Implicit Neural Representations (INRs), also known as neural fields, have emerged as a powerful paradigm in deep learning, parameterizing continuous spatial fields using coordinate-based neural networks. In this paper, we propose \textbf{PICO}, an INR-based framework for static point cloud compression. Unlike prevailing encoder-decoder paradigms, we decompose the point cloud compression task into two separate stages: geometry compression and attribute compression, each with distinct INR optimization objectives. Inspired by Kolmogorov-Arnold Networks (KANs), we introduce a novel network architecture, \textbf{LeAFNet}, which leverages learnable activation functions in the latent space to better approximate the target signal's implicit function. By reformulating point cloud compression as neural parameter compression, we further improve compression efficiency through quantization and entropy coding. Experimental results demonstrate that \textbf{LeAFNet} outperforms conventional MLPs in INR-based point cloud compression. Furthermore, \textbf{PICO} achieves superior geometry compression performance compared to the current MPEG point cloud compression standard, yielding an average improvement of $4.92$ dB in D1 PSNR. In joint geometry and attribute compression, our approach exhibits highly competitive results, with an average PCQM gain of $2.7 \times 10^{-3}$.
Recent advances in unsupervised anomaly detection (UAD) have shifted from single-class to multi-class scenarios. In such complex contexts, the increasing pattern diversity has brought two challenges to reconstruction-based approaches: (1) over-generalization: anomalies that are subtle or share compositional similarities with normal patterns may be reconstructed with high fidelity, making them difficult to distinguish from normal instances; and (2) insufficient normality reconstruction: complex normal features, such as intricate textures or fine-grained structures, may not be faithfully reconstructed due to the model's limited representational capacity, resulting in false positives. Existing methods typically focus on addressing the former, which unintentionally exacerbate the latter, resulting in inadequate representation of intricate normal patterns. To concurrently address these two challenges, we propose a Memory-augmented Dual-Decoder Networks (MDD-Net). This network includes two critical components: a Dual-Decoder Reverse Distillation Network (DRD-Net) and a Class-aware Memory Module (CMM). Specifically, the DRD-Net incorporates a restoration decoder designed to recover normal features from synthetic abnormal inputs and an identity decoder to reconstruct features that maintain the anomalous semantics. By exploiting the discrepancy between features produced by two decoders, our approach refines anomaly scores beyond the conventional encoder-decoder comparison paradigm, effectively reducing false positives and enhancing localization accuracy. Furthermore, the CMM explicitly encodes and preserves class-specific normal prototypes, actively steering the network away from anomaly reconstruction. Comprehensive experimental results across several benchmarks demonstrate the superior performance of our MDD-Net framework over current SoTA approaches in multi-class UAD tasks.
We present LOCATE 3D, a model for localizing objects in 3D scenes from referring expressions like "the small coffee table between the sofa and the lamp." LOCATE 3D sets a new state-of-the-art on standard referential grounding benchmarks and showcases robust generalization capabilities. Notably, LOCATE 3D operates directly on sensor observation streams (posed RGB-D frames), enabling real-world deployment on robots and AR devices. Key to our approach is 3D-JEPA, a novel self-supervised learning (SSL) algorithm applicable to sensor point clouds. It takes as input a 3D pointcloud featurized using 2D foundation models (CLIP, DINO). Subsequently, masked prediction in latent space is employed as a pretext task to aid the self-supervised learning of contextualized pointcloud features. Once trained, the 3D-JEPA encoder is finetuned alongside a language-conditioned decoder to jointly predict 3D masks and bounding boxes. Additionally, we introduce LOCATE 3D DATASET, a new dataset for 3D referential grounding, spanning multiple capture setups with over 130K annotations. This enables a systematic study of generalization capabilities as well as a stronger model.
