arXiv subjects

Zhongyu Jiang

Publications and source records attributed to Zhongyu Jiang.

At least 19 recordsLinked to original sources

arXiv2026

Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning

Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments. By generating intermediate reasoning images, Visual CoT provides an intuitive mechanism for visual foresight but introduces substantial inference overhead, which is particularly problematic for proactive video reasoning. We ask whether models can learn to think visually during training while reasoning directly at inference. We introduce Internalized Visual Thinking (IVT), a post-training framework that jointly optimizes textual prediction and next-embedding prediction over unlabeled videos. Given a partially observed video, IVT predicts latent representations of future frames together with the target textual answer, encouraging the model to capture motion, object transitions, interactions, and latent intent. At inference, IVT generates the answer directly without synthesizing or re-encoding future frames. We conduct controlled studies across target representations, decoder designs, prediction horizons, data mixtures, training curricula, and predictive objectives. IVT improves over direct-answer fine-tuning on all six evaluation settings while retaining the same inference pathway. Compared with explicit Visual CoT, IVT achieves comparable or better performance and reduces average end-to-end latency by more than 5x. Together, our findings suggest that explicit pixel-space generation at inference time, as used in visual chain-of-thought, may not be necessary for effective proactive video reasoning. Predictive world modeling can be internalized during training to produce multimodal reasoners that are both more accurate and substantially more efficient.

cs.CV↗

arXiv2026

On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual reasoning benchmarks, they remain vulnerable to weak visual grounding, hallucinations, and over-reliance on textual cues. We show that simple, controlled textual perturbations, including misleading captions or incorrect chain-of-thought (CoT) traces, cause substantial drops in robustness and confidence, and that these effects are more pronounced when CoT consistency is taken into account across open-source multimodal reasoning models. In contrast, closed models exhibit similar failure modes but maintain markedly greater robustness and reasoning consistency, suggesting that the gap reflects a shortcoming in current open-source RL finetuning rather than an inherent limitation of the task. To better understand these vulnerabilities, we further analyze RL finetuning dynamics and uncover an accuracy-faithfulness trade-off: finetuning raises benchmark accuracy, but can simultaneously erode the reliability of the accompanying CoT and its robustness to contextual shifts. Although adversarial augmentation improves robustness, it does not by itself prevent faithfulness drift. Incorporating a faithfulness-aware reward can restore alignment between answers and reasoning, but when paired with augmentation, training risks collapsing onto shortcut strategies and robustness remains elusive. Together, these findings highlight the limitations of accuracy-only evaluations and motivate training and assessment protocols that jointly emphasize correctness, robustness, and the faithfulness of visually grounded reasoning.

cs.LG↗

arXiv2025

UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning

In recent years, there has been a growing interest in developing effective alignment pipelines to generate unified representations from different modalities for multi-modal fusion and generation. As an important component of Human-Centric applications, Human Pose representations are critical in many downstream tasks, such as Human Pose Estimation, Action Recognition, Human-Computer Interaction, Object tracking, etc. Human Pose representations or embeddings can be extracted from images, 2D keypoints, 3D skeletons, mesh models, and lots of other modalities. Yet, there are limited instances where the correlation among all of those representations has been clearly researched using a contrastive paradigm. In this paper, we propose UniHPR, a unified Human Pose Representation learning pipeline, which aligns Human Pose embeddings from images, 2D and 3D human poses. To align more than two data representations at the same time, we propose a novel singular value-based contrastive learning loss, which better aligns different modalities and further boosts performance. To evaluate the effectiveness of the aligned representation, we choose 2D and 3D Human Pose Estimation (HPE) as our evaluation tasks. In our evaluation, with a simple 3D human pose decoder, UniHPR achieves remarkable performance metrics: MPJPE 49.9mm on the Human3.6M dataset and PA-MPJPE 51.6mm on the 3DPW dataset with cross-domain evaluation. Meanwhile, we are able to achieve 2D and 3D pose retrieval with our unified human pose representations in Human3.6M dataset, where the retrieval error is 9.24mm in MPJPE.

