arXiv subjects

Ruobing Zheng

Publications and source records attributed to Ruobing Zheng.

17 recordsLinked to original sources

arXiv2026

Jovian Zonal Winds Revealed from Cassini/VIMS Observations

Understanding Jupiter's zonal winds is crucial to unraveling the dynamics of its atmosphere. Over the last decades, multiple data sources and techniques have been used to study zonal winds in Jupiter. Here, we develop a correlation-based method for the near-infrared data from the Cassini spacecraft to investigate zonal winds at different altitudes. The new method uses Jupiter's rotation to scan the planet as it rotates, allowing retrieval of winds from the analysis of light-curves of specific pixels over the Jovian disc. The method allows the retrieval of winds at multiple wavelengths from the Cassini/VIMS spectral data despite the low spatial resolution and the non-uniform cadence of the data. By applying this method to two VIMS data cubes acquired on 15 January 2001 at 09:42 UT and 16 January 2001 at 03:22 UT, we reveal the zonal winds at five main latitudes using information from three different wavebands, as well as the wind vertical structure at the equator, showing significant vertical wind shear in the troposphere. The vertical wind shear we derived is weaker than as reported in previous studies, highlighting the intricate interactions among multiple dynamical processes in Jupiter's atmosphere and reflecting the complexity of its atmospheric circulation. Despite the uncertainty due to the low spatial/temporal resolution and non-uniform cadence of the Cassini/VIMS-IR spectral data, the new method established in this study maximizes the value of the Cassini/VIMS in understanding Jupiter's zonal winds. Further observations are essential to explore the underlying mechanisms in Jupiter's atmosphere.

astro-ph.EP↗

arXiv2026

Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM Training

Reasoning post-training improves Large Language Models (LLMs) on complex tasks such as mathematics and coding, but its benefits across diverse multimodal tasks remains uncertain. The trend of releasing parallel "Instruct" and "Thinking" models by leading teams is both resource-intensive and user-unfriendly. Prior work finds that the gains from reasoning training are influenced by multiple factors, such as base model capabilities, task characteristics, and Chain-of-Thought (CoT) data quality. However, principled criteria for determining when reasoning post-training is beneficial and which data should support it are still lacking. In this paper, we propose Dual Tuning, a reasoning efficacy-driven data curation framework for multimodal LLMs training. Given a target task and a base model, Dual Tuning jointly evaluates whether the training data is beneficial and whether reasoning training with current CoT content yields positive gains over non-reasoning alternatives. We apply Dual Tuning across spatial, mathematical, and multi-disciplinary tasks, and further analyze how reinforcement learning and thinking patterns affect reasoning efficacy. The Dual Tuning results guide data curation by identifying data that benefit reasoning training, data better suited to direct-answer training, and data that are detrimental under both training modes. Our work provides quantitative criteria for selecting appropriate training data and matching post-training strategies.

cs.CL↗

arXiv2025

Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation

We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which only 6.1 billion are active per token. This architecture enables highly efficient scaling (dramatically improving computational efficiency while significantly expanding model capacity) and empowers stronger unified multimodal intelligence across vision, speech, and language, representing a key step toward Artificial General Intelligence (AGI). Compared to its predecessor, the upgraded version exhibits substantial improvements across multimodal understanding and generation. Notably, it achieves strong performance on vision-language understanding benchmarks, with overall scores on par with Gemini 2.5 Pro, and enables seamless switching among multimodal tasks in multi-turn interactions. In speech, it achieves strong performance in contextual and dialect-aware ASR while enabling joint, continuous-generation of speech, sound, and music. In vision, it introduces generative semantic segmentation that achieves competitive standalone performance and enhances spatial control and editing consistency, alongside marked improvements in identity preservation, and high-fidelity in-image text rendering. Together, these capabilities demonstrate that a single unified model can serve as a practical foundation for general-purpose multimodal intelligence.

