Inertial mass plays a crucial role in robotic applications such as object grasping, manipulation, and simulation, providing a strong prior for planning and control. Accurately estimating an object's mass before interaction can significantly enhance the performance of various robotic tasks. However, mass estimation using only vision sensors is a relatively underexplored area. This paper proposes a novel approach combining sparse point-cloud data from depth images with RGB images to estimate the mass of objects. We evaluate a range of point-cloud processing architectures, alongside RGB-only methods. To overcome the limited availability of training data, we create a synthetic dataset using ShapeNetSem 3D models, simulating RGBD images via a Kinect camera. This synthetic data is used to train an image generation model for estimating dense depth maps, which we then use to augment an existing dataset of images paired with mass values. Our approach significantly outperforms existing benchmarks across all evaluated metrics. The data generation (https://github.com/RavineWindteer/ShapenetSem-to-RGBD) as well as the training of the depth estimator (https://github.com/RavineWindteer/GLPDepth-Edited) and the mass estimator (https://github.com/RavineWindteer/Depth-mass-estimator) are available online.
Hyperspectral image (HSI) classification faces challenges such as high-dimensional data, limited training samples, and spectral redundancy, which often lead to overfitting and insufficient generalization capability. This paper proposes a novel MVNet network architecture that integrates 3D-CNN's local feature extraction, Transformer's global modeling, and Mamba's linear complexity sequence modeling capabilities, achieving efficient spatial-spectral feature extraction and fusion. MVNet features a redesigned dual-branch Mamba module, including a State Space Model (SSM) branch and a non-SSM branch employing 1D convolution with SiLU activation, enhancing modeling of both short-range and long-range dependencies while reducing computational latency in traditional Mamba. The optimized HSI-MambaVision Mixer module overcomes the unidirectional limitation of causal convolution, capturing bidirectional spatial-spectral dependencies in a single forward pass through decoupled attention that focuses on high-value features, alleviating parameter redundancy and the curse of dimensionality. On IN, UP, and KSC datasets, MVNet outperforms mainstream hyperspectral image classification methods in both classification accuracy and computational efficiency, demonstrating robust capability in processing complex HSI data.
Talking Head Generation (THG) has emerged as a transformative technology in computer vision, enabling the synthesis of realistic human faces synchronized with image, audio, text, or video inputs. This paper provides a comprehensive review of methodologies and frameworks for talking head generation, categorizing approaches into 2D--based, 3D--based, Neural Radiance Fields (NeRF)--based, diffusion--based, parameter-driven techniques and many other techniques. It evaluates algorithms, datasets, and evaluation metrics while highlighting advancements in perceptual realism and technical efficiency critical for applications such as digital avatars, video dubbing, ultra-low bitrate video conferencing, and online education. The study identifies challenges such as reliance on pre--trained models, extreme pose handling, multilingual synthesis, and temporal consistency. Future directions include modular architectures, multilingual datasets, hybrid models blending pre--trained and task-specific layers, and innovative loss functions. By synthesizing existing research and exploring emerging trends, this paper aims to provide actionable insights for researchers and practitioners in the field of talking head generation. For the complete survey, code, and curated resource list, visit our GitHub repository: https://github.com/VineetKumarRakesh/thg.
The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.
Recent progress in multimodal reasoning has been significantly advanced by textual Chain-of-Thought (CoT), a paradigm where models conduct reasoning within language. This text-centric approach, however, treats vision as a static, initial context, creating a fundamental "semantic gap" between rich perceptual data and discrete symbolic thought. Human cognition often transcends language, utilizing vision as a dynamic mental sketchpad. A similar evolution is now unfolding in AI, marking a fundamental paradigm shift from models that merely think about images to those that can truly think with images. This emerging paradigm is characterized by models leveraging visual information as intermediate steps in their thought process, transforming vision from a passive input into a dynamic, manipulable cognitive workspace. In this survey, we chart this evolution of intelligence along a trajectory of increasing cognitive autonomy, which unfolds across three key stages: from external tool exploration, through programmatic manipulation, to intrinsic imagination. To structure this rapidly evolving field, our survey makes four key contributions. (1) We establish the foundational principles of the think with image paradigm and its three-stage framework. (2) We provide a comprehensive review of the core methods that characterize each stage of this roadmap. (3) We analyze the critical landscape of evaluation benchmarks and transformative applications. (4) We identify significant challenges and outline promising future directions. By providing this structured overview, we aim to offer a clear roadmap for future research towards more powerful and human-aligned multimodal AI.
