paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Rendering

Huangsheng Du, Haoran Zhu, Youcheng Cai, Jingyang Meng, Ligang Liu

We present RenderFormer++, a scalable and physics-informed feed-forward neural rendering framework for global illumination in mesh scenes. Existing Transformer-based neural rendering methods such as RenderFormer achieve promising cross-scene generalization, but lack explicit transport priors and scale poorly due to quadratic triangle-level attention. To address these issues, we introduce Physics-Informed Transport Guidance (PITG), which embeds rendering-equation-inspired inductive biases into the attention mechanism and introduces a transport consistency loss, encouraging physics-informed light transport modeling. We further propose Hierarchical Object-Centric Tokenization (HOCT), which aggregates triangle-level features into compact object-level tokens via cross-attention with learnable queries, substantially reducing computational and memory costs. Extensive experiments demonstrate that RenderFormer++ achieves scalable and generalizable feed-forward global illumination rendering across complex large-scale scenes with competitive rendering quality and substantially improved efficiency over RenderFormer. The code will be made publicly available upon acceptance.

arXiv

Ordinal Neural Collapse as a Representation Prior for Visual Navigation

E-In Son, Jung-Taak Kim, Seung-Woo Seo

Learning robust navigation policies directly from visual observations remains a fundamental challenge in vision-based robotic navigation. In end-to-end imitation learning approaches, the visual encoder and action decoder are jointly optimized using a single action loss, which provides only an indirect supervisory signal to the encoder. This indirect supervision frequently results in the encoder learning ambiguous, action-agnostic representations. The problem is further complicated by substantial variations in scene structure and appearance across diverse environments, as well as the prevalence of visual distractors inherent to real-world navigation settings. Such action-agnostic features cause the navigation policy to produce inconsistent actions at ambiguous decision points, leading to navigation failure. To overcome these limitations, we propose ORION (Ordinal Neural Collapse for Visual Navigation), a method that explicitly organizes the encoder's representation space according to the ordinal structure of navigation actions. In the context of goal-directed navigation, ego-centric control categories from Far Left to Far Right exhibit a natural ordinal relationship in which neighboring classes share similar visual contexts, while semantically opposing classes differ substantially in appearance. We encourage class representations to be arranged sequentially along a single discriminative axis, while suppressing off-axis variance within each class. The pretrained encoder is then integrated into a diffusion-based navigation framework, and the full pipeline is fine-tuned end-to-end. Extensive experiments in both simulation and real-world settings show that ORION consistently outperforms end-to-end and neural collapse baselines in navigation success rate and goal progress, with notable gains in visually challenging scenarios such as complex multi-way intersections.

arXiv

High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology

Johannes Boehm, Bappaditya Dey

Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming essential, but current generative models often miss TEM-specific noise, structural detail, and stochastic variability crucial for evaluation. We present a Denoising Diffusion Probabilistic Model (DDPM) framework for synthetic TEM image generation under extreme data scarcity. A progressive patch-based training strategy scales from low-resolution patches to full images, enabling from-scratch training with only 15 samples. We integrate a custom TrivialAugment adaptation, cross-process domain transfer, classifier guidance, and RePaint-style inpainting, culminating in full-image generation that preserves global structural and spatial relationships in compliance with FAB metrology requirements. Beyond synthesis, we repurpose DDPM feature representations for segmentation, partitioning encoder feature maps to obtain coherent region masks. Our synthetic images achieve up to MS-SSIM > 0.98 and qualitative expert assessment consistent with structural similarity results, facilitating downstream ML training for defect detection, segmentation, and metrology while preserving statistical and physical realism.

arXiv

CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain

Chidera Agbasiere, Mikhail Sannikov, Faith Ogunwoye, Erik Shaikhiev, Alex Kozinov, Ilya Mikhalchuk, Iana Zhura, Dzmitry Tsetserukou