cs.CV↗

arXiv2025

The Role of Deductive and Inductive Reasoning in Large Language Models

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning tasks, yet their reliance on static prompt structures and limited adaptability to complex scenarios remains a significant challenge. In this paper, we propose the Deductive and InDuctive(DID) method, a novel framework that enhances LLM reasoning by dynamically integrating both deductive and inductive reasoning approaches. Drawing from cognitive science principles, DID implements a dual-metric complexity evaluation system that combines Littlestone dimension and information entropy to precisely assess task difficulty and guide decomposition strategies. DID enables the model to progressively adapt its reasoning pathways based on problem complexity, mirroring human cognitive processes. We evaluate DID's effectiveness across multiple benchmarks, including the AIW and MR-GSM8K, as well as our custom Holiday Puzzle dataset for temporal reasoning. Our results demonstrate significant improvements in reasoning quality and solution accuracy - achieving 70.3% accuracy on AIW (compared to 62.2% for Tree of Thought) while maintaining lower computational costs. The success of DID in improving LLM performance while preserving computational efficiency suggests promising directions for developing more cognitively aligned and capable language models. Our work contributes a theoretically grounded, input-centric approach to enhancing LLM reasoning capabilities, offering an efficient alternative to traditional output-exploration methods.

cs.AI↗

arXiv2025

Bayesian Optimization for Controlled Image Editing via LLMs

In the rapidly evolving field of image generation, achieving precise control over generated content and maintaining semantic consistency remain significant limitations, particularly concerning grounding techniques and the necessity for model fine-tuning. To address these challenges, we propose BayesGenie, an off-the-shelf approach that integrates Large Language Models (LLMs) with Bayesian Optimization to facilitate precise and user-friendly image editing. Our method enables users to modify images through natural language descriptions without manual area marking, while preserving the original image's semantic integrity. Unlike existing techniques that require extensive pre-training or fine-tuning, our approach demonstrates remarkable adaptability across various LLMs through its model-agnostic design. BayesGenie employs an adapted Bayesian optimization strategy to automatically refine the inference process parameters, achieving high-precision image editing with minimal user intervention. Through extensive experiments across diverse scenarios, we demonstrate that our framework significantly outperforms existing methods in both editing accuracy and semantic preservation, as validated using different LLMs including Claude3 and GPT-4.

cs.CV↗

arXiv2025

Human Motion Instruction Tuning

This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning. In contrast to conventional instruction-tuning approaches that convert non-linguistic inputs, such as video or motion sequences, into language tokens, LLaMo retains motion in its native form for instruction tuning. This method preserves motion-specific details that are often diminished in tokenization, thereby improving the model's ability to interpret complex human behaviors. By processing both video and motion data alongside textual inputs, LLaMo enables a flexible, human-centric analysis. Experimental evaluations across high-complexity domains, including human behaviors and professional activities, indicate that LLaMo effectively captures domain-specific knowledge, enhancing comprehension and prediction in motion-intensive scenarios. We hope LLaMo offers a foundation for future multimodal AI systems with broad applications, from sports analytics to behavioral prediction. Our code and models are available on the project website: https://github.com/ILGLJ/LLaMo.

cs.AI↗

arXiv2025

PackDiT: Joint Human Motion and Text Generation via Mutual Prompting

Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models.

cs.CV↗

arXiv2025

MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking

In the field of multi-object tracking (MOT), traditional methods often rely on the Kalman filter for motion prediction, leveraging its strengths in linear motion scenarios. However, the inherent limitations of these methods become evident when confronted with complex, nonlinear motions and occlusions prevalent in dynamic environments like sports and dance. This paper explores the possibilities of replacing the Kalman filter with a learning-based motion model that effectively enhances tracking accuracy and adaptability beyond the constraints of Kalman filter-based tracker. In this paper, our proposed method MambaMOT and MambaMOT+, demonstrate advanced performance on challenging MOT datasets such as DanceTrack and SportsMOT, showcasing their ability to handle intricate, non-linear motion patterns and frequent occlusions more effectively than traditional methods.

cs.CV↗

arXiv2024

Graph Canvas for Controllable 3D Scene Generation

Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined datasets, and struggle to adapt dynamically to changing spatial relationships. In this paper, we introduce GraphCanvas3D, a programmable, extensible, and adaptable framework for controllable 3D scene generation. Leveraging in-context learning, GraphCanvas3D enables dynamic adaptability without the need for retraining, supporting flexible and customizable scene creation. Our framework employs hierarchical, graph-driven scene descriptions, representing spatial elements as graph nodes and establishing coherent relationships among objects in 3D environments. Unlike conventional approaches, which are constrained in adaptability and often require predefined input masks or retraining for modifications, GraphCanvas3D allows for seamless object manipulation and scene adjustments on the fly. Additionally, GraphCanvas3D supports 4D scene generation, incorporating temporal dynamics to model changes over time. Experimental results and user studies demonstrate that GraphCanvas3D enhances usability, flexibility, and adaptability for scene generation. Our code and models are available on the project website: https://github.com/ILGLJ/Graph-Canvas.