Modeling task-driven attention in driving is a fundamental challenge for both autonomous vehicles and cognitive science. Existing methods primarily predict where drivers look by generating spatial heatmaps, but fail to capture the cognitive motivations behind attention allocation in specific contexts, which limits deeper understanding of attention mechanisms. To bridge this gap, we introduce Explainable Driver Attention Prediction, a novel task paradigm that jointly predicts spatial attention regions (where), parses attended semantics (what), and provides cognitive reasoning for attention allocation (why). To support this, we present W3DA, the first large-scale explainable driver attention dataset. It enriches existing benchmarks with detailed semantic and causal annotations across diverse driving scenarios, including normal conditions, safety-critical situations, and traffic accidents. We further propose LLada, a Large Language model-driven framework for driver attention prediction, which unifies pixel modeling, semantic parsing, and cognitive reasoning within an end-to-end architecture. Extensive experiments demonstrate the effectiveness of LLada, exhibiting robust generalization across datasets and driving conditions. This work serves as a key step toward a deeper understanding of driver attention mechanisms, with significant implications for autonomous driving, intelligent driver training, and human-computer interaction.
Image restoration is a key task in low-level computer vision that aims to reconstruct high-quality images from degraded inputs. The emergence of Vision Mamba, which draws inspiration from the advanced state space model Mamba, marks a significant advancement in this field. Vision Mamba demonstrates excellence in modeling long-range dependencies with linear complexity, a crucial advantage for image restoration tasks. Despite its strengths, Vision Mamba encounters challenges in low-level vision tasks, including computational complexity that scales with the number of scanning sequences and local pixel forgetting. To address these limitations, this study introduces Efficient All-Around Mamba (EAMamba), an enhanced framework that incorporates a Multi-Head Selective Scan Module (MHSSM) with an all-around scanning mechanism. MHSSM efficiently aggregates multiple scanning sequences, which avoids increases in computational complexity and parameter count. The all-around scanning strategy implements multiple patterns to capture holistic information and resolves the local pixel forgetting issue. Our experimental evaluations validate these innovations across several restoration tasks, including super resolution, denoising, deblurring, and dehazing. The results validate that EAMamba achieves a significant 31-89% reduction in FLOPs while maintaining favorable performance compared to existing low-level Vision Mamba methods.
In this paper, we, as the DS@GT team for CLEF 2025 CheckThat! Task 4a Scientific Web Discourse Detection, present the methods we explored for this task. For this multiclass classification task, we determined if a tweet contained a scientific claim, a reference to a scientific study or publication, and/or mentions of scientific entities, such as a university or a scientist. We present 3 modeling approaches for this task: transformer finetuning, few-shot prompting of LLMs, and a combined ensemble model whose design was informed by earlier experiments. Our team placed 7th in the competition, achieving a macro-averaged F1 score of 0.8611, an improvement over the DeBERTaV3 baseline of 0.8375. Our code is available on Github at https://github.com/dsgt-arc/checkthat-2025-swd/tree/main/subtask-4a.
Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, especially when guided by explicit chain-of-thought (CoT) reasoning that verbalizes intermediate steps. While CoT improves both interpretability and accuracy, its dependence on natural language reasoning limits the model's expressive bandwidth. Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state, eliminating token-level supervision. To advance latent reasoning research, this survey provides a comprehensive overview of the emerging field of latent reasoning. We begin by examining the foundational role of neural network layers as the computational substrate for reasoning, highlighting how hierarchical representations support complex transformations. Next, we explore diverse latent reasoning methodologies, including activation-based recurrence, hidden state propagation, and fine-tuning strategies that compress or internalize explicit reasoning traces. Finally, we discuss advanced paradigms such as infinite-depth latent reasoning via masked diffusion models, which enable globally consistent and reversible reasoning processes. By unifying these perspectives, we aim to clarify the conceptual landscape of latent reasoning and chart future directions for research at the frontier of LLM cognition. An associated GitHub repository collecting the latest papers and repos is available at: https://github.com/multimodal-art-projection/LatentCoT-Horizon/.
Numerical claims, statements involving quantities, comparisons, and temporal references, pose unique challenges for automated fact-checking systems. In this study, we evaluate modeling strategies for veracity prediction of such claims using the QuanTemp dataset and building our own evidence retrieval pipeline. We investigate three key factors: (1) the impact of more evidences with longer input context windows using ModernBERT, (2) the effect of right-to-left (R2L) tokenization, and (3) their combined influence on classification performance. Contrary to prior findings in arithmetic reasoning tasks, R2L tokenization does not boost natural language inference (NLI) of numerical tasks. A longer context window does also not enhance veracity performance either, highlighting evidence quality as the dominant bottleneck. Our best-performing system achieves competitive macro-average F1 score of 0.57 and places us among the Top-4 submissions in Task 3 of CheckThat! 2025. Our code is available at https://github.com/dsgt-arc/checkthat-2025-numerical.
