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

Evidence of Absence: Cross-Modal Abductive Risk Perception to Sustain World Models When Vision Fails

Cong Xu, Ravi Sankar

A structured world-state (entities, relations, context, and predictive cues) is designed to preserve prediction-critical content when perception degrades, but it presumes observations to populate it; when the primary visual modality is occluded or degraded, those observations may be missing. We address how to sustain the world model from a complementary modality by treating the absence of expected co-evidence as evidence of a hidden cause. The abductive framework is modality-agnostic; this article instantiates it acoustically. A microphone-array front-end estimates the bearing of engine and tire sources and extracts approach-rate evidence (Doppler when a stable tone exists, a broadband looming readout otherwise); the event "signature present, visual co-evidence absent" then triggers abductive inference of a hidden road user, emitting a calibrated risk advisory rather than a control command. Recoverability of the hidden state is analyzed as an identifiability question separating shared from modality-unique information, and cueing is cast as Neyman-Pearson detection under an explicit false-alarm budget. On real occluded-approach recordings at blind junctions, the method warns a mean 1.7 seconds before line-of-sight entry, matches the sustained-window variant of the published acoustic baseline's detection rate with 42% fewer false alarms, localizes to 3.4 degrees median once in view, is well calibrated (expected calibration error 0.034), and keeps hazard awareness above 0.87 under staged vision degradation that collapses a vision-only channel to 0.03. We also measure the method's limits: calibration transfers to an unseen junction almost losslessly, the signature classifier does not, and moving-ego noise is the binding deployment constraint.

arXiv

MAD-HOI: Masked Autoregressive Diffusion for Generating Articulated Hand Object Interactions from Text

Ananya Bal, Kartik sharma, Ethan Lai, Samyak Tiwari, Liza Dahiya, Chaitanya Chawla, Laszlo A. Jeni

Methods for text-based generation of hand-object interaction (HOI) sequences primarily focus on producing smooth, physically plausible trajectories. A truly utilitarian method should additionally support variable-length generation, composite motion sequences, motion completion and infilling, and reliable termination without compromising physical plausibility. Standard diffusion models for HOI generation are typically trained only for text-to-motion generation on atomic motions and require the motion length to be specified a-priori. Autoregressive (AR) methods provide greater sequence-level flexibility, but commonly depend on discrete motion codes, which can lose contact-sensitive motion detail. To address these key limitations, we present a model performing Masked Autoregression with Diffusion for HOI generation (MAD-HOI). Our method starts by encoding hand and object motions in a continuous latent space while keeping them disentangled to maintain stream-wise control. This is followed by a masked autoregressive transformer to predict context features that condition a flow-matching head. MAD-HOI is capable of motion generation for atomic and composite articulated sequences, conditioned motion completion and infilling, as well as EOM (End of Motion) prediction from a single training objective. We provide comprehensive evaluations for these capabilities and benchmark our method on the ARCTIC and GRAB datasets. Our experiments demonstrate that our method generates more diverse and physically plausible interactions compared to other open-sourced baseline methods.

arXiv

RMR-P: Road Metadata-Aware Restoration for Pavement Inspection

Amir Ghorbani, Amirali K. Gostar, WeiQin Chuah, Vahid Ghorbani, Aidan Blair, Reza Hoseinnezhad, Alireza Bab-Hadiashar

Road-surface images captured by vehicle-mounted cameras are often degraded by motion blur, defocus, poor illumination, and noise due to vehicle motion, camera limitations, and varying environmental conditions. These degradations can obscure thin cracks and pothole boundaries that are critical for accurate road-defect detection. This paper presents RMR-P, a restoration network designed to recover defect-relevant information from degraded road images. It estimates degradation characteristics from the input image and can optionally incorporate external degradation parameters to guide restoration. To evaluate whether the recovered information improves downstream detection, a clean-trained YOLO11s detector is applied to degraded and restored images without further modification. Experiments on the IVCNZ and PCM datasets, with known synthetic degradation parameters provided as conditioning information, demonstrate that RMR-P achieves the highest mAP50 in seven of eight held-out degradation conditions, including improvements from 0.140 to 0.427 under IVCNZ motion blur and from 0.060 to 0.233 under PCM defocus. Moreover, our ablation studies show that preserving fine pavement details (detail-preserving pathway) provides the largest contribution to defect-detection improvement, while degradation conditioning and task-guided training offer complementary benefits.