Reconstructing dense 3D scenes from sparse LiDAR point clouds (LiDAR scene completion) is a fundamental challenge in autonomous driving, where diffusion models offer a promising solution. However, existing approaches rely on object-level autoencoders that collapse into unstable global representations at outdoor scale, and suffer from ground truth data corrupted by odometry drift that systematically degrades supervision quality. Furthermore, multi-step diffusion inference incurs prohibitive latency for real-time deployment. We present CloudDiffusion, addressing these issues with three independent components. First, a multi-token Gaussian VAE with cross-attention pooling provides stable scene-scale LiDAR compression as a standalone reconstruction module, avoiding the global-pooling and codebook-collapse failure modes of prior point-cloud autoencoders. Second, an anchor-based ICP ground truth refinement pipeline eliminates drift-induced noise from training supervision, reducing our single-step x0 diffusion teacher's squared Chamfer distance by approximately 16x on SemanticKITTI seq. 08 (0.396 to 0.024 m^2) with no model change (partly aided by the denser, more compact refined references). Third, the same teacher completes scenes in a single x0 step, operating directly in coordinate space, not in the VAE latent. It runs in near real time at 209ms/frame, 65-138x lower inference latency than iterative diffusion baselines. Our results indicate that data quality dominates model design in this regime, and suggest that multi-token latent spaces could serve as a stable first stage for future latent diffusion-based scene completion.

arXiv

TIDE: Task-Isolated Diffusion for Unified Video Editing and Generation

Qi Liu, Gang Yue, Mingyu Yin, Lisai Zhang, Yidi Wu, Yaole Wang, Yaohui Wang, Chang Yao, Jingyuan Chen, Lin Ma

Recent advances in Diffusion Transformers have driven rapid progress in video generation and editing, yet these capabilities are still handled by separate, task-specific models. Building a unified framework that supports diverse video tasks remains an open challenge: existing unified attempts either require dedicated auxiliary encoders or lack explicit mechanisms to distinguish heterogeneous conditioning tokens, struggling when the number and type of visual conditions vary across tasks. We propose TIDE, a unified framework that integrates instruction-based editing, reference-guided editing, and multi-reference generation. At its core, we introduce per-token task embeddings that assign each input token a task-specific identifier, enabling the model to explicitly disambiguate target, source, and reference tokens. To simultaneously capture high-level semantic understanding and fine-grained structural fidelity, we design a dual-path conditioning scheme that couples a vision-language model with a VAE latent path for complementary signals. We further devise a multi-task progressive training strategy that incrementally introduces tasks of increasing complexity, effectively harmonizing diverse objectives and enabling smooth generalization across heterogeneous task distributions. Extensive experiments on multiple video editing and generation benchmarks demonstrate that TIDE achieves state-of-the-art performance across all evaluated tasks. Our project page is available at https://LittleWork123.github.io/tide.

arXiv

Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation

Haocheng Luo, Jiahui Liu, Ruicheng Zhang, Zhizhou Zhong, Jiaqi Huang, Zunnan Xu, Quan Shi, JUN ZHOU, Shuiyang Mao, Wei Liu, Xiu Li

While Vision-Language Models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this limitation to a perception--reasoning modality gap. Visual planning requires models to infer latent state structures from pixels and then reason over the recovered structure to produce valid actions, whereas symbolic planning directly leverages explicit representation. This discrepancy introduces two sequential bottlenecks: visual state recovery at the perception stage and multi-step planning at the reasoning stage. To address this, we propose MGSD, a two-stage modality-gap-aware self-distillation framework. First, a cold-start grounding stage establishes reliable visual state recovery before on-policy training. Second, a symbol-guided on-policy self-distillation stage transfers the privileged teacher's planning behavior to the student through token-level supervision on student-generated prefixes. Crucially, symbolic information is used only during training, while inference relies exclusively on visual inputs. Experiments on visual planning benchmarks show that MGSD consistently improves performance across different model scales, raising the macro average by 19.3% and 18.4%, respectively. The resulting models substantially reduce the gap to the upper bounds obtained with symbolic inputs. Ablation studies and diagnostic analyses further confirm that the gains arise from improvements in both visual state recovery and optimal-path reasoning. These results demonstrate that MGSD strengthens not only the recovery of actionable states from visual observations but also the ability to plan over the inferred structures. Code is available at https://github.com/Oranger-l/MGSD.

arXiv

Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations

Yuan Zhang, Chenyi Li, Haodong Yu, Guoqing Ma, Jiajun Zha, Yuanming Yang, Bo Wang, Wei Tang, Wenbo Li, Haoyang Huang, Nan Duan

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed training stages, or complex optimization pipelines. In this work, we revisit the recently proposed Drifting Model objective and show that a single drifting loss can be directly used to simplify one step distillation. A key observation is that the pretrained diffusion teacher itself already provides a strong representation space. Unlike the original Drifting Model, which relies on an additional pretrained feature extractor, we use intermediate hidden states of the pretrained teacher model as the feature representation. This removes the need for training or introducing an extra representation network while preserving a semantically meaningful feature geometry for drifting. Furthermore, we introduce a lightweight mode coverage loss to mitigate mode collapse during distillation and encourage the student generator to cover diverse teacher-supported regions. Extensive experiments on ImageNet and SDXL demonstrate that our method achieves efficient one step generation with competitive image quality and diversity, achieving FID scores of 1.58 on ImageNet-64$\times$64 and 18.4 on SDXL, while substantially simplifying the overall distillation framework.