Diffusion models has underpinned much recent advances of dataset augmentation in various computer vision tasks. However, when involving generating multi-object images as real scenarios, most existing methods either rely entirely on text condition, resulting in a deviation between the generated objects and the original data, or rely too much on the original images, resulting in a lack of diversity in the generated images, which is of limited help to downstream tasks. To mitigate both problems with one stone, we propose a prompt-free conditional diffusion framework for multi-object image augmentation. Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text, and inject knowledge into the diffusion model through LoRA to alleviate the category deviation between the original model and the target dataset. In addition, we design a reward model based counting loss to assist the traditional reconstruction loss for model training. By constraining the object counts of each category instead of pixel-by-pixel constraints, bridging the quantity deviation between the generated data and the original data while improving the diversity of the generated data. Experimental results demonstrate the superiority of the proposed method over several representative state-of-the-art baselines and showcase strong downstream task gain and out-of-domain generalization capabilities. Code is available at \href{https://github.com/00why00/PFCD}{here}.
Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these introduce semantic drift, computational overhead, and cultural misalignment. We introduce NeoBabel, a novel multilingual image generation framework that sets a new Pareto frontier in performance, efficiency and inclusivity, supporting six languages: English, Chinese, Dutch, French, Hindi, and Persian. The model is trained using a combination of large-scale multilingual pretraining and high-resolution instruction tuning. To evaluate its capabilities, we expand two English-only benchmarks to multilingual equivalents: m-GenEval and m-DPG. NeoBabel achieves state-of-the-art multilingual performance while retaining strong English capability, scoring 0.75 on m-GenEval and 0.68 on m-DPG. Notably, it performs on par with leading models on English tasks while outperforming them by +0.11 and +0.09 on multilingual benchmarks, even though these models are built on multilingual base LLMs. This demonstrates the effectiveness of our targeted alignment training for preserving and extending crosslingual generalization. We further introduce two new metrics to rigorously assess multilingual alignment and robustness to code-mixed prompts. Notably, NeoBabel matches or exceeds English-only models while being 2-4x smaller. We release an open toolkit, including all code, model checkpoints, a curated dataset of 124M multilingual text-image pairs, and standardized multilingual evaluation protocols, to advance inclusive AI research. Our work demonstrates that multilingual capability is not a trade-off but a catalyst for improved robustness, efficiency, and cultural fidelity in generative AI.
We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images. Our pipeline combines (i) a fine-tuned Vision Transformer ViTD2PC24All for patch-level inference, (ii) a 4x4 tiling strategy that aligns patch size with the network's 518x518 receptive field, and (iii) domain-prior adaptation through PaCMAP + K-Means visual clustering and geolocation filtering. Tile predictions are aggregated by majority vote and re-weighted with cluster-specific Bayesian priors, yielding a macro-averaged F1 of 0.348 (private leaderboard) while requiring no additional training. All code, configuration files, and reproducibility scripts are publicly available at https://github.com/dsgt-arc/plantclef-2025.
This survey reviews prompt tuning, a parameter-efficient approach for adapting language models by prepending trainable continuous vectors while keeping the model frozen. We classify existing approaches into two categories: direct prompt learning and transfer learning. Direct prompt learning methods include: general optimization approaches, encoder-based methods, decomposition strategies, and mixture-of-experts frameworks. Transfer learning methods consist of: general transfer approaches, encoder-based methods, and decomposition strategies. For each method, we analyze method designs, innovations, insights, advantages, and disadvantages, with illustrative visualizations comparing different frameworks. We identify challenges in computational efficiency and training stability, and discuss future directions in improving training robustness and broadening application scope.
Despite the success of deep learning across various domains, it remains vulnerable to adversarial attacks. Although many existing adversarial attack methods achieve high success rates, they typically rely on $\ell_{p}$-norm perturbation constraints, which do not align with human perceptual capabilities. Consequently, researchers have shifted their focus toward generating natural, unrestricted adversarial examples (UAEs). GAN-based approaches suffer from inherent limitations, such as poor image quality due to instability and mode collapse. Meanwhile, diffusion models have been employed for UAE generation, but they still rely on iterative PGD perturbation injection, without fully leveraging their central denoising capabilities. In this paper, we introduce a novel approach for generating UAEs based on diffusion models, named ScoreAdv. This method incorporates an interpretable adversarial guidance mechanism to gradually shift the sampling distribution towards the adversarial distribution, while using an interpretable saliency map to inject the visual information of a reference image into the generated samples. Notably, our method is capable of generating an unlimited number of natural adversarial examples and can attack not only classification models but also retrieval models. We conduct extensive experiments on ImageNet and CelebA datasets, validating the performance of ScoreAdv across ten target models in both black-box and white-box settings. Our results demonstrate that ScoreAdv achieves state-of-the-art attack success rates and image quality. Furthermore, the dynamic balance between denoising and adversarial perturbation enables ScoreAdv to remain robust even under defensive measures.
