8935 papers
MindDriver is a novel progressive multimodal reasoning framework that bridges the gap between semantic understanding and physical trajectory planning for autonomous driving by introducing a human-like thinking process, supported by a feedback-guided data annotation pipeline and progressive reinforcement fine-tuning, which achieves superior performance in both open-loop and closed-loop evaluations.
This paper introduces GLoTran, a global-local dual perception framework for MLLMs that combines low-resolution global context with multi-scale region-level details to overcome challenges in high-resolution text-rich image translation, supported by the newly constructed large-scale GLoD dataset.
This paper proposes a globally-aware edge prioritization framework for Structure-from-Motion pose graph initialization that leverages a GNN to predict edge reliability and guide a connectivity-aware construction process, resulting in more accurate and compact 3D reconstructions compared to existing retrieval-based methods.
Dream-SLAM is a novel monocular active SLAM method that enhances localization accuracy, mapping quality, and exploration efficiency in dynamic environments by "dreaming" cross-spatio-temporal images and semantically plausible structures to mitigate data incompleteness and enable long-horizon planning.
This paper introduces PanoEnv, a large-scale 3D spatial reasoning benchmark for panoramic images, and proposes a curriculum-based reinforcement learning framework with GRPO that significantly enhances the 3D spatial intelligence of Vision-Language Models, achieving state-of-the-art performance on omnidirectional perception tasks.
The paper proposes WoG (World Guidance), a framework that enhances Vision-Language-Action models by training them to simultaneously predict future actions and compact condition representations derived from future observations, thereby achieving superior fine-grained action generation and generalization in both simulation and real-world environments.
This paper addresses the challenges of Kilometer Marker Recognition for autonomous metro trains in complex environments by proposing a robust multi-modal method that adapts a pre-trained RGB OCR foundation model to event camera data and introducing the first large-scale synchronized RGB-Event dataset, EvMetro5K, to validate the approach.
This paper introduces RT-RMOT, a new task for all-day referring multi-object tracking, along with the first RGB-Thermal dataset (RefRT) and the RTrack framework, which leverages a multimodal large language model enhanced by Group Sequence Policy Optimization and specialized reward strategies to achieve robust tracking in challenging low-visibility conditions.
The paper introduces SPGen, a novel deep learning model that utilizes unsupervised domain adaptation and stochastic sampling to accurately predict human eye movement scanpaths on paintings, thereby advancing the analysis and preservation of cultural heritage.
AutoSew is a fully automatic, geometry-based framework that utilizes Graph Neural Networks and optimal transport to predict stitch correspondences directly from 2D pattern contours, achieving high accuracy in assembling garments without relying on manual annotations or semantic cues.
The paper proposes NESTOR, a nested Mixture-of-Experts neural operator that combines image-level and token-level expert modules to capture both global and local dependencies, thereby enabling effective large-scale pre-training across diverse PDE systems and enhancing generalization to downstream tasks.
AdaSpot is a novel framework for precise event spotting that enhances efficiency and localization accuracy by processing low-resolution videos globally while adaptively selecting and analyzing high-resolution regions of interest through an unsupervised, task-aware strategy, achieving state-of-the-art performance on standard benchmarks.
WeatherCity is a novel framework that enables flexible, high-fidelity, and temporally consistent 4D urban scene reconstruction with controllable multi-weather transformations by combining text-guided image editing, a shared-feature weather Gaussian representation, and a physics-driven dynamic model.
The paper introduces Brain3D, a specialized vision-language framework that converts 2D pretrained encoders into native 3D architectures to automate neuroradiology report generation from brain tumor MRIs, achieving significantly higher clinical accuracy and perfect specificity on healthy scans compared to 2D baselines through a three-stage alignment process.
The paper introduces GeoDiv, a novel framework leveraging large language and vision-language models to systematically measure and reveal significant geographical biases and socio-economic stereotypes in text-to-image generation, demonstrating how current models disproportionately portray countries like India, Nigeria, and Colombia in impoverished ways.
The paper presents Lumosaic, a compact active hyperspectral video system that synchronizes a narrowband LED array with coded-exposure pixels to achieve real-time, high-fidelity 31-channel video reconstruction of dynamic scenes, significantly outperforming existing passive snapshot methods in both spectral accuracy and temporal stability.
WeaveTime is a model-agnostic framework that addresses the time-agnostic limitations of current Video-LLMs in streaming scenarios by introducing a lightweight Temporal Reconstruction objective to instill order-aware representations and a Past-Current Dynamic Focus Cache for uncertainty-triggered retrieval, thereby improving accuracy and reducing latency without architectural changes.
This paper introduces MedTri, a deployable framework that normalizes heterogeneous medical reports into structured, anatomy-grounded triplets to remove stylistic noise and significantly enhance the performance and generalizability of medical vision-language pretraining across X-ray and CT modalities.
This paper introduces NoLan, a training-free framework that mitigates object hallucinations in Large Vision-Language Models by identifying language decoder priors as the primary cause and dynamically suppressing them during decoding.
CASR is a robust, single-model cyclic framework for arbitrary-scale super-resolution that mitigates cross-scale distribution shifts and texture inconsistencies by reformulating ultra-magnification as a sequence of in-distribution transitions guided by structural alignment and self-similarity priors.