arXiv

Tropical Cyclone Forecasting via Latent Rectified Flow using Satellite Imagery and Atmospheric Fields

Meheru Zannat, Sk. Md. Masudul Ahsan

Tropical cyclones are growing more destructive in a changing climate, and efficient forecasting of their structure and track has become a necessity. Deep generative models promise an alternative to computationally expensive numerical weather prediction (NWP), yet current systems produce either satellite imagery or atmospheric fields, never both; they need many sampling steps, putting them out of reach of modest hardware; and their storm tracks come from regression heads with no physical link to the generated atmosphere. This work presents a single-pass model that jointly forecasts GRIDSAT-B1 infrared imagery and four ERA5 atmospheric fields (U-wind, V-wind, air temperature, and surface pressure) out to nine hours. A five-channel variational autoencoder compresses each 5 x 256 x 256 frame to a 4 x 64 x 64 latent, and a conditional rectified-flow UNet with a factorized temporal-attention module predicts the next three frames from three past frames, their best-track coordinates, and timestamps. The model is then reward-fine-tuned (DRaFT) against a differentiable track error derived from the predicted winds through a steering-flow calculation. On held-out 2022 storms the model reaches 16.35 dB PSNR and 0.759 SSIM, ahead of a reproduced cascaded-diffusion baseline at every lead time (+0.84 dB at +9 h) while sampling ~30x faster (56 ms vs. 1673 ms). Track error at +9 h is 62.4 km, 15% below the baseline, and a reward fine-tuning study demonstrates a further 8-11% track-error reduction across sampler budgets.

arXiv

ScratchSim: A Procedural Synthetic Data Pipeline for Surface Scratch Detection

Paul Julius Kühn, Saptarshi Neil Sinha, Tiago Kleist, Richard Hoffmann, Arjan Kuijper, Michael Weinmann

While automated defect detection such as the detection of surface scratched is an important aspect in industrial quality control, the scarcity of annotated defect data make this task challenging. This paper presents a procedural rendering pipeline that generates large-scale annotated synthetic training data using BlenderProc, with configurable material appearance, camera modes, and domain randomization, producing automatic COCO-format annotations. To show the potential of our approach, we evaluate four training strategies, namely synthetic-only, real-only, mixed, and fine-tuning from synthetic weights, across two objects with different material properties and three lightweight edge-deployable detectors, YOLOX, YOLO26, and LW-DETR. Our evaluation show that fine-tuning from synthetic weights consistently outperforms real-only training, and that mixed training effectively recovers performance under scarce real-data conditions, with findings validated across both convolutional and transformer-based architectures. The proposed approach enables scalable defect detection without the burden of large real annotated datasets, making it practical for on-device industrial inspection. The pipeline scripts for generating synthetic scratches, 3D model, and both the synthetic and real annotated scratch datasets for a glossy toy Ferrari car are publicly available at https://github.com/saptarshineil/ScratchSim.

arXiv

WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis

Danilo Danese, Angela Lombardi, Giuseppe Fasano, Matteo Attimonelli, Tommaso Di Noia

Large and demographically balanced datasets are essential for reliable neuroimaging biomarkers. Full-resolution 3D brain MRI synthesis can support data augmentation in this setting, but existing approaches either incur prohibitive computational cost at volumetric scale or rely on lossy latent compression that may compromise anatomical detail. As a result, practical 3D generative augmentation often requires specialized compute infrastructure. We propose WaveDiT, a conditional flow matching framework operating in the coefficient space of a 3D Haar Discrete Wavelet Transform. The model combines factorized spatio-depth attention with band-wise heteroscedastic uncertainty modeling derived from higher-order wavelet statistics. Predicted log-variance is integrated directly into both the flow objective and conditioning pathway, enabling adaptive precision consistent with the heavy-tailed and input-dependent variance structure of anatomical detail. This formulation supports full-resolution 3D synthesis under practical memory and time constraints on a single modern GPU. Evaluation on a multi-site cohort demonstrates improved alignment between generated and real MRI distributions, together with enhanced downstream brain age prediction and region-level anatomical agreement relative to diffusion, latent, and wavelet-based baselines. Code is available at https://github.com/sisinflab/WaveDiT

arXiv

Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

Tri Cao, Khoi Le, Thong Nguyen, Cong-Duy Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng YAN, Bryan Hooi