cs.CV↗

arXiv2025

HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

While Multimodal Large Language Models (MLLMs) show immense promise for achieving truly human-like interactions, progress is hindered by the lack of fine-grained evaluation frameworks for human-centered scenarios, encompassing both the understanding of complex human intentions and the provision of empathetic, context-aware responses. Here we introduce HumanSense, a comprehensive benchmark designed to evaluate the human-centered perception and interaction capabilities of MLLMs, with a particular focus on deep understanding of extended multimodal contexts and the formulation of rational feedback. Our evaluation reveals that leading MLLMs still have considerable room for improvement, particularly for advanced interaction-oriented tasks. Supplementing visual input with audio and text information yields substantial improvements, and Omni-modal models show advantages on these tasks.Furthermore, grounded in the observation that appropriate feedback stems from a contextual analysis of the interlocutor's needs and emotions, we posit that reasoning ability serves as the key to unlocking it. We devise a multi-stage, modality-progressive reinforcement learning approach, resulting in HumanSense-Omni-Reasoning, which substantially enhances performance on higher-level understanding and interactive tasks. Additionally, we observe that successful reasoning processes appear to exhibit consistent thought patterns. By designing corresponding prompts, we also enhance the performance of non-reasoning models in a training-free manner.Project page: \textcolor{brightpink}{https://digital-avatar.github.io/ai/HumanSense/}

cs.CV↗

arXiv2025

Versatile Multimodal Controls for Expressive Talking Human Animation

In filmmaking, directors typically allow actors to perform freely based on the script before providing specific guidance on how to present key actions. AI-generated content faces similar requirements, where users not only need automatic generation of lip synchronization and basic gestures from audio input but also desire semantically accurate and expressive body movement that can be ``directly guided'' through text descriptions. Therefore, we present VersaAnimator, a versatile framework that synthesizes expressive talking human videos from arbitrary portrait images. Specifically, we design a motion generator that produces basic rhythmic movements from audio input and supports text-prompt control for specific actions. The generated whole-body 3D motion tokens can animate portraits of various scales, producing talking heads, half-body gestures and even leg movements for whole-body images. Besides, we introduce a multi-modal controlled video diffusion that generates photorealistic videos, where speech signals govern lip synchronization, facial expressions, and head motions while body movements are guided by the 2D poses. Furthermore, we introduce a token2pose translator to smoothly map 3D motion tokens to 2D pose sequences. This design mitigates the stiffness resulting from direct 3D to 2D conversion and enhances the details of the generated body movements. Extensive experiments shows that VersaAnimator synthesizes lip-synced and identity-preserving videos while generating expressive and semantically meaningful whole-body motions.

cs.CV↗

arXiv2025

M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning

Recent advancements in Multimodal Large Language Models (MLLMs), particularly through Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced their reasoning abilities. However, a critical gap persists: these models struggle with dynamic spatial interactions, a capability essential for real-world applications. To bridge this gap, we introduce M2-Reasoning-7B, a model designed to excel in both general and spatial reasoning. Our approach integrates two key innovations: (1) a novel data pipeline that generates 294.2K high-quality data samples (168K for cold-start fine-tuning and 126.2K for RLVR), which feature logically coherent reasoning trajectories and have undergone comprehensive assessment; and (2) a dynamic multi-task training strategy with step-wise optimization to mitigate conflicts between data, and task-specific rewards for delivering tailored incentive signals. This combination of curated data and advanced training allows M2-Reasoning-7B to set a new state-of-the-art (SOTA) across 8 benchmarks, showcasing superior performance in both general and spatial reasoning domains.