arXiv

RemoteZero: Geospatial Reasoning with Zero Labels

Liang Yao, Fan Liu, Shengxiang Xu, Chuanyi Zhang, Rui Min, Shimin Di, Yuhui Zheng

Geospatial reasoning requires models to identify image regions that satisfy complex and often implicit user intents. Recent reinforcement learning approaches improve reasoning without manually annotated reasoning traces, but still require human-provided target labels to construct rewards, limiting their use on large-scale unlabeled Earth observation data. We introduce RemoteZero, a label-free framework for reinforcement-based geospatial reasoning. Our key observation is twofold: MLLMs are often more reliable at evaluating candidates than generating solutions, while aerial imagery reduces interference in region-level verification. Therefore, RemoteZero converts each predicted region into a visual crop and uses its semantic consistency with the query as an intrinsic reward for GRPO optimization. This formulation removes the need for human-provided solution labels and further supports iterative self-evolution by reusing previous-round models as verifiers. Experiments show that RemoteZero outperforms strong supervised baselines, applies effectively to other Earth observation tasks, and continues to improve through self-evolution as the training data expand. We hope this direction can broadly benefit the Earth observation community.

arXiv

MILE: Mixture of Incremental LoRA Experts for Continual Semantic Segmentation across Domains and Modalities

Shishir Muralidhara, Didier Stricker, René Schuster

Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which task-specific modules specialize in different domains, has proven effective in mitigating forgetting. These methods include dynamic expansion, which suffers from scalability issues, or parameter isolation, which constrains the ability to learn new tasks. We introduce Mixture of Incremental LoRA Experts (MILE), a modular and parameter-efficient framework for continual segmentation across both domains and modalities. MILE leverages Low-Rank Adaptation (LoRA) to instantiate lightweight experts for each new task while keeping the pretrained base network frozen. Each expert is trained exclusively on its task data, thus avoids overwriting previously learned information. A prototype-guided gating mechanism dynamically selects the most appropriate expert at inference. MILE achieves the benefits of expert-based learning while overcoming its scalability limitations. It requires only a marginal parameter increase per task and tens of LoRA adapters are needed before matching the size of a single full model, making it highly efficient in both training and storage. Across domain- and modality-incremental benchmarks, MILE achieves strong performance while ensuring better stability, plasticity, and scalability.

arXiv

Intersectional Disentangling of Temporal and Acquisition Bias in Fetal Ultrasound

Aya Elgebaly, Joris Fournel, Benjamin Laine Jønch Jurgensen, Kamil Mikolaj, Anders Christensen, Martin Tolsgaard, Claes Ladefoged, Aasa Feragen

Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentangle fairness and performance gaps arising from clinical and acquisition confounders that co-vary with the target. As a case, we study scan-time fetal weight estimation from obstetric ultrasound, analyzing two models: a state-of-the-art deep learning (DL) model and the clinical gold-standard Hadlock formula. Using unsupervised slice discovery, we find that high-error subgroups share extreme in the image-acquisition pixel spacing (PS) and in the scan-to-delivery (STD) interval. Of these, PS is an acquisition parameter that can be optimized, while STD is a potential confounder for both PS and our bias diagnostics. Subgroup inspection alone cannot separate them. We disentangle the factors using a model-agnostic analysis with identical metadata partitions and partial regression. Holding STD fixed, the apparent PS effect collapses to a small residual (standardized coefficient $β=-0.17$), whereas holding PS fixed, STD dominates error ($β=+0.56$). Both models degrade with increasing STD, including the biometric formula, indicating much of the error is intrinsic to the prediction target rather than imaging. The DL model is $\sim$1.5$\times$ more sensitive to STD than Hadlock, though it remains more accurate in every subgroup. We conclude that fairness analyses need to carefully analyze potential confounds, or risk attributing an effect such as temporal or acquisition-related dependency to demographics.

arXiv

Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models

Kexin Ma, Jing Xiao, Chaofeng Chen, Geyong Min, Guibo Zhu, Jinqiao Wang, Liang Liao

Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual tokens while preserving performance. However, existing methods typically rely on individual attention sources from different LVLM components, resulting in incomplete and suboptimal pruning decisions due to biased attention distributions. To address this problem, we propose DeSAP, a novel Decoupled Similarity-Aware Pruning method for precise, task-aware token pruning within the visual encoder. Specifically, DeSAP introduces a decoupled similarity to capture fine-grained cross-modal relevance between visual features and text tokens, providing explicit task-related guidance for pruning. By integrating decoupled similarity with visual saliency signals derived from visual attention, DeSAP performs token pruning under the guidance of both task-related and visual cues, enabling robust pruning even under aggressive pruning ratios. Extensive experiments across diverse benchmarks and architectures show that DeSAP consistently outperforms SOTA methods in both accuracy and efficiency. On LLaVA-1.5-7B, DeSAP achieves a 10 times FLOPs reduction and a 2.3 times prefill speedup by retaining only 11.1% of visual tokens, while maintaining 98.1% of the original performance.

arXiv

SciLT: Long-tailed Image Classification under Scientific Image Domains

Jiahao Chen, Bing Su

Long-tailed recognition has benefited from foundation models and fine-tuning paradigms, yet existing studies and benchmarks are mainly confined to natural image domains, where pre-training and fine-tuning data share similar distributions. In contrast, scientific images exhibit distinct visual characteristics and supervision signals, raising questions about the effectiveness of fine-tuning foundation models in such settings. In this work, we investigate scientific long-tailed recognition under a purely visual and fine-tuning paradigm. Experiments on three scientific benchmarks show that fine-tuning foundation models yields limited gains, and reveal that penultimate-layer features play an important role, particularly for tail classes. Motivated by these findings, we propose SciLT, a framework that exploits multi-level representations through adaptive feature fusion and dual-supervision learning. By jointly leveraging penultimate- and final-layer features, SciLT achieves balanced performance across head and tail classes. Extensive experiments demonstrate that SciLT consistently outperforms existing methods, establishing a strong and practical baseline for scientific long-tailed recognition and providing valuable guidance for adapting foundation models to scientific data with substantial domain shifts.

arXiv

SparseVoxelDet: Fully Sparse Voxel Networks for Efficient Event-Based Drone Detection

Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad

Event cameras excel at detecting small, fast drones, but today's detectors give away their key advantage: they convert the sparse event stream into dense grids and pay dense-processing cost on inputs that are almost entirely empty. We present SparseVoxelDet, to our knowledge the first coordinate-sparse 3D event voxel bounding-box detector: backbone, feature pyramid, temporal reduction, and detection head all operate directly on coordinate-indexed features, with no dense spatial grid at any stage. Building it exposed a hidden failure mode we name support inflation: an input filling a median 0.0652% of the voxel lattice inflates stage by stage until standard pyramid fusion leaves the detection head locally near-dense. We answer with two ideas. Expansion-free inverse-convolution fusion provably creates no active sites beyond the stored backbone supports, cutting head occupancy from a median 78.88% to 10.53%; quality-aligned supervision then recovers more accuracy than preserving sparsity costs. The payoff is measured, not assumed: executing the same trained network densely costs a median 27.5x the work and 4.65x the latency across 5,000 paired frames, with no frame cheaper dense, while the 6.22M-parameter detector reaches 87.01 AP50 on the FRED drone benchmark, ahead of matched dense controls, and holds its lead on the held-out test partition evaluated once. Sparsity, preserved by construction and supervised well, delivers the efficiency and the accuracy together.

arXiv

Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation

Qin Chen, Yingjie Chen, Shilun Lin, Cai Xing, Binxin Yang, Long Zhou, Qixin Yan, Wenjing Wang, Dingming Liu, Hao Liu, Chen Li, Jing Lyu

Recent advances in video synthesis have enabled realistic integration of real individuals, driving demand for identity-aware generation. While emerging methods support joint appearance and voice injection in audio-visual models, they primarily focus on single-subject settings. Multimodal identity integration across multiple subjects remains limited, and precise alignment between visual and vocal identities in multi-subject scenarios remains underexplored. We present Identity-as-Presence, a unified framework for joint personalized audio-video generation. An automated data curation pipeline constructs identity-labeled audio-visual pairs for single- and multi-subject scenes. A unified identity injection mechanism then binds paired appearance and voice through shared cross-modal identity binding and subject-anchored captions. A multi-stage training strategy further leverages large-scale unimodal data alongside scarce paired clips to mitigate modality imbalance. Experiments show superior audio quality, video fidelity, and audio-visual consistency, with stronger multi-subject binding than the compared methods. For more details and qualitative results, please refer to our webpage: \href{https://chen-yingjie.github.io/projects/Identity-as-Presence}{Identity-as-Presence}.