Cancer remains one of the leading causes of mortality worldwide, and among its many forms, brain tumors are particularly notorious due to their aggressive nature and the critical challenges involved in early diagnosis. Recent advances in artificial intelligence have shown great promise in assisting medical professionals with precise tumor segmentation, a key step in timely diagnosis and treatment planning. However, many state-of-the-art segmentation methods require extensive computational resources and prolonged training times, limiting their practical application in resource-constrained settings. In this work, we present a novel dual-decoder U-Net architecture enhanced with attention-gated skip connections, designed specifically for brain tumor segmentation from MRI scans. Our approach balances efficiency and accuracy by achieving competitive segmentation performance while significantly reducing training demands. Evaluated on the BraTS 2020 dataset, the proposed model achieved Dice scores of 85.06% for Whole Tumor (WT), 80.61% for Tumor Core (TC), and 71.26% for Enhancing Tumor (ET) in only 50 epochs, surpassing several commonly used U-Net variants. Our model demonstrates that high-quality brain tumor segmentation is attainable even under limited computational resources, thereby offering a viable solution for researchers and clinicians operating with modest hardware. This resource-efficient model has the potential to improve early detection and diagnosis of brain tumors, ultimately contributing to better patient outcomes
We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face challenges with capturing global dependencies, our method leverages a discrete Fourier transform to mix token embeddings across the entire sequence dimension, coupled with learned frequency-domain gating. This allows the model to efficiently propagate context without explicit autoregressive steps. Empirically, FourierNAT achieves competitive results against leading NAT baselines on standard benchmarks like WMT machine translation and CNN/DailyMail summarization, providing significant speed advantages over autoregressive Transformers. We further demonstrate that learned frequency-domain parameters allow the model to adaptively focus on long-range or short-range dependencies, partially mitigating the well-known coherence gaps in one-pass NAT generation. Overall, FourierNAT highlights the potential of integrating spectral-domain operations to accelerate and improve parallel text generation. This approach can potentially provide great computational and time savings in inference tasks LLMs.
Current sign language machine translation systems rely on recognizing hand movements, facial expressions and body postures, and natural language processing, to convert signs into text. Recent approaches use Transformer architectures to model long-range dependencies via positional encoding. However, they lack accuracy in recognizing fine-grained, short-range temporal dependencies between gestures captured at high frame rates. Moreover, their high computational complexity leads to inefficient training. To mitigate these issues, we propose an Adaptive Transformer (ADAT), which incorporates components for enhanced feature extraction and adaptive feature weighting through a gating mechanism to emphasize contextually relevant features while reducing training overhead and maintaining translation accuracy. To evaluate ADAT, we introduce MedASL, the first public medical American Sign Language dataset. In sign-to-gloss-to-text experiments, ADAT outperforms the encoder-decoder transformer, improving BLEU-4 accuracy by 0.1% while reducing training time by 14.33% on PHOENIX14T and 3.24% on MedASL. In sign-to-text experiments, it improves accuracy by 8.7% and reduces training time by 2.8% on PHOENIX14T and achieves 4.7% higher accuracy and 7.17% faster training on MedASL. Compared to encoder-only and decoder-only baselines in sign-to-text, ADAT is at least 6.8% more accurate despite being up to 12.1% slower due to its dual-stream structure.
Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion model that leverages Mamba-based layers within a U-Net-like hierarchical structure. By progressively reducing sequence length in the encoder and restoring it in the decoder through Mamba blocks, USM significantly lowers computational overhead while maintaining strong generative capabilities. Experimental results against Zigma, which is currently the most efficient Mamba-based diffusion model, demonstrate that USM achieves one-third the GFlops, requires less memory and is faster, while outperforming Zigma in image quality. Frechet Inception Distance (FID) is improved by 15.3, 0.84 and 2.7 points on AFHQ, CelebAHQ and COCO datasets, respectively. These findings highlight USM as a highly efficient and scalable solution for diffusion-based generative models, making high-quality image synthesis more accessible to the research community while reducing computational costs.
Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that enhances object detection performance by dynamically integrating positional encoding with semantic detection information through heatmap-guided adaptive learning.We also innovatively visualize the HMPE method, offering clear visualization of embedded information for parameter fine-tuning.We then create Multi-Scale ObjectBox-Heatmap Fusion Encoder (MOHFE) and HeatMap Induced High-Quality Queries for Decoder (HIDQ) modules. These are designed for the encoder and decoder, respectively, to generate high-quality queries and reduce background noise queries.Using both heatmap embedding and Linear-Snake Conv(LSConv) feature engineering, we enhance the embedding of massively diverse small object categories and reduced the decoder multihead layers, thereby accelerating both inference and training.In the generalization experiments, our approach outperforme the baseline mAP by 1.9% on the small object dataset (NWPU VHR-10) and by 1.2% on the general dataset (PASCAL VOC). By employing HMPE-enhanced embedding, we are able to reduce the number of decoder layers from eight to a minimum of three, significantly decreasing both inference and training costs.
Colonoscopy is vital in the early diagnosis of colorectal polyps. Regular screenings can effectively prevent benign polyps from progressing to CRC. While deep learning has made impressive strides in polyp segmentation, most existing models are trained on single-modality and single-center data, making them less effective in real-world clinical environments. To overcome these limitations, we propose FocusNet, a Transformer-enhanced focus attention network designed to improve polyp segmentation. FocusNet incorporates three essential modules: the Cross-semantic Interaction Decoder Module (CIDM) for generating coarse segmentation maps, the Detail Enhancement Module (DEM) for refining shallow features, and the Focus Attention Module (FAM), to balance local detail and global context through local and pooling attention mechanisms. We evaluate our model on PolypDB, a newly introduced dataset with multi-modality and multi-center data for building more reliable segmentation methods. Extensive experiments showed that FocusNet consistently outperforms existing state-of-the-art approaches with a high dice coefficients of 82.47% on the BLI modality, 88.46% on FICE, 92.04% on LCI, 82.09% on the NBI and 93.42% on WLI modality, demonstrating its accuracy and robustness across five different modalities. The source code for FocusNet is available at https://github.com/JunZengz/FocusNet.
We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook: a VQVAE model to learn a latent codebook of hand poses and contact points, effectively tokenizing interaction trajectories, (2) Interaction Predictor: a transformer-decoder module to predict the interaction trajectory from test time inputs by using an indexer module to retrieve a latent affordance from the learned codebook. To train our model, we develop a data engine that extracts 3D hand poses and contact trajectories from the diverse HoloAssist dataset. We evaluate our model on a benchmark that is 2.5-10X larger than existing works, in terms of diversity of objects and interactions observed, and test for generalization of the model across object categories, action categories, tasks, and scenes. Experimental results show the effectiveness of our approach over transformer & diffusion baselines across all settings.
Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains, where data is often irregularly distributed (e.g., missing values from sensor failures) and high-volume (e.g., high-fidelity simulations), posing additional computational and modeling difficulties. In this paper, we present SCENT, a novel framework for scalable and continuity-informed spatiotemporal representation learning. SCENT unifies interpolation, reconstruction, and forecasting within a single architecture. Built on a transformer-based encoder-processor-decoder backbone, SCENT introduces learnable queries to enhance generalization and a query-wise cross-attention mechanism to effectively capture multi-scale dependencies. To ensure scalability in both data size and model complexity, we incorporate a sparse attention mechanism, enabling flexible output representations and efficient evaluation at arbitrary resolutions. We validate SCENT through extensive simulations and real-world experiments, demonstrating state-of-the-art performance across multiple challenging tasks while achieving superior scalability.
Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often demands complex training recipes and careful data balancing. We introduce MetaQueries, a set of learnable queries that act as an efficient interface between autoregressive multimodal LLMs (MLLMs) and diffusion models. MetaQueries connects the MLLM's latents to the diffusion decoder, enabling knowledge-augmented image generation by leveraging the MLLM's deep understanding and reasoning capabilities. Our method simplifies training, requiring only paired image-caption data and standard diffusion objectives. Notably, this transfer is effective even when the MLLM backbone remains frozen, thereby preserving its state-of-the-art multimodal understanding capabilities while achieving strong generative performance. Additionally, our method is flexible and can be easily instruction-tuned for advanced applications such as image editing and subject-driven generation.