Accurate driving behavior recognition and reasoning are critical for autonomous driving video understanding. However, existing methods often tend to dig out the shallow causal, fail to address spurious correlations across modalities, and ignore the ego-vehicle level causality modeling. To overcome these limitations, we propose a novel Multimodal Causal Analysis Model (MCAM) that constructs latent causal structures between visual and language modalities. Firstly, we design a multi-level feature extractor to capture long-range dependencies. Secondly, we design a causal analysis module that dynamically models driving scenarios using a directed acyclic graph (DAG) of driving states. Thirdly, we utilize a vision-language transformer to align critical visual features with their corresponding linguistic expressions. Extensive experiments on the BDD-X, and CoVLA datasets demonstrate that MCAM achieves SOTA performance in visual-language causal relationship learning. Furthermore, the model exhibits superior capability in capturing causal characteristics within video sequences, showcasing its effectiveness for autonomous driving applications. The code is available at https://github.com/SixCorePeach/MCAM.
Cone-Beam Computed Tomography (CBCT) is widely used for intraoperative imaging due to its rapid acquisition and low radiation dose. However, CBCT images typically suffer from artifacts and lower visual quality compared to conventional Computed Tomography (CT). A promising solution is synthetic CT (sCT) generation, where CBCT volumes are translated into the CT domain. In this work, we enhance sCT generation through multimodal learning by jointly leveraging intraoperative CBCT and preoperative CT data. To overcome the inherent misalignment between modalities, we introduce an end-to-end learnable registration module within the sCT pipeline. This model is evaluated on a controlled synthetic dataset, allowing precise manipulation of data quality and alignment parameters. Further, we validate its robustness and generalizability on two real-world clinical datasets. Experimental results demonstrate that integrating registration in multimodal sCT generation improves sCT quality, outperforming baseline multimodal methods in 79 out of 90 evaluation settings. Notably, the improvement is most significant in cases where CBCT quality is low and the preoperative CT is moderately misaligned.
Machine learning methods often struggle with real-world applications in science and engineering due to limited or low-quality training data. In this work, the example of groundwater flow with heat transport is considered; this corresponds to an advection-diffusion process under heterogeneous flow conditions, that is, spatially distributed material parameters and heat sources. Classical numerical simulations are costly and challenging due to high spatio-temporal resolution requirements and large domains. While often computationally more efficient, purely data-driven surrogate models face difficulties, particularly in predicting the advection process, which is highly sensitive to input variations and involves long-range spatial interactions. Therefore, in this work, a Local-Global Convolutional Neural Network (LGCNN) approach is introduced. It combines a lightweight numerical surrogate for the transport process (global) with convolutional neural networks for the groundwater velocity and heat diffusion processes (local). With the LGCNN, a city-wide subsurface temperature field is modeled, involving a heterogeneous groundwater flow field and one hundred groundwater heat pump injection points forming interacting heat plumes over long distances. The model is first systematically analyzed based on random subsurface input fields. Then, the model is trained on a handful of cut-outs from a real-world subsurface map of the Munich region in Germany, and it scales to larger cut-outs without retraining. All datasets, our code, and trained models are published for reproducibility.
Unlike classification, whose goal is to estimate the class of each data point in a dataset, prevalence estimation or quantification is a task that aims to estimate the distribution of classes in a dataset. The two main tasks in prevalence estimation are to adjust for bias, due to the prevalence in the training dataset, and to quantify the uncertainty in the estimate. The standard methods used to quantify uncertainty in prevalence estimates are bootstrapping and Bayesian quantification methods. It is not clear which approach is ideal in terms of precision (i.e. the width of confidence intervals) and coverage (i.e. the confidence intervals being well-calibrated). Here, we propose Precise Quantifier (PQ), a Bayesian quantifier that is more precise than existing quantifiers and with well-calibrated coverage. We discuss the theory behind PQ and present experiments based on simulated and real-world datasets. Through these experiments, we establish the factors which influence quantification precision: the discriminatory power of the underlying classifier; the size of the labeled dataset used to train the quantifier; and the size of the unlabeled dataset for which prevalence is estimated. Our analysis provides deep insights into uncertainty quantification for quantification learning.
We present EdgeCodec, an end-to-end neural compressor for barometric data collected from wind turbine blades. EdgeCodec leverages a heavily asymmetric autoencoder architecture, trained with a discriminator and enhanced by a Residual Vector Quantizer to maximize compression efficiency. It achieves compression rates between 2'560:1 and 10'240:1 while maintaining a reconstruction error below 3%, and operates in real time on the GAP9 microcontroller with bitrates ranging from 11.25 to 45 bits per second. Bitrates can be selected on a sample-by-sample basis, enabling on-the-fly adaptation to varying network conditions. In its highest compression mode, EdgeCodec reduces the energy consumption of wireless data transmission by up to 2.9x, significantly extending the operational lifetime of deployed sensor units.