arXiv subjects

Haotian Zhang

Publications and source records attributed to Haotian Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

GENMO: A GENeralist Model for Human MOtion

Human motion modeling traditionally separates motion generation and estimation into distinct tasks with specialized models. Motion generation models focus on creating diverse, realistic motions from inputs like text, audio, or keyframes, while motion estimation models aim to reconstruct accurate motion trajectories from observations like videos. Despite sharing underlying representations of temporal dynamics and kinematics, this separation limits knowledge transfer between tasks and requires maintaining separate models. We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework. Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals. Leveraging the synergy between regression and diffusion, GENMO achieves accurate global motion estimation while enabling diverse motion generation. We also introduce an estimation-guided training objective that exploits in-the-wild videos with 2D annotations and text descriptions to enhance generative diversity. Furthermore, our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control. This unified approach creates synergistic benefits: generative priors improve estimated motions under challenging conditions like occlusions, while diverse video data enhances generation capabilities. Extensive experiments demonstrate GENMO's effectiveness as a generalist framework that successfully handles multiple human motion tasks within a single model.

cs.GR↗

arXiv2025

The Fourth Monocular Depth Estimation Challenge

This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.

cs.CV↗

arXiv2025

Learning Switchable Priors for Neural Image Compression

Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the parametric probabilistic distributions. We train the entropy model to predict the index of the appropriate prior within the set, rather than the specific parameters. Switching between the trained priors further enables us to embrace a skip mode into the prior set, which simply omits a latent variable during the entropy coding. To demonstrate the practical value of our solution, we present a lightweight NIC model, namely FastNIC, together with the learning of switchable priors. FastNIC obtains a better trade-off between compression efficiency and computational complexity for neural image compression. We also implanted the switchable priors into state-of-the-art NIC models and observed improved compression efficiency with a significant reduction of entropy coding complexity.

cs.MM↗

arXiv2025

SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM

Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However, replicating these advancements across diverse domains remains challenging due to limited methodological transparency. In this work, we present two-Staged history-Resampling Policy Optimization (SRPO), which surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks. SRPO achieves this using the same base model as DeepSeek (i.e. Qwen2.5-32B), using only about 1/10 of the training steps required by DeepSeek-R1-Zero-32B, demonstrating superior efficiency. Building upon Group Relative Policy Optimization (GRPO), we introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples. Our comprehensive experiments validate the effectiveness of our approach, offering valuable insights into scaling LLM reasoning capabilities across diverse tasks.

cs.LG↗

arXiv2025

Dissecting coupled orders in a terahertz-driven electron-doped cuprate

The interplay between superconductivity and charge density wave has often been studied from an equilibrium point of view. For example, using static tuning knobs such as doping, magnetic field and pressure, superconductivity can be enhanced or suppressed. The resulting effect on the co-existing charge density wave order, if any, is judged by variations in its ground state properties such as the ordering temperature or the spatial correlation. Such an approach can be understood as coordinated static displacements of two coupled order parameters within a Ginzburg-Landau description, evincing their interplay as either co-operative or competing but does not provide further microscopic information about the interaction. In order to assess such information, we dynamically perturb both orders from equilibrium and observe their coupling directly in the time-domain. We show that high-field multicycle terahertz pulses drive both the Higgs amplitude fluctuations of the superconducting order as well as collective fluctuations of the charge order in an electron-doped cuprate, resulting in characteristic third harmonic generation. A notable time delay is manifested between their respective driven dynamics. We propose that this may signify the important energy scale describing their coupling or imply a terahertz field-depinned charge density wave that destroys macroscopic superconductivity. Our work demonstrates a holistic approach for investigating coupled superconducting and charge density wave orders, which may shed novel light on their intertwined presence and widespread fluctuations in many classes of unconventional superconductors.

cond-mat.supr-con↗

arXiv2025

MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA

This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a \textit{global glimpse} step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.

cs.CV↗

arXiv2025

Synesthesia of Machines (SoM)-Enhanced Wideband Multi-User CSI Learning With LiDAR Sensing

Light detection and ranging (LiDAR) has been utilized for optimizing wireless communications due to its ability to detect the environment. This paper explores the use of LiDAR in channel estimation for wideband multi-user multiple-input-multiple-output orthogonal frequency division multiplexing systems and introduces a LiDAR-enhanced Channel State Information (CSI) learning network (LE-CLN). By utilizing user positioning information, LE-CLN first calculates user-localized over-complete angular measurements. It then investigates the correlation between LiDAR and CSI, transforming raw LiDAR data into a low-complexity format embedded with signal propagation characteristics. LE-CLN also adapts the use of LiDAR based on channel conditions through attention mechanisms. Thanks to the unique wireless features offered by LiDAR, LE-CLN achieves higher estimation accuracy and spectrum efficiency compared to benchmarks, particularly in latency-sensitive applications where pilot transmissions are expected to be reduced.