We present MaskMark, a simple, efficient, and flexible framework for image watermarking. MaskMark has two variants: (1) MaskMark-D, which supports global watermark embedding, watermark localization, and local watermark extraction for applications such as tamper detection; (2) MaskMark-ED, which focuses on local watermark embedding and extraction, offering enhanced robustness in small regions to support fine-grined image protection. MaskMark-D builds on the classical encoder-distortion layer-decoder training paradigm. In MaskMark-D, we introduce a simple masking mechanism during the decoding stage that enables both global and local watermark extraction. During training, the decoder is guided by various types of masks applied to watermarked images before extraction, helping it learn to localize watermarks and extract them from the corresponding local areas. MaskMark-ED extends this design by incorporating the mask into the encoding stage as well, guiding the encoder to embed the watermark in designated local regions, which improves robustness under regional attacks. Extensive experiments show that MaskMark achieves state-of-the-art performance in global and local watermark extraction, watermark localization, and multi-watermark embedding. It outperforms all existing baselines, including the recent leading model WAM for local watermarking, while preserving high visual quality of the watermarked images. In addition, MaskMark is highly efficient and adaptable. It requires only 20 hours of training on a single A6000 GPU, achieving 15x computational efficiency compared to WAM. By simply adjusting the distortion layer, MaskMark can be quickly fine-tuned to meet varying robustness requirements.
Large language models (LLMs) frequently generate hallucinations-content that deviates from factual accuracy or provided context-posing challenges for diagnosis due to the complex interplay of underlying causes. This paper introduces a subsequence association framework to systematically trace and understand hallucinations. Our key insight is that hallucinations arise when dominant hallucinatory associations outweigh faithful ones. Through theoretical and empirical analyses, we demonstrate that decoder-only transformers effectively function as subsequence embedding models, with linear layers encoding input-output associations. We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts. Experiments show our method outperforms standard attribution techniques in identifying hallucination causes and aligns with evidence from the model's training corpus. This work provides a unified perspective on hallucinations and a robust framework for their tracing and analysis.
Large language models are increasingly used in scientific domains, especially for molecular understanding and analysis. However, existing models are affected by hallucination issues, resulting in errors in drug design and utilization. In this paper, we first analyze the sources of hallucination in LLMs for molecular comprehension tasks, specifically the knowledge shortcut phenomenon observed in the PubChem dataset. To evaluate hallucination in molecular comprehension tasks with computational efficiency, we introduce \textbf{Mol-Hallu}, a novel free-form evaluation metric that quantifies the degree of hallucination based on the scientific entailment relationship between generated text and actual molecular properties. Utilizing the Mol-Hallu metric, we reassess and analyze the extent of hallucination in various LLMs performing molecular comprehension tasks. Furthermore, the Hallucination Reduction Post-processing stage~(HRPP) is proposed to alleviate molecular hallucinations, Experiments show the effectiveness of HRPP on decoder-only and encoder-decoder molecular LLMs. Our findings provide critical insights into mitigating hallucination and improving the reliability of LLMs in scientific applications.
This paper proposes a novel end-to-end digital semantic communication framework based on multi-codebook vector quantization (VQ), referred to as ESC-MVQ. Unlike prior approaches that rely on end-to-end training with a specific power or modulation scheme, often under a particular channel condition, ESC-MVQ models a channel transfer function as parallel binary symmetric channels (BSCs) with trainable bit-flip probabilities. Building on this model, ESC-MVQ jointly trains multiple VQ codebooks and their associated bit-flip probabilities with a single encoder-decoder pair. To maximize inference performance when deploying ESC-MVQ in digital communication systems, we devise an optimal communication strategy that jointly optimizes codebook assignment, adaptive modulation, and power allocation. To this end, we develop an iterative algorithm that selects the most suitable VQ codebook for semantic features and flexibly allocates power and modulation schemes across the transmitted symbols. Simulation results demonstrate that ESC-MVQ, using a single encoder-decoder pair, outperforms existing digital semantic communication methods in both performance and memory efficiency, offering a scalable and adaptive solution for realizing digital semantic communication in diverse channel conditions.