While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We argue this stems from a failure in spatio-temporal monitoring, the ability to persistently track object identities, states, and relations over time. Existing benchmarks obscure this deficit by relying on single final-answer evaluations for queries that can often be resolved via local visual cues or statistical priors. To rigorously diagnose this, we introduce STEMO-Bench (Spatio-TEmporal MOnitoring), a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness. To address failure modes exposed by STEMO, we propose STEMO-Track, a novel object-centric framework that explicitly constructs and reasons over structured object trajectories via chunk-wise state extraction and temporal aggregation. Extensive experiments demonstrate that our object-centric framework significantly reduces hallucinated answers and improves spatio-temporal reasoning consistency over state-of-the-art MLLMs.

arXiv

Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset

Yuhai Deng, Huimin She, Wei Shen, Meng Li, Ruoxi Wu, Lunxi Yuan, Xiang Li

Tone style transfer for photo retouching aims to adapt the stylistic tone of the reference image to a given content image. However, the lack of high-quality large-scale triplet datasets with stylized ground truth forces existing methods to rely on self-supervised or proxy objectives, which limits model capability. To mitigate this gap, we design a data construction pipeline to build TST100K, a large-scale dataset of 100,000 content-reference-stylized triplets. At the core of this pipeline, we train a tone style scorer to ensure strict stylistic consistency for each triplet. In addition, existing methods typically extract content and reference features independently and then fuse them in a decoder, which may cause semantic loss and lead to inappropriate color transfer and degraded visual aesthetics. Instead, we propose ICTone, a diffusion-based framework that performs tone transfer in an in-context manner by jointly conditioning on both images, leveraging the semantic priors of generative models for semantic-aware transfer. Reward feedback learning using the tone style scorer is further incorporated to improve stylistic fidelity and visual quality. Experiments demonstrate the effectiveness of TST100K, and ICTone achieves state-of-the-art performance on both quantitative metrics and human evaluations. The project page is available online: https://dengyuhai.github.io/ICTone_Project/.

arXiv

PIEDet: Prototype-Driven Intrinsically Explainable Object Detection

Jianlin Xiang, Linhui Dai, Xue Yang, Chaolei Yang, Yanshan Li

Existing object detectors typically make predictions in a black-box manner and struggle to simultaneously provide discriminative evidence for their predictions, which limits their deployment in safety-critical scenarios. To explain model predictions, existing post-hoc explanation methods mostly rely on gradient-based or perturbation-based operators. These methods not only introduce additional memory and computational overhead but also make it difficult to ensure that the generated explanations faithfully reflect the model's internal decision-making process. To address these limitations, we propose PIEDet, a prototype-driven intrinsically explainable object detection framework. PIEDet innovatively embeds class prototypes as explicit discriminative units into the classification branch of a one-stage detector, thereby improving detection performance while providing intrinsic interpretability. First, PIEDet constructs hierarchical class prototypes at different detection levels, enabling the model to learn scale-aware class-semantic representations. Second, we propose a prototype-driven feature learning method consisting of prototype regularization and a region-to-prototype matching loss. The former enhances the inter-class discriminability of the prototypes, while the latter encourages prototype responses to focus on object regions. Finally, we introduce a scale-aligned hierarchical prototype supervision mechanism that assigns scale-matched supervision signals to different detection levels, thereby enhancing the scale specificity of the hierarchical prototypes. On the ExDark, RTTS, and VOC2012-FOG datasets, PIEDet improves mAP@0.5 over the baseline by 4.7%, 1.6%, and 4.8%, respectively, while demonstrating superior computational efficiency. Compared with mainstream post-hoc explanation methods, PIEDet achieves a better balance between explanation quality and explanation cost.

arXiv

Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding

Zhenghao Xie, Jing Xiao, Zhenqi Wang, Kexin Ma, Liang Liao, Gui-song Xia, Mi Wang

Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of spatial detail. While low-resolution (LR) imagery enables efficient global observation, high-resolution (HR) imagery provides critical local details at a much higher acquisition cost and with limited coverage. This motivates a cross-scale sensing strategy that selectively acquires HR imagery guided by LR-based global perception to improve task performance under constrained cost. Existing HR sampling methods typically make selection decisions from isolated LR patches, thereby ignoring fine-grained intra-patch importance and cross-patch contextual interactions, leading to fragmented feature representation and suboptimal scene reasoning under sparse HR observations. To address this issue, we formulate cross-scale remote sensing understanding as a unified cost-aware problem that couples fine-grained HR sampling with cross-patch representation prediction, enabling more effective task reasoning with fewer HR observations. Furthermore, we present GL-10M, a high- and low-resolution dataset with nearly 100,000 scene pairs and 10 million images for large-scale cross-resolution pretraining. Extensive experiments on recognition and retrieval tasks show that our method consistently achieves a superior performance-cost trade-off. The code is publicly available at https://github.com/xzhacc/CrossSO.

