised learning (SSL) methodologies typically follow two paradigms: (1) learning rich morphological representations from short waveform segments while collapsing longitudinal dynamics through simple aggregation, or (2) modeling behavioral patterns from coarse, hand-crafted features (e.g. heart rate, step counts) spanning longer horizons but foregoing subtle, predictive signatures in raw waveforms. To bridge this gap, we propose WavesFM, a foundation model utilizing a two-stage SSL framework for longitudinal physiological data. Specifically, we decompose the learning problem into two stages: first, a segment-level encoder is pretrained to extract local embeddings from short waveforms; subsequently, a temporal encoder is trained to model the sequence of these embeddings across a multi-day horizon. This hierarchical approach overcomes the computational complexity of high-resolution, long-sequence data, allowing the overall model to capture both local signal semantics and the complex circadian and inter-day variations governing physiological dynamics. Pretrained on over 6.8M hours (N=324k individuals) of recordings for the first stage and 5.3M hours (N=10k) for the second stage, WavesFM demonstrates superior performance across 58 diverse tasks spanning demographics, lifestyle, health conditions, and medications.

Long-term multimodal action quality assessment (AQA) evaluates action execution in several-minute audiovisual sequences by mining discriminative quality cues for score prediction. Existing multimodal methods usually model entire sequences with a single temporal encoder and fuse modality features by direct alignment or concatenation, causing key cues to be obscured by global trends, weakened by modal redundancy, and distorted during one-shot score mapping. To address this issue, we reformulate long-term multimodal AQA as a quality cue organization problem and propose MLCR, a multi-level cue refinement framework. MLCR organizes quality evidence at three levels: intra-modal representation, cross-modal interaction, and stage-wise aggregation. Specifically, the intra-modal decoupling encoder (IMDE) preserves modality identity while refining global temporal context and local frequency details. The cross-modal dynamic complementarity-aware retrieval (CMDCR) module retrieves incremental evidence conditioned on the evolving fused state and suppresses redundant responses. The stage-wise multimodal integration (SMI) block progressively accumulates intra-modal and cross-modal cues to refine the fused representation. Experiments on the Rhythmic Gymnastics and Fis-V datasets show that MLCR achieves the best or second-best performance in both Spearman correlation and prediction error, demonstrating its effectiveness and robustness.

The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet frontier Video Large Language Models (Video-LLMs) perform only modestly above chance. This gap raises a key question: do visual backbones fail to encode temporal information, or does information bottleneck lie elsewhere in the Video-LLM architecture? We address this question by isolating the vision encoder from the Video-LLM and tracing temporal information across the encoder, projector, and LLM. We find that video-centric encoders with explicit temporal modeling encode strong temporal signals, whereas frame-centric encoders do not. However, when video-centric representations are passed through a standard Video-LLM architecture, performance often collapses, revealing a bottleneck of temporal information flow. We identify projector design as a key factor: Q-Former disrupts temporal information, while a time-preserved MLP projection substantially improves the LLM's access to such information. Our layer-wise analysis further shows temporal representation dynamics across encoder layers. Guided by these findings, we build a Video-LLM with temporal-aware video-centric encoder, time-preserved projector, and AoT supervision, surpassing human performance on AoT$_{PPB}$ with 98.1% accuracy, and improving broader temporal reasoning tasks by up to 6.0 points on VITATECS-Direction and 1.3 points on TVBench. Our results show that temporal reasoning in Video-LLMs requires both effective temporal encoding and reliable transfer of this information to the LLM.

Cameras and LiDAR degrade in rain, fog, and snow, while millimeter-wave radar remains largely unaffected. We align a radar encoder to frozen SigLIP vision embeddings and decode structured scene captions through a frozen vision-language model (VLM) with approximately 7M trainable parameters. On K-RADAR with held-out fog, light snow, and heavy snow sequences, all radar configurations outperform a camera baseline that collapses to over 90% hallucination. We identify a token-norm mismatch as the dominant failure mode when bridging radar to a frozen VLM and show that projector-output LayerNorm resolves it. Analysis of encoder complexity, caption format, and pooling strategy reveals tradeoffs that inform future radar-VLM pipeline design.

Graph Edit Distance (GED) is a fundamental, albeit NP-hard, metric for structural graph similarity. Recent neural graph matching architectures approximate GED by first encoding graphs with a Graph Neural Network (GNN) and then applying either a graph-level regression head or a matching-based alignment module. Despite substantial architectural progress, the role of encoder geometry in neural GED estimation remains poorly understood. In this paper, we develop a theoretical framework that connects encoder geometry to GED estimation quality for two broad classes of neural GED estimators: graph similarity predictors and alignment-based methods. On fixed graph collections, where the doubly-stochastic metric $d_{\mathrm{DS}}$ is comparable to GED, we show that graph-level bi-Lipschitz encoders yield controlled GED surrogates and improved ranking stability; for matching-based estimators, node-level bi-Lipschitz geometry propagates to encoder-induced alignment costs and the resulting optimized alignment objective. We instantiate this perspective using FSW-GNN, a bi-Lipschitz WL-equivalent encoder, as a drop-in replacement in representative neural GED architectures. Across representative baselines and benchmark datasets, the resulting geometry-aware variants significantly improve GED prediction and ranking metrics. A faithfulness case study of untrained encoders, together with ablations and transfer experiments, supports the view that these gains arise from improved representation geometry, positioning encoder geometry as a useful design principle for neural graph matching.

Diffusion-based talking head generation has achieved remarkable visual quality, yet scaling it to long-term videos remains challenging. The widely adopted chunk-wise paradigm introduces two fundamental failures: (1) temporal-spatial misalignment between static identity references and dynamic audio streams, and (2) cascading identity drift propagated through self-generated continuity references across chunks. To address both issues, we propose AsymTalker, a novel diffusion-based talking head generation method comprising Temporal Reference Encoding (TRE) and Asymmetric Knowledge Distillation (AKD). First, TRE mitigates temporal-spatial misalignment by transforming the static identity image into a temporally coherent latent representation through encoding of a temporally replicated pseudo-video, without introducing additional parameters. Second, AKD resolves the inherent conditioning dilemma in chunk-wise training: using ground-truth references causes train-inference mismatch, while self-generated references entangle supervision with identity drift. Our asymmetric design circumvents this by anchoring the teacher model with ground-truth continuity references to provide drift-free, chunk-level supervision, thereby avoiding the teacher bottleneck. Meanwhile, the student model learns under inference-aligned conditions, conditioned only on self-generated references, and is trained via distribution matching to preserve identity over long horizons. Extensive experiments show AsymTalker achieves state-of-the-art results on HDTF and VFHQ. It guarantees high-fidelity, identity-consistent synthesis over 600-second videos and reaches a real-time inference speed of 66 FPS.