cs.AI↗

arXiv2025

EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

Recent work on human animation usually incorporates large-scale video models, thereby achieving more vivid performance. However, the practical use of such methods is hindered by the slow inference speed and high computational demands. Moreover, traditional work typically employs separate models for each animation task, increasing costs in multi-task scenarios and worsening the dilemma. To address these limitations, we introduce EchoMimicV3, an efficient framework that unifies multi-task and multi-modal human animation. At the core of EchoMimicV3 lies a threefold design: a Soup-of-Tasks paradigm, a Soup-of-Modals paradigm, and a novel training and inference strategy. The Soup-of-Tasks leverages multi-task mask inputs and a counter-intuitive task allocation strategy to achieve multi-task gains without multi-model pains. Meanwhile, the Soup-of-Modals introduces a Coupled-Decoupled Multi-Modal Cross Attention module to inject multi-modal conditions, complemented by a Multi-Modal Timestep Phase-aware Dynamical Allocation mechanism to modulate multi-modal mixtures. Besides, we propose Negative Direct Preference Optimization, Phase-aware Negative Classifier-Free Guidance (CFG), and Long Video CFG, which ensure stable training and inference. Extensive experiments and analyses demonstrate that EchoMimicV3, with a minimal model size of 1.3 billion parameters, achieves competitive performance in both quantitative and qualitative evaluations.

cs.CV↗

arXiv2024

LokiTalk: Learning Fine-Grained and Generalizable Correspondences to Enhance NeRF-based Talking Head Synthesis

Despite significant progress in talking head synthesis since the introduction of Neural Radiance Fields (NeRF), visual artifacts and high training costs persist as major obstacles to large-scale commercial adoption. We propose that identifying and establishing fine-grained and generalizable correspondences between driving signals and generated results can simultaneously resolve both problems. Here we present LokiTalk, a novel framework designed to enhance NeRF-based talking heads with lifelike facial dynamics and improved training efficiency. To achieve fine-grained correspondences, we introduce Region-Specific Deformation Fields, which decompose the overall portrait motion into lip movements, eye blinking, head pose, and torso movements. By hierarchically modeling the driving signals and their associated regions through two cascaded deformation fields, we significantly improve dynamic accuracy and minimize synthetic artifacts. Furthermore, we propose ID-Aware Knowledge Transfer, a plug-and-play module that learns generalizable dynamic and static correspondences from multi-identity videos, while simultaneously extracting ID-specific dynamic and static features to refine the depiction of individual characters. Comprehensive evaluations demonstrate that LokiTalk delivers superior high-fidelity results and training efficiency compared to previous methods. The code will be released upon acceptance.

cs.CV↗

arXiv2024

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Character image animation, which generates high-quality videos from a reference image and target pose sequence, has seen significant progress in recent years. However, most existing methods only apply to human figures, which usually do not generalize well on anthropomorphic characters commonly used in industries like gaming and entertainment. Our in-depth analysis suggests to attribute this limitation to their insufficient modeling of motion, which is unable to comprehend the movement pattern of the driving video, thus imposing a pose sequence rigidly onto the target character. To this end, this paper proposes Animate-X, a universal animation framework based on LDM for various character types (collectively named X), including anthropomorphic characters. To enhance motion representation, we introduce the Pose Indicator, which captures comprehensive motion pattern from the driving video through both implicit and explicit manner. The former leverages CLIP visual features of a driving video to extract its gist of motion, like the overall movement pattern and temporal relations among motions, while the latter strengthens the generalization of LDM by simulating possible inputs in advance that may arise during inference. Moreover, we introduce a new Animated Anthropomorphic Benchmark (A^2Bench) to evaluate the performance of Animate-X on universal and widely applicable animation images. Extensive experiments demonstrate the superiority and effectiveness of Animate-X compared to state-of-the-art methods.

cs.CV↗

arXiv2024

Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis

Recent advances in diffusion models have endowed talking head synthesis with subtle expressions and vivid head movements, but have also led to slow inference speed and insufficient control over generated results. To address these issues, we propose Ditto, a diffusion-based talking head framework that enables fine-grained controls and real-time inference. Specifically, we utilize an off-the-shelf motion extractor and devise a diffusion transformer to generate representations in a specific motion space. We optimize the model architecture and training strategy to address the issues in generating motion representations, including insufficient disentanglement between motion and identity, and large internal discrepancies within the representation. Besides, we employ diverse conditional signals while establishing a mapping between motion representation and facial semantics, enabling control over the generation process and correction of the results. Moreover, we jointly optimize the holistic framework to enable streaming processing, real-time inference, and low first-frame delay, offering functionalities crucial for interactive applications such as AI assistants. Extensive experimental results demonstrate that Ditto generates compelling talking head videos and exhibits superiority in both controllability and real-time performance.