arXiv

RAIN-FIT: Learning of Fitting Surfaces and Noise Distribution from Large Data Sets

Omar M. Sleem, Sahand Kiani, Constantino M. Lagoa

This paper proposes a method for estimating a surface that contains a given set of points from noisy measurements. More precisely, by assuming that the surface is described by the zero set of a function in the span of a given set of features and a parametric description of the distribution of the noise, a computationally efficient method is described that estimates both the surface and the noise distribution parameters. In the provided examples, polynomial and sinusoidal basis functions were used. However, any chosen basis that satisfies the outlined conditions mentioned in the paper can be approximated as a combination of trigonometric, exponential, and/or polynomial terms, making the presented approach highly generalizable. The proposed algorithm exhibits linear computational complexity in the number of samples. Our approach requires no hyperparameter tuning or data preprocessing and effectively handles data in dimensions beyond 2D and 3D. The theoretical results demonstrating the convergence of the proposed algorithm have been provided. To highlight the performance of the proposed method, comprehensive numerical results are conducted, evaluating our method against state-of-the-art algorithms, including Poisson Reconstruction and the Neural Network-based Encoder-X, on 2D and 3D shapes. The results demonstrate the superiority of our method under the same conditions.

arXiv

MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation

Ruiyao Liu, Hui Shen, Ping Zhang, Yunta Hsieh, Yifan Zhang, Jing Xu, Qi Han, Junchen Li, Jiawei Lu, Jianing Ma, Jiaqi Mo, Sicheng Chen, Zhen Zhang, Zhongwei Wan, Jing Xiong, Xin Wang, Ziyuan Liu, Hangrui Cao, Ngai Wong

Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed visually through diagrams, plots, geometric constructions, and structured symbolic layouts, where correctness depends on precise visual composition. This naturally raises the question of whether generative models can still do so when the answer must be rendered visually rather than written in text? To study this problem, we introduce MathGen, a rigorous benchmark of 420 problems spanning seven core domains, including 350 Clean-Scene problems and 70 paired Open-Scene problems. Each problem is evaluated under a Script-as-a-Judge protocol with problem-specific verification criteria implemented through reusable executable scripts for deterministic and reproducible evaluation. Experiments on representative open-source and proprietary text-to-image models show that mathematical fidelity remains a major bottleneck: even the best closed-source model reaches only 53.7% overall accuracy, while open-source models achieve just 1--11%, often near 0% on structured tasks, particularly those requiring precise geometric and functional rendering. Overall, current T2I models remain far from reliable at even elementary mathematical visual generation.

arXiv

DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification

Kenji Tojo, Bernd Bickel, Nobuyuki Umetani

Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics hardware. However, efficient online transmission and rendering across diverse platforms requires drastic model simplification, reducing the number of primitives by several orders of magnitude. We introduce DiffSoup, a radiance field representation that employs a soup (i.e., a highly unstructured set) of a small number of triangles with neural textures and binary opacity. We show that this binary opacity representation is directly differentiable via stochastic opacity masking, enabling stable training without a mollifier (i.e., smooth rasterization). DiffSoup can be rasterized using standard depth testing, enabling seamless integration into traditional graphics pipelines and interactive rendering on consumer-grade laptops and mobile devices. Code is available at https://github.com/kenji-tojo/diffsoup.