eess.SP↗

arXiv2025

USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s

Image/video coding has been a remarkable research area for both academia and industry for many years. Testing datasets, especially high-quality image/video datasets are desirable for the justified evaluation of coding-related research, practical applications, and standardization activities. We put forward a test dataset namely USTC-TD, which has been successfully adopted in the practical end-to-end image/video coding challenge of the IEEE International Conference on Visual Communications and Image Processing (VCIP) in 2022 and 2023. USTC-TD contains 40 images at 4K spatial resolution and 10 video sequences at 1080p spatial resolution, featuring various content due to the diverse environmental factors (e.g. scene type, texture, motion, view) and the designed imaging factors (e.g. illumination, lens, shadow). We quantitatively evaluate USTC-TD on different image/video features (spatial, temporal, color, lightness), and compare it with the previous image/video test datasets, which verifies its excellent compensation for the shortcomings of existing datasets. We also evaluate both classic standardized and recently learned image/video coding schemes on USTC-TD using objective quality metrics (PSNR, MS-SSIM, VMAF) and subjective quality metric (MOS), providing an extensive benchmark for these evaluated schemes. Based on the characteristics and specific design of the proposed test dataset, we analyze the benchmark performance and shed light on the future research and development of image/video coding. All the data are released online: https://esakak.github.io/USTC-TD.

eess.IV↗

arXiv2025

Synesthesia of Machines (SoM)-Aided FDD Precoding with Sensing Heterogeneity: A Vertical Federated Learning Approach

High complexity in precoding design for frequency division duplex systems necessitates streamlined solutions. Guided by Synesthesia of Machines (SoM), this paper introduces a heterogeneous multi-vehicle, multi-modal sensing aided precoding scheme within a vertical federated learning (VFL) framework, which significantly minimizes pilot sequence length while optimizing the system's sum rate. We address the challenges posed by local data heterogeneity due to varying on-board sensor configurations through a meticulously designed VFL training procedure. To extract valuable channel features from multi-modal sensing, we employ three distinct data preprocessing methods that convert raw data into informative representations relevant for precoding. Additionally, we propose an online training strategy based on VFL framework, enabling the scheme to adapt dynamically to fluctuations in user numbers. Numerical results indicate that our approach, utilizing short pilot sequences, closely approximates the performance of traditional optimization methods with perfect channel state information.

eess.SP↗

arXiv2025

Generalized Gaussian Model for Learned Image Compression

In learned image compression, probabilistic models play an essential role in characterizing the distribution of latent variables. The Gaussian model with mean and scale parameters has been widely used for its simplicity and effectiveness. Probabilistic models with more parameters, such as the Gaussian mixture models, can fit the distribution of latent variables more precisely, but the corresponding complexity is higher. To balance the compression performance and complexity, we extend the Gaussian model to the generalized Gaussian family for more flexible latent distribution modeling, introducing only one additional shape parameter beta than the Gaussian model. To enhance the performance of the generalized Gaussian model by alleviating the train-test mismatch, we propose improved training methods, including beta-dependent lower bounds for scale parameters and gradient rectification. Our proposed generalized Gaussian model, coupled with the improved training methods, is demonstrated to outperform the Gaussian and Gaussian mixture models on a variety of learned image compression networks.

eess.IV↗

arXiv2025

Generative Motion Infilling From Imprecisely Timed Keyframes

Keyframes are a standard representation for kinematic motion specification. Recent learned motion-inbetweening methods use keyframes as a way to control generative motion models, and are trained to generate life-like motion that matches the exact poses and timings of input keyframes. However, the quality of generated motion may degrade if the timing of these constraints is not perfectly consistent with the desired motion. Unfortunately, correctly specifying keyframe timings is a tedious and challenging task in practice. Our goal is to create a system that synthesizes high-quality motion from keyframes, even if keyframes are imprecisely timed. We present a method that allows constraints to be retimed as part of the generation process. Specifically, we introduce a novel model architecture that explicitly outputs a time-warping function to correct mistimed keyframes, and spatial residuals that add pose details. We demonstrate how our method can automatically turn approximately timed keyframe constraints into diverse, realistic motions with plausible timing and detailed submovements.

cs.GR↗

arXiv2025

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

Building a generalist model for user interface (UI) understanding is challenging due to various foundational issues, such as platform diversity, resolution variation, and data limitation. In this paper, we introduce Ferret-UI 2, a multimodal large language model (MLLM) designed for universal UI understanding across a wide range of platforms, including iPhone, Android, iPad, Webpage, and AppleTV. Building on the foundation of Ferret-UI, Ferret-UI 2 introduces three key innovations: support for multiple platform types, high-resolution perception through adaptive scaling, and advanced task training data generation powered by GPT-4o with set-of-mark visual prompting. These advancements enable Ferret-UI 2 to perform complex, user-centered interactions, making it highly versatile and adaptable for the expanding diversity of platform ecosystems. Extensive empirical experiments on referring, grounding, user-centric advanced tasks (comprising 9 subtasks $\times$ 5 platforms), GUIDE next-action prediction dataset, and GUI-World multi-platform benchmark demonstrate that Ferret-UI 2 significantly outperforms Ferret-UI, and also shows strong cross-platform transfer capabilities.