This paper presents RFconstruct, a framework that enables 3D shape reconstruction using commercial off-the-shelf (COTS) mmWave radars for self-driving scenarios. RFconstruct overcomes radar limitations of low angular resolution, specularity, and sparsity in radar point clouds through a holistic system design that addresses hardware, data processing, and machine learning challenges. The first step is fusing data captured by two radar devices that image orthogonal planes, then performing odometry-aware temporal fusion to generate denser 3D point clouds. RFconstruct then reconstructs 3D shapes of objects using a customized encoder-decoder model that does not require prior knowledge of the object's bound box. The shape reconstruction performance of RFconstruct is compared against 3D models extracted from a depth camera equipped with a LiDAR. We show that RFconstruct can accurately generate 3D shapes of cars, bikes, and pedestrians.
Moir\'e patterns, resulting from aliasing between object light signals and camera sampling frequencies, often degrade image quality during capture. Traditional demoir\'eing methods have generally treated images as a whole for processing and training, neglecting the unique signal characteristics of different color channels. Moreover, the randomness and variability of moir\'e pattern generation pose challenges to the robustness of existing methods when applied to real-world data. To address these issues, this paper presents SIDME (Self-supervised Image Demoir\'eing via Masked Encoder-Decoder Reconstruction), a novel model designed to generate high-quality visual images by effectively processing moir\'e patterns. SIDME combines a masked encoder-decoder architecture with self-supervised learning, allowing the model to reconstruct images using the inherent properties of camera sampling frequencies. A key innovation is the random masked image reconstructor, which utilizes an encoder-decoder structure to handle the reconstruction task. Furthermore, since the green channel in camera sampling has a higher sampling frequency compared to red and blue channels, a specialized self-supervised loss function is designed to improve the training efficiency and effectiveness. To ensure the generalization ability of the model, a self-supervised moir\'e image generation method has been developed to produce a dataset that closely mimics real-world conditions. Extensive experiments demonstrate that SIDME outperforms existing methods in processing real moir\'e pattern data, showing its superior generalization performance and robustness.
This paper investigates deploying semantic edge inference systems for performing a common image clarification task. In particular, each system consists of multiple Internet of Things (IoT) devices that first locally encode the sensing data into semantic features and then transmit them to an edge server for subsequent data fusion and task inference. The inference accuracy is determined by efficient training of the feature encoder/decoder using labeled data samples. Due to the difference in sensing data and communication channel distributions, deploying the system in a new environment may induce high costs in annotating data labels and re-training the encoder/decoder models. To achieve cost-effective transferable system deployment, we propose an efficient Domain Adaptation method for Semantic Edge INference systems (DASEIN) that can maintain high inference accuracy in a new environment without the need for labeled samples. Specifically, DASEIN exploits the task-relevant data correlation between different deployment scenarios by leveraging the techniques of unsupervised domain adaptation and knowledge distillation. It devises an efficient two-step adaptation procedure that sequentially aligns the data distributions and adapts to the channel variations. Numerical results show that, under a substantial change in sensing data distributions, the proposed DASEIN outperforms the best-performing benchmark method by 7.09% and 21.33% in inference accuracy when the new environment has similar or 25 dB lower channel signal to noise power ratios (SNRs), respectively. This verifies the effectiveness of the proposed method in adapting both data and channel distributions in practical transfer deployment applications.
With the growing demand for protecting the intellectual property (IP) of text-to-image diffusion models, we propose PCDiff -- a proactive access control framework that redefines model authorization by regulating generation quality. At its core, PCDIFF integrates a trainable fuser module and hierarchical authentication layers into the decoder architecture, ensuring that only users with valid encrypted credentials can generate high-fidelity images. In the absence of valid keys, the system deliberately degrades output quality, effectively preventing unauthorized exploitation.Importantly, while the primary mechanism enforces active access control through architectural intervention, its decoupled design retains compatibility with existing watermarking techniques. This satisfies the need of model owners to actively control model ownership while preserving the traceability capabilities provided by traditional watermarking approaches.Extensive experimental evaluations confirm a strong dependency between credential verification and image quality across various attack scenarios. Moreover, when combined with typical post-processing operations, PCDIFF demonstrates powerful performance alongside conventional watermarking methods. This work shifts the paradigm from passive detection to proactive enforcement of authorization, laying the groundwork for IP management of diffusion models.