cs.CV↗

arXiv2024

StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models

Despite the burst of innovative methods for controlling the diffusion process, effectively controlling image styles in text-to-image generation remains a challenging task. Many adapter-based methods impose image representation conditions on the denoising process to accomplish image control. However these conditions are not aligned with the word embedding space, leading to interference between image and text control conditions and the potential loss of semantic information from the text prompt. Addressing this issue involves two key challenges. Firstly, how to inject the style representation without compromising the effectiveness of text representation in control. Secondly, how to obtain the accurate style representation from a single reference image. To tackle these challenges, we introduce StyleTokenizer, a zero-shot style control image generation method that aligns style representation with text representation using a style tokenizer. This alignment effectively minimizes the impact on the effectiveness of text prompts. Furthermore, we collect a well-labeled style dataset named Style30k to train a style feature extractor capable of accurately representing style while excluding other content information. Experimental results demonstrate that our method fully grasps the style characteristics of the reference image, generating appealing images that are consistent with both the target image style and text prompt. The code and dataset are available at https://github.com/alipay/style-tokenizer.

cs.CV↗

arXiv2024

Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis

Recent works in implicit representations, such as Neural Radiance Fields (NeRF), have advanced the generation of realistic and animatable head avatars from video sequences. These implicit methods are still confronted by visual artifacts and jitters, since the lack of explicit geometric constraints poses a fundamental challenge in accurately modeling complex facial deformations. In this paper, we introduce Dynamic Tetrahedra (DynTet), a novel hybrid representation that encodes explicit dynamic meshes by neural networks to ensure geometric consistency across various motions and viewpoints. DynTet is parameterized by the coordinate-based networks which learn signed distance, deformation, and material texture, anchoring the training data into a predefined tetrahedra grid. Leveraging Marching Tetrahedra, DynTet efficiently decodes textured meshes with a consistent topology, enabling fast rendering through a differentiable rasterizer and supervision via a pixel loss. To enhance training efficiency, we incorporate classical 3D Morphable Models to facilitate geometry learning and define a canonical space for simplifying texture learning. These advantages are readily achievable owing to the effective geometric representation employed in DynTet. Compared with prior works, DynTet demonstrates significant improvements in fidelity, lip synchronization, and real-time performance according to various metrics. Beyond producing stable and visually appealing synthesis videos, our method also outputs the dynamic meshes which is promising to enable many emerging applications.

cs.CV↗

arXiv2023

DC-Former: Diverse and Compact Transformer for Person Re-Identification

In person re-identification (re-ID) task, it is still challenging to learn discriminative representation by deep learning, due to limited data. Generally speaking, the model will get better performance when increasing the amount of data. The addition of similar classes strengthens the ability of the classifier to identify similar identities, thereby improving the discrimination of representation. In this paper, we propose a Diverse and Compact Transformer (DC-Former) that can achieve a similar effect by splitting embedding space into multiple diverse and compact subspaces. Compact embedding subspace helps model learn more robust and discriminative embedding to identify similar classes. And the fusion of these diverse embeddings containing more fine-grained information can further improve the effect of re-ID. Specifically, multiple class tokens are used in vision transformer to represent multiple embedding spaces. Then, a self-diverse constraint (SDC) is applied to these spaces to push them away from each other, which makes each embedding space diverse and compact. Further, a dynamic weight controller(DWC) is further designed for balancing the relative importance among them during training. The experimental results of our method are promising, which surpass previous state-of-the-art methods on several commonly used person re-ID benchmarks.

cs.CV↗

arXiv2022

Statistical Study on the Sources of Jovian Decametric Radio Emissions Based on the Radio Observations of Remote Instruments