cs.CV↗

arXiv2024

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOT$_{\text{ext}}$ and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments.

cs.CV↗

arXiv2024

GTA: Global Tracklet Association for Multi-Object Tracking in Sports

Multi-object tracking in sports scenarios has become one of the focal points in computer vision, experiencing significant advancements through the integration of deep learning techniques. Despite these breakthroughs, challenges remain, such as accurately re-identifying players upon re-entry into the scene and minimizing ID switches. In this paper, we propose an appearance-based global tracklet association algorithm designed to enhance tracking performance by splitting tracklets containing multiple identities and connecting tracklets seemingly from the same identity. This method can serve as a plug-and-play refinement tool for any multi-object tracker to further boost their performance. The proposed method achieved a new state-of-the-art performance on the SportsMOT dataset with HOTA score of 81.04%. Similarly, on the SoccerNet dataset, our method enhanced multiple trackers' performance, consistently increasing the HOTA score from 79.41% to 83.11%. These significant and consistent improvements across different trackers and datasets underscore our proposed method's potential impact on the application of sports player tracking. We open-source our project codebase at https://github.com/sjc042/gta-link.git.

cs.CV↗

arXiv2024

ToddlerAct: A Toddler Action Recognition Dataset for Gross Motor Development Assessment

Assessing gross motor development in toddlers is crucial for understanding their physical development and identifying potential developmental delays or disorders. However, existing datasets for action recognition primarily focus on adults, lacking the diversity and specificity required for accurate assessment in toddlers. In this paper, we present ToddlerAct, a toddler gross motor action recognition dataset, aiming to facilitate research in early childhood development. The dataset consists of video recordings capturing a variety of gross motor activities commonly observed in toddlers aged under three years old. We describe the data collection process, annotation methodology, and dataset characteristics. Furthermore, we benchmarked multiple state-of-the-art methods including image-based and skeleton-based action recognition methods on our datasets. Our findings highlight the importance of domain-specific datasets for accurate assessment of gross motor development in toddlers and lay the foundation for future research in this critical area. Our dataset will be available at https://github.com/ipl-uw/ToddlerAct.

cs.CV↗

arXiv2024

ScalingGaussian: Enhancing 3D Content Creation with Generative Gaussian Splatting

The creation of high-quality 3D assets is paramount for applications in digital heritage preservation, entertainment, and robotics. Traditionally, this process necessitates skilled professionals and specialized software for the modeling, texturing, and rendering of 3D objects. However, the rising demand for 3D assets in gaming and virtual reality (VR) has led to the creation of accessible image-to-3D technologies, allowing non-professionals to produce 3D content and decreasing dependence on expert input. Existing methods for 3D content generation struggle to simultaneously achieve detailed textures and strong geometric consistency. We introduce a novel 3D content creation framework, ScalingGaussian, which combines 3D and 2D diffusion models to achieve detailed textures and geometric consistency in generated 3D assets. Initially, a 3D diffusion model generates point clouds, which are then densified through a process of selecting local regions, introducing Gaussian noise, followed by using local density-weighted selection. To refine the 3D gaussians, we utilize a 2D diffusion model with Score Distillation Sampling (SDS) loss, guiding the 3D Gaussians to clone and split. Finally, the 3D Gaussians are converted into meshes, and the surface textures are optimized using Mean Square Error(MSE) and Gradient Profile Prior(GPP) losses. Our method addresses the common issue of sparse point clouds in 3D diffusion, resulting in improved geometric structure and detailed textures. Experiments on image-to-3D tasks demonstrate that our approach efficiently generates high-quality 3D assets.

cs.CV↗

arXiv2024

RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark

Traditional methods for human localization and pose estimation (HPE), which mainly rely on RGB images as an input modality, confront substantial limitations in real-world applications due to privacy concerns. In contrast, radar-based HPE methods emerge as a promising alternative, characterized by distinctive attributes such as through-wall recognition and privacy-preserving, rendering the method more conducive to practical deployments. This paper presents a Radar Tensor-based human pose (RT-Pose) dataset and an open-source benchmarking framework. The RT-Pose dataset comprises 4D radar tensors, LiDAR point clouds, and RGB images, and is collected for a total of 72k frames across 240 sequences with six different complexity-level actions. The 4D radar tensor provides raw spatio-temporal information, differentiating it from other radar point cloud-based datasets. We develop an annotation process using RGB images and LiDAR point clouds to accurately label 3D human skeletons. In addition, we propose HRRadarPose, the first single-stage architecture that extracts the high-resolution representation of 4D radar tensors in 3D space to aid human keypoint estimation. HRRadarPose outperforms previous radar-based HPE work on the RT-Pose benchmark. The overall HRRadarPose performance on the RT-Pose dataset, as reflected in a mean per joint position error (MPJPE) of 9.91cm, indicates the persistent challenges in achieving accurate HPE in complex real-world scenarios. RT-Pose is available at https://huggingface.co/datasets/uwipl/RT-Pose.