cs.CV↗

arXiv2025

Contrastive Localized Language-Image Pre-Training

Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone of multimodal large language models (MLLMs) to connect image inputs for language interactions. The success of CLIP as a vision-language foundation model relies on aligning web-crawled noisy text annotations at image levels. Nevertheless, such criteria may become insufficient for downstream tasks in need of fine-grained vision representations, especially when region-level understanding is demanding for MLLMs. In this paper, we improve the localization capability of CLIP with several advances. We propose a pre-training method called Contrastive Localized Language-Image Pre-training (CLOC) by complementing CLIP with region-text contrastive loss and modules. We formulate a new concept, promptable embeddings, of which the encoder produces image embeddings easy to transform into region representations given spatial hints. To support large-scale pre-training, we design a visually-enriched and spatially-localized captioning framework to effectively generate region-text pseudo-labels at scale. By scaling up to billions of annotated images, CLOC enables high-quality regional embeddings for image region recognition and retrieval tasks, and can be a drop-in replacement of CLIP to enhance MLLMs, especially on referring and grounding tasks.

cs.CV↗

arXiv2025

The Gap Between Principle and Practice of Lossy Image Coding

Lossy image coding is the art of computing that is principally bounded by the image's rate-distortion function. This bound, though never accurately characterized, has been approached practically via deep learning technologies in recent years. Indeed, learned image coding schemes allow direct optimization of the joint rate-distortion cost, thereby outperforming the handcrafted image coding schemes by a large margin. Still, it is observed that there is room for further improvement in the rate-distortion performance of learned image coding. In this article, we identify the gap between the ideal rate-distortion function forecasted by Shannon's information theory and the empirical rate-distortion function achieved by the state-of-the-art learned image coding schemes, revealing that the gap is incurred by five different effects: modeling effect, approximation effect, amortization effect, digitization effect, and asymptotic effect. We design simulations and experiments to quantitively evaluate the last three effects, which demonstrates the high potential of future lossy image coding technologies.

cs.IT↗

arXiv2025

Few-Shot Domain Adaptation for Learned Image Compression

Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC and observe that out-of-training-domain images disrupt pre-trained channel-wise decomposition. Consequently, we introduce a method for channel-wise re-allocation using convolution-based adapters and low-rank adapters, which are lightweight and compatible to mainstream LIC schemes. Extensive experiments across multiple domains and multiple representative LIC schemes demonstrate that our method significantly enhances pre-trained models, achieving comparable performance to H.266/VVC intra coding with merely 25 target-domain samples. Additionally, our method matches the performance of full-model finetune while transmitting fewer than $2\%$ of the parameters.

eess.IV↗

arXiv2024

Sparse Point Clouds Assisted Learned Image Compression

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few techniques have explored the potential benefits of utilizing inter-modality correlations to enhance the image compression performance. In this paper, motivated by the recent success of learned image compression, we propose a new framework that uses sparse point clouds to assist in learned image compression in the autonomous driving scenario. We first project the 3D sparse point cloud onto a 2D plane, resulting in a sparse depth map. Utilizing this depth map, we proceed to predict camera images. Subsequently, we use these predicted images to extract multi-scale structural features. These features are then incorporated into learned image compression pipeline as additional information to improve the compression performance. Our proposed framework is compatible with various mainstream learned image compression models, and we validate our approach using different existing image compression methods. The experimental results show that incorporating point cloud assistance into the compression pipeline consistently enhances the performance.

cs.CV↗

arXiv2024

Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation

In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency. Our method projects the RGB attributes and semantic features of point clouds onto the image plane, simultaneously rendering RGB images and semantic segmentation results. Leveraging the explicit structure of point clouds and a one-time rendering strategy, our approach significantly enhances efficiency during optimization and rendering. Additionally, we employ SAM2 to generate pseudo-labels for boundary regions, which often lack sufficient supervision, and introduce two-level aggregation losses at the 2D feature map and 3D spatial levels to improve the view-consistent and spatial continuity.

cs.CV↗

arXiv2024

Probabilistic Prior Driven Attention Mechanism Based on Diffusion Model for Imaging Through Atmospheric Turbulence

Atmospheric turbulence introduces severe spatial and geometric distortions, challenging traditional image restoration methods. We propose the Probabilistic Prior Turbulence Removal Network (PPTRN), which combines probabilistic diffusion-based prior modeling with Transformer-driven feature extraction to address this issue. PPTRN employs a two-stage approach: first, a latent encoder and Transformer are jointly trained on clear images to establish robust feature representations. Then, a Denoising Diffusion Probabilistic Model (DDPM) models prior distributions over latent vectors, guiding the Transformer in capturing diverse feature variations essential for restoration. A key innovation in PPTRN is the Probabilistic Prior Driven Cross Attention mechanism, which integrates the DDPM-generated prior with feature embeddings to reduce artifacts and enhance spatial coherence. Extensive experiments validate that PPTRN significantly improves restoration quality on turbulence-degraded images, setting a new benchmark in clarity and structural fidelity.

cs.CV↗