arXiv

Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robots

Guoqiang Zhao, Zhe Yang, Sheng Wu, Fei Teng, Mengfei Duan, Yuanfan Zheng, Kai Luo, Kailun Yang

Panoramic imagery provides holistic 360° visual coverage for environmental perception in quadruped robots. However, existing occupancy prediction methods are primarily designed for wheeled autonomous driving and rely heavily on RGB cues, which limits their robustness in complex, dynamically changing environments. To bridge this gap, we introduce PanoMMOcc, the first real-world panoramic multimodal occupancy dataset for quadruped robots, comprising four sensing modalities collected across diverse scenes. We further propose VoxelHound, a panoramic multimodal occupancy perception framework tailored to legged locomotion and spherical imaging. VoxelHound incorporates a Vertical Jitter Compensation (VJC) module to mitigate severe viewpoint perturbations caused by body pitch and roll during locomotion, enabling more consistent spatial reasoning, and a Multimodal Information Prompt Fusion (MIPF) module to effectively integrate panoramic visual cues with auxiliary modalities for enhanced volumetric occupancy prediction. We also establish a comprehensive benchmark on PanoMMOcc and provide detailed dataset analyses to enable systematic evaluation in challenging embodied perception scenarios. Extensive experiments demonstrate that VoxelHound achieves state-of-the-art performance on PanoMMOcc, with a +4.16 gain in mIoU. The dataset and code will be publicly released to facilitate future research on panoramic multimodal 3D perception for embodied robotic systems at https://github.com/SXDR/PanoMMOcc.

arXiv

SynthRender and I-AsSET: Open-Source Framework and Dataset for Bidirectional Sim-Real Transfer in Industrial Object Perception

Jose Moises Araya-Martinez, Thushar Tom, Adrián Sanchis Reig, Pablo Rey Valiente, Jens Lambrecht, Jörg Krüger

Object perception is fundamental for tasks such as robotic material handling and quality inspection. However, modern supervised deep-learning models require large annotated datasets for robust automation under semi-uncontrolled conditions; a major barrier for widespread deployment with proprietary industrial parts. We address this through an integrated framework combining synthetic data generation and structured empirical evaluation for systematic investigation of bidirectional sim-to-real transfer. Our method integrates 2D-to-3D Reality-to-Simulation techniques for 3D asset creation from physical parts with programmatic Guided Domain Randomization (GDR) via SynthRender, an open-source synthetic image generation framework. Structured ablation studies across multiple benchmarks quantify the impact of individual rendering design choices, yielding practical guidelines for data-efficient synthetic training. To support evaluation under realistic industrial conditions, we introduce Industrial Assets for Sim-to-Real Evaluation and Transfer (I-AsSET), a 32-class dataset with diverse textures, intra-class variation, strong inter-class similarities, and 19,672 annotations, providing both CAD models and reconstructed meshes for bidirectional sim-to-real benchmarking. Across three industrial benchmarks, the proposed framework achieves highly competitive performance, reaching 98.7% mAP@50 on a public robotics dataset, 97.9% mAP@50 on an automotive benchmark, and 95.1% mAP@50 on I-AsSET.

arXiv

DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation

Wangkai Li, Rui Sun, Zhaoyang Li, Yujia Chen, Tianzhu Zhang

While existing unsupervised domain adaptation (UDA) methods greatly enhance target domain performance in semantic segmentation, they often neglect network calibration quality, resulting in misalignment between prediction confidence and actual accuracy---a significant risk in safety-critical applications. Our key insight emerges from observing that performance degrades substantially when soft pseudo-labels replace hard pseudo-labels in cross-domain scenarios due to poor calibration, despite the theoretical equivalence of perfectly calibrated soft pseudo-labels to hard pseudo-labels. Based on this finding, we propose DA-Cal, a dedicated cross-domain calibration framework that transforms target domain calibration into soft pseudo-label optimization. DA-Cal introduces a Meta Temperature Network to generate pixel-level calibration parameters and employs bi-level optimization to establish the relationship between soft pseudo-labels and UDA supervision, while utilizing complementary domain-mixing strategies to prevent overfitting and reduce domain discrepancies. Experiments demonstrate that DA-Cal seamlessly integrates with existing self-training frameworks across multiple UDA segmentation benchmarks, significantly improving target domain calibration while delivering performance gains without inference overhead.