To better understand the physical processes associated with Jovian decametric (DAM) radio emissions, we present the statistical study of DAMs and inferred characteristics of DAM sources based on multi-view observation from Wind and STEREO spacecraft. The distribution of the apparent rotation speed of DAMs derived from multiple spacecraft suggests that the rotation speed of Io-related DAMs is in range of 0.15-0.6Ω_J and that of non-Io-DAMs is between 0.7-1.2Ω_J. Based on the method of Wang et al. (2020), we locate the sources of the DAMs and infer their emission angles and associated electron energies. The statistical results show that the DAM source locations have three preferred regions, two in the southern hemisphere and one in the northern hemisphere, which is probably caused by the non-symmetrical topology of Jupiter's magnetic field. The difference between Io-DAM source footprints and Io auroral spots changes with the Io's position in longitude, consistent with the previous results from Hess et al. (2010), Bonfond et al. (2017) and Hinton et al. (2019). In addition, the emission angles for non-Io-DAMs are smaller than that for Io-DAMs from the same source regions and all the emission angles range from 60° to 85°. Correspondingly, the electron energy is mainly distributed between 0.5 and 20 keV.

astro-ph.EP↗

arXiv2021

HBReID: Harder Batch for Re-identification

Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away. However, the selected samples are not the hardest globally, but the hardest only in a mini-batch, which will affect the performance. In this report, a hard batch mining method is proposed to mine the hardest samples globally to make triplet harder. More specifically, the most similar classes are selected into a same mini-batch so that the similar classes could be pushed further away. Besides, an adversarial scene removal module composed of a scene classifier and an adversarial loss is used to learn scene invariant feature representations. Experiments are conducted on dataset MSMT17 to prove the effectiveness, and our method surpasses all of the previous methods and sets state-of-the-art result.

cs.CV↗

arXiv2021

A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual News Anchors

Lip sync has emerged as a promising technique for generating mouth movements from audio signals. However, synthesizing a high-resolution and photorealistic virtual news anchor is still challenging. Lack of natural appearance, visual consistency, and processing efficiency are the main problems with existing methods. This paper presents a novel lip-sync framework specially designed for producing high-fidelity virtual news anchors. A pair of Temporal Convolutional Networks are used to learn the cross-modal sequential mapping from audio signals to mouth movements, followed by a neural rendering network that translates the synthetic facial map into a high-resolution and photorealistic appearance. This fully trainable framework provides end-to-end processing that outperforms traditional graphics-based methods in many low-delay applications. Experiments also show the framework has advantages over modern neural-based methods in both visual appearance and efficiency.

cs.CV↗

arXiv2019

Joint Ranking SVM and Binary Relevance with Robust Low-Rank Learning for Multi-Label Classification

Multi-label classification studies the task where each example belongs to multiple labels simultaneously. As a representative method, Ranking Support Vector Machine (Rank-SVM) aims to minimize the Ranking Loss and can also mitigate the negative influence of the class-imbalance issue. However, due to its stacking-style way for thresholding, it may suffer error accumulation and thus reduces the final classification performance. Binary Relevance (BR) is another typical method, which aims to minimize the Hamming Loss and only needs one-step learning. Nevertheless, it might have the class-imbalance issue and does not take into account label correlations. To address the above issues, we propose a novel multi-label classification model, which joints Ranking support vector machine and Binary Relevance with robust Low-rank learning (RBRL). RBRL inherits the ranking loss minimization advantages of Rank-SVM, and thus overcomes the disadvantages of BR suffering the class-imbalance issue and ignoring the label correlations. Meanwhile, it utilizes the hamming loss minimization and one-step learning advantages of BR, and thus tackles the disadvantages of Rank-SVM including another thresholding learning step. Besides, a low-rank constraint is utilized to further exploit high-order label correlations under the assumption of low dimensional label space. Furthermore, to achieve nonlinear multi-label classifiers, we derive the kernelization RBRL. Two accelerated proximal gradient methods (APG) are used to solve the optimization problems efficiently. Extensive comparative experiments with several state-of-the-art methods illustrate a highly competitive or superior performance of our method RBRL.

cs.LG↗