arXiv

DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis

Hongjin Niu, Jiahao Wang, Xirui Hu, Weizhan Zhang, Lan Ma, Yuan Gao, Feng Lei

Text-to-image models often struggle to synthesize correct occlusion relationships among multiple objects, especially in densely overlapping regions. Many training-free layout-guided methods enforce 2D spatial constraints but do not explicitly resolve depth-dependent attention competition, which can cause concept mixing and implausible occlusion. To address this problem, we propose DepthArb, a training-free framework that formulates occlusion generation as attention arbitration within a unified denoising trajectory. DepthArb employs two core occlusion-control mechanisms: Attention Arbitration Modulation suppresses background-object attention within foreground support according to relative depth, while Spatial Compactness Control limits attention dispersion to preserve object coherence. Because interference varies during generation, Occlusion Conflict Estimation constructs a shared spatial conflict field to adaptively weight both objectives. Through a unified spatial-text attention interface, DepthArb operates on U-Net cross-attention and the image-to-text component of MMDiT joint attention without model retraining. We further introduce OcclBench, a benchmark with continuous relative-depth specifications and occlusion-specific evaluation metrics. Experiments on OcclBench and public benchmarks show that DepthArb improves several layout and occlusion metrics over the evaluated baselines while maintaining competitive text-image alignment.

arXiv

FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion

Hugo Caselles-Dupré, Mathis Koroglu, Guillaume Jeanneret, Arnaud Dapogny, Matthieu Cord

Diffusion-based image-to-video (I2V) models are increasingly effective, yet they struggle to scale to ultra-high-resolution inputs (e.g., 4K). Generating videos at the model's native resolution often loses fine-grained structure, whereas high-resolution tiled denoising preserves local detail but breaks global layout consistency. This failure mode is particularly severe in the fresco animation setting: monumental artworks containing many distinct characters, objects, and semantically different sub-scenes that must remain spatially coherent over time. We introduce FrescoDiffusion, a training-free method for coherent large-format I2V generation from a single complex image. The key idea is to augment tiled denoising with a precomputed latent prior: we first generate a low-resolution video at the underlying model resolution and upsample its latent trajectory to obtain a global reference that captures long-range temporal and spatial structure. For 4K generation, we compute per-tile noise predictions and fuse them with this reference at every diffusion timestep by minimizing a single weighted least-squares objective in model-output space. The objective combines a standard tile-merging criterion with our regularization term, yielding a closed-form fusion update that strengthens global coherence while retaining fine detail. We additionally provide a spatial regularization variable that enables region-level control over where motion is allowed. Experiments on the VBench-I2V dataset and our proposed fresco I2V dataset show improved global consistency and fidelity over tiled baselines, while being computationally efficient. Our regularization enables explicit controllability of the trade-off between creativity and consistency.

arXiv

Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs

Yiwei Li, Yifan Zhou, Huaqin Zhao, Zihao Wu, Zhengliang Liu, Xiang Li, Quanzheng Li, Tianming Liu, Lin Zhao

Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be suboptimal for visually grounded radiology tasks. Radiologists instead diagnose via sequential visual search; eye-tracking captures this process as time-ordered gaze trajectories that reveal how evidence is acquired over time. We use eye-gaze as supervision to guide VLM reasoning by introducing a small set of dedicated gaze tokens. These tokens are trained to predict gaze-selected image patch indices in temporal order, encouraging the model to follow human-like evidence acquisition and integration. Experiments on MIMIC-EYE and multiple external zero-shot benchmarks show consistent gains over baselines, achieving state-of-the-art in-domain performance and improved out-of-domain robustness. These results highlight temporally ordered gaze as an effective supervision signal for learning visually grounded medical reasoning.

arXiv

Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues

Marco Willi, Melanie Mathys, Michael Graber

Recent generative models produce near-photorealistic images, challenging the trustworthiness of photographs. Synthetic image detection (SID) methods, however, often struggle to generalize across datasets and generative models. CLIP, which embeds images and text in a shared semantic space, performs well at SID, but the cues underlying its decisions remain poorly understood. We therefore study CLIP-based SID as an empirical interpretability problem rather than proposing a new detector. We introduce SynthCLIC, which pairs real photographs with caption-matched, high-quality diffusion-generated counterparts. We evaluate CLIP-based detectors on SynthCLIC, a GAN-heavy benchmark, and a broad external benchmark, and compare them with a low-level forensic CNN, a broad-generator detector, and a text-grounded concept model. CLIP-based linear detectors reach 0.96 mAP on the GAN-heavy benchmark but 0.92 on SynthCLIC, while cross-family transfer to CNNSpot falls to 0.42 mAP. Within-class associations between detector scores and text-derived cue scores show that higher synthetic scores correspond to cleaner, more compositionally controlled, and technically polished images, whereas lower scores correspond to messier capture conditions and provenance cues characteristic of real photographs. These associations are distributed across many overlapping cues, and their profiles differ strongly across training datasets. CLIP-based and forensic detectors therefore fail in different ways and provide complementary evidence, while broad generator coverage appears important for robust SID.