cs.CV↗

arXiv2024

MPM: A Unified 2D-3D Human Pose Representation via Masked Pose Modeling

Estimating 3D human poses only from a 2D human pose sequence is thoroughly explored in recent years. Yet, prior to this, no such work has attempted to unify 2D and 3D pose representations in the shared feature space. In this paper, we propose \mpm, a unified 2D-3D human pose representation framework via masked pose modeling. We treat 2D and 3D poses as two different modalities like vision and language and build a single-stream transformer-based architecture. We apply two pretext tasks, which are masked 2D pose modeling, and masked 3D pose modeling to pre-train our network and use full-supervision to perform further fine-tuning. A high masking ratio of $71.8~\%$ in total with a spatio-temporal mask sampling strategy leads to better relation modeling both in spatial and temporal domains. \mpm~can handle multiple tasks including 3D human pose estimation, 3D pose estimation from occluded 2D pose, and 3D pose completion in a \textbf{single} framework. We conduct extensive experiments and ablation studies on several widely used human pose datasets and achieve state-of-the-art performance on MPI-INF-3DHP.

cs.CV↗

arXiv2024

Tree Counting by Bridging 3D Point Clouds with Imagery

Accurate and consistent methods for counting trees based on remote sensing data are needed to support sustainable forest management, assess climate change mitigation strategies, and build trust in tree carbon credits. Two-dimensional remote sensing imagery primarily shows overstory canopy, and it does not facilitate easy differentiation of individual trees in areas with a dense canopy and does not allow for easy separation of trees when the canopy is dense. We leverage the fusion of three-dimensional LiDAR measurements and 2D imagery to facilitate the accurate counting of trees. We compare a deep learning approach to counting trees in forests using 3D airborne LiDAR data and 2D imagery. The approach is compared with state-of-the-art algorithms, like operating on 3D point cloud and 2D imagery. We empirically evaluate the different methods on the NeonTreeCount data set, which we use to define a tree-counting benchmark. The experiments show that FuseCountNet yields more accurate tree counts.

cs.CV↗

arXiv2024

A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video

Dense object counting or crowd counting has come a long way thanks to the recent development in the vision community. However, indiscernible object counting, which aims to count the number of targets that are blended with respect to their surroundings, has been a challenge. Image-based object counting datasets have been the mainstream of the current publicly available datasets. Therefore, we propose a large-scale dataset called YoutubeFish-35, which contains a total of 35 sequences of high-definition videos with high frame-per-second and more than 150,000 annotated center points across a selected variety of scenes. For benchmarking purposes, we select three mainstream methods for dense object counting and carefully evaluate them on the newly collected dataset. We propose TransVidCount, a new strong baseline that combines density and regression branches along the temporal domain in a unified framework and can effectively tackle indiscernible object counting with state-of-the-art performance on YoutubeFish-35 dataset.

cs.CV↗

arXiv2023

UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning

In recent times, there has been a growing interest in developing effective perception techniques for combining information from multiple modalities. This involves aligning features obtained from diverse sources to enable more efficient training with larger datasets and constraints, as well as leveraging the wealth of information contained in each modality. 2D and 3D Human Pose Estimation (HPE) are two critical perceptual tasks in computer vision, which have numerous downstream applications, such as Action Recognition, Human-Computer Interaction, Object tracking, etc. Yet, there are limited instances where the correlation between Image and 2D/3D human pose has been clearly researched using a contrastive paradigm. In this paper, we propose UniHPE, a unified Human Pose Estimation pipeline, which aligns features from all three modalities, i.e., 2D human pose estimation, lifting-based and image-based 3D human pose estimation, in the same pipeline. To align more than two modalities at the same time, we propose a novel singular value based contrastive learning loss, which better aligns different modalities and further boosts the performance. In our evaluation, UniHPE achieves remarkable performance metrics: MPJPE $50.5$mm on the Human3.6M dataset and PAMPJPE $51.6$mm on the 3DPW dataset. Our proposed method holds immense potential to advance the field of computer vision and contribute to various applications.

cs.CV↗