arXiv

Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction

Hao Phung, Hadar Averbuch-Elor

Reconstructing a structured vector-graphics representation from a rasterized floorplan image is typically an important prerequisite for computational tasks involving floorplans such as automated understanding or CAD workflows. However, existing techniques struggle in faithfully generating the structure and semantics conveyed by complex floorplans that depict large indoor spaces with many rooms and a varying numbers of polygon corners. To this end, we propose Raster2Seq, framing floorplan reconstruction as a sequence-to-sequence task in which floorplan elements--such as rooms, windows, and doors--are represented as labeled polygon sequences that jointly encode geometry and semantics. Our approach introduces an autoregressive decoder that learns to predict the next corner conditioned on image features and previously generated corners using guidance from learnable anchors. These anchors represent spatial coordinates in image space, hence allowing for effectively directing the attention mechanism to focus on informative image regions. By embracing the autoregressive mechanism, our method offers flexibility in the output format, enabling for efficiently handling complex floorplans with numerous rooms and diverse polygon structures. Our method achieves state-of-the-art performance on standard benchmarks such as Structure3D, CubiCasa5K, and Raster2Graph, while also demonstrating strong generalization to more challenging datasets like WAFFLE, which contain diverse room structures and complex geometric variations.

arXiv

Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT

Aujasvit Datta, Jiayun Wang, Asad Aali, Anima Anandkumar

Sparse-view Computed Tomography (CT) reconstructs images from a limited number of X-ray projections to reduce radiation and scanning time, which is an ill-posed inverse problem. Existing methods achieve high-fidelity reconstructions but overfit to a fixed acquisition setup, failing to generalize well across sampling rates. For example, convolutional neural networks (CNNs) use the same kernels across resolutions, leading to artifacts when data resolution changes. This is a critical limitation in clinical practice, where acquisition sampling settings vary across organs and diagnostic protocols. We propose Computed Tomography neural Operator (CTO), the first neural operator (NO) framework for CT reconstruction. CTO extends learning from fixed discretized grids to continuous function space, enabling a single model to generalize across measurement sampling rates without retraining. We also propose new NO architectural designs for CT: (i) a dual-domain NO architecture in both sinogram and image spaces, capturing complementary spatial-frequency information, and (ii) rotation-equivariant DIScrete-COntinuous convolutions (DISCO) that exploit the rotational structure inherent in tomographic acquisition. Empirically, CTO outperforms CNNs (> 3.4dB PSNR gain) and other baselines in multi-resolution settings across multiple CT datasets. Compared to state-of-the-art diffusion methods, CTO has 500x faster inference with an average 3dB gain. CTO further demonstrates strong out-of-distribution robustness, maintaining gains under cross-dataset transfer and noisy sinogram conditions. Ablation studies also validate each design choice. CTO establishes neural operators as a principled and practical paradigm for flexible, discretization-agnostic CT reconstruction. Our code is available at https://github.com/neuraloperator/sparse_ct.

arXiv

Direct Visual Grounding by Directing Attention of Visual Tokens

Parsa Esmaeilkhani, Longin Jan Latecki

Vision Language Models (VLMs) mix visual tokens and text tokens. A puzzling issue is the fact that visual tokens most related to the query receive little to no attention in the final layers of the LLM module of VLMs from the answer tokens, where all tokens are treated equally, in particular, visual and language tokens in the LLM attention layers. This fact may result in wrong answers to visual questions, as our experimental results confirm. It appears that the standard next-token prediction (NTP) loss provides an insufficient signal for directing attention to visual tokens. We hypothesize that a more direct supervision of the attention of visual tokens to corresponding language tokens in the LLM module of VLMs will lead to improved performance on visual tasks. To demonstrate that this is indeed the case, we propose a novel loss function that directly supervises the attention of visual tokens. It directly grounds the answer language tokens in images by directing their attention to the relevant visual tokens. This is achieved by aligning the attention distribution of visual tokens to ground truth attention maps with KL divergence. The ground truth attention maps are obtained from task geometry in synthetic cases or from standard grounding annotations (e.g., bounding boxes or point annotations) in real images, and are used inside the LLM for attention supervision without requiring new labels. The obtained KL attention loss (KLAL) when combined with NTP encourages VLMs to attend to relevant visual tokens while generating answer tokens. This results in notable improvements across geometric tasks, pointing, and referring expression comprehension on both synthetic and real-world data, as demonstrated by our experiments. We also introduce a new dataset to evaluate the line tracing abilities of VLMs. Surprisingly, even commercial VLMs do not perform well on this task.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.