arXiv

DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection

Amirhossein Khadivi Noghredeh, Abdollah Safari, Fatemeh Ziaeetabar, Firoozeh Haghighi

Anomaly detection in industrial visual inspection is challenging due to the scarcity of defective samples. Most existing methods rely on unsupervised reconstruction using only normal data, often resulting in overfitting and poor detection of subtle defects. We propose a semi-supervised deep reinforcement learning framework that integrates a neural batch sampler, an autoencoder, and a predictor. The RL-based sampler adaptively selects informative patches by balancing exploration and exploitation through a composite reward. The autoencoder generates loss profiles highlighting abnormal regions, while the predictor performs segmentation in the loss-profile space. This interaction enables the system to effectively learn both normal and defective patterns with limited labeled data. Experiments on the MVTec AD dataset demonstrate that our method achieves higher accuracy and better localization of subtle anomalies than recent state-of-the-art approaches while maintaining low complexity, yielding an average improvement of 0.15 in F1_max and 0.06 in AUC, with a maximum gain of 0.37 in F1_max in the best case.

arXiv

Comprehensive language-image pre-training for 3D medical image understanding

Tassilo Wald, Ibrahim Ethem Hamamci, Yuan Gao, Sam Bond-Taylor, Harshita Sharma, Maximilian Ilse, Cynthia Lo, Olesya Melnichenko, Anton Schwaighofer, Noel C. F. Codella, Maria Teodora Wetscherek, Klaus H. Maier-Hein, Panagiotis Korfiatis, Valentina Salvatelli, Javier Alvarez-Valle, Fernando Pérez-García

In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports. While the methodology holds promise, three challenges limit the capabilities of current 3D VLEs: data scarcity due to privacy concerns, high computational costs resulting from the volumetric nature of the images, and a domain shift between the long reports used for training and the short prompts used during inference for, e.g., zero-shot classification. As a consequence, natural-image VLE recipes do not directly transfer to 3D medical imaging. In this paper, we overcome these challenges by injecting additional supervision via a report generation objective and combining vision-language with vision-only pre-training, allowing us to leverage both image-only and paired image-text 3D datasets. Further, we propose a novel loss that addresses the domain shift between long reports and short textual prompts. Through these additional objectives, paired with best practices of the 3D medical imaging domain, we develop the Comprehensive Language-Image Pre-training (COLIPRI) encoder family. Our COLIPRI encoders achieve state-of-the-art performance in report generation, semantic segmentation, classification probing, and zero-shot classification. The model weights and inference code are freely available at https://huggingface.co/microsoft/colipri.

arXiv

Dissecting Embodied Abilities in Multimodal Language Models through Skill-level Evaluation and Diagnosis

Yu Qi, Haibo Zhao, Ziyu Guo, Siyuan Ma, Ziyan Chen, Yaokun Han, Renrui Zhang, Zitiantao Lin, Yizhe Zhu, Shiji Xin, Yijian Huang, Boce Hu, Kai Cheng, Peiheng Wang, jiazheng liu, Jiayi Zhang, Wenqing Wang, Yiran Qin, Haojie Huang, Lawson L. S. Wong

Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, existing embodied benchmarks mainly focus on task-level evaluation and fail to provide actionable insights into the underlying causes of model failures. To address this limitation, we introduce BEAR, a benchmark that decomposes embodied tasks into 14 atomic skills for fine-grained skill-level evaluation. BEAR comprises 4,469 interleaved image-video-text samples spanning 14 skills across 6 categories, ranging from low-level perception to high-level planning. We evaluate 20 MLLMs on BEAR under a hierarchical skill-level diagnosis framework and uncover two key findings: (1) perceptual capabilities are major bottlenecks behind reasoning failures, and (2) current models suffer from unstable spatiotemporal modeling that remains largely unexposed in prior benchmarks. Motivated by these findings, we further propose BEAR-Agent, a multimodal conversational agent that augments MLLMs with visual and spatial reasoning tools. BEAR-Agent substantially improves performance across embodied skills, achieving a relative improvement of 17.5% on GPT-5 over the base model on BEAR, while also outperforming strong baselines in both simulation and real-world robotic experiments. Project page: https://bear-official66.github.io/

Keep browsing

More papers from top AI conferences

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