arXiv subjects

Lingting Zhu

Publications and source records attributed to Lingting Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Policy and World Modeling Co-Training for Language Agents

Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do to the environment. World modeling (WM) can fill this gap, yet existing approaches often require separate simulators, extra training stages, or additional inference-time computation. We observe that on-policy RL rollouts already contain the needed signal: each transition pairs an action with its resulting next observation. Based on this observation, we propose PaW, a Policy and World modeling co-training framework that adds auxiliary WM supervision to the same policy during RL, without changing the inference paradigm. To make auxiliary WM supervision informative and stable, PaW introduces three components: action-entropy-based WM data selection, noise-tolerant WM loss, and reward-adaptive loss balancing. Experiments on three agentic task benchmarks show consistent improvements over strong RL baselines across models and RL algorithms. These results suggest that standard RL rollouts are a practical source of WM supervision for language-agent training.

cs.LG↗

arXiv2026

CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport

While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maximize dispersion. However, in 3D environments, this approach frequently drops representative prototype tokens in favor of outliers, breaking the multi-view consistencies and geometric structures essential for spatial reasoning. In this paper, we propose a paradigm shift for 3D VLM token pruning: from maximizing diversity to preserving visual evidence coverage. We introduce CoverPrune, a training-free framework that formulates inference-time token pruning as an Optimal Transport (OT) problem. To overcome the intractable combinatorial subset selection inherent in this formulation, we design the Feature-Spatial-Temporal (FST) transport cost and target capacity, along with an efficient Spatial-Guided Greedy Selection (SGS) algorithm to approximate the OT objective. Furthermore, we propose CoverPrune-Lite, an accelerated variant utilizing spatially structured local matching for minimal overhead. Extensive experiments across multiple 3D visual-spatial reasoning benchmarks demonstrate that our methods achieve state-of-the-art token efficiency, maintaining robust reasoning performance even under highly aggressive pruning budgets. Visit our project website at https://github.com/Brucess/CoverPrune.

cs.CV↗

arXiv2026

MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction

High-fidelity 3D generative modeling increasingly relies on the latent diffusion paradigm, where the reconstruction quality of the underlying 3D VAE becomes a primary bottleneck. Existing approaches largely follow two paradigms: sparse voxel-based representations achieve strong reconstruction quality but incur significant memory and computational overhead, while set-based representations are compact and continuous yet typically lag in fidelity due to latent sparsity and excessive global smoothness. We propose MSVS-VAE, a hierarchical set-based VAE that closes this fidelity gap without sacrificing compactness. Our key idea is to progressively densify anchored VecSet latents via hierarchical point-shuffle upsampling, increasing spatial capacity for fine-grained geometry modeling. To efficiently decode from the densified hierarchy, we replace global cross-attention with AVS-Conv, a geometry-aware local aggregation operator operating within local neighborhoods rather than the exhaustive latent set. We further introduce multi-scale query decoding to fuse coarse-to-fine latent features, where coarse scales provide stable global context, and fine scales refine localized geometry, reducing artifacts from overly local receptive fields. Extensive experiments on Objaverse, ABO, and in-the-wild benchmarks demonstrate that MSVS-VAE consistently outperforms prior set-based and voxel-based VAEs, delivering approximately 10x faster decoding than prior set-based methods and approximately 10x higher compactness than voxel-based baselines.

cs.CV↗

arXiv2026

OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per (agent, game) pair, focus on single-agent Solo play, and lack unified protocols for evaluating heterogeneous agent classes (commercial VLMs, open-weight VLMs, and specialized game policies) on the same footing. We address these gaps with OmniGameArena, a real-time benchmark of twelve newly built Unreal Engine 5 games spanning Solo (7), PvP (3), and Coop (2) with unified action interfaces, and the Improvement Dynamics Curve (IDC), an agentic-reflection harness in which a tool-using reflector LLM autonomously refines a bounded skill prompt across multiple rounds. Beyond cold-start leaderboard scores, IDC exposes two additional observables for each (agent, game) pair: how the score evolves across reflection rounds, and how the learned skill behaves on held-out task variants. We report these observables for twelve VLM agents on the cold-start leaderboard and four top agents under IDC.

cs.CV↗

arXiv2026

Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

Pansharpening aims to generate high-resolution multi-spectral images by fusing the spatial detail of panchromatic images with the spectral richness of low-resolution MS data. However, most existing methods are evaluated under limited, low-resolution settings, limiting their generalization to real-world, high-resolution scenarios. To bridge this gap, we systematically investigate the data, algorithmic, and computational challenges of cross-scale pansharpening. We first introduce PanScale, the first large-scale, cross-scale pansharpening dataset, accompanied by PanScale-Bench, a comprehensive benchmark for evaluating generalization across varying resolutions and scales. To realize scale generalization, we propose ScaleFormer, a novel architecture designed for multi-scale pansharpening. ScaleFormer reframes generalization across image resolutions as generalization across sequence lengths: it tokenizes images into patch sequences of the same resolution but variable length proportional to image scale. A Scale-Aware Patchify module enables training for such variations from fixed-size crops. ScaleFormer then decouples intra-patch spatial feature learning from inter-patch sequential dependency modeling, incorporating Rotary Positional Encoding to enhance extrapolation to unseen scales. Extensive experiments show that our approach outperforms SOTA methods in fusion quality and cross-scale generalization. The datasets and source code are available at https://github.com/caoke-963/ScaleFormer.

cs.CV↗

arXiv2026

AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer

The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer.

cs.CV↗

arXiv2025

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

cs.CV↗

arXiv2025

CaliTex: Geometry-Calibrated Attention for View-Coherent 3D Texture Generation

Despite major advances brought by diffusion-based models, current 3D texture generation systems remain hindered by cross-view inconsistency -- textures that appear convincing from one viewpoint often fail to align across others. We find that this issue arises from attention ambiguity, where unstructured full attention is applied indiscriminately across tokens and modalities, causing geometric confusion and unstable appearance-structure coupling. To address this, we introduce CaliTex, a framework of geometry-calibrated attention that explicitly aligns attention with 3D structure. It introduces two modules: Part-Aligned Attention that enforces spatial alignment across semantically matched parts, and Condition-Routed Attention which routes appearance information through geometry-conditioned pathways to maintain spatial fidelity. Coupled with a two-stage diffusion transformer, CaliTex makes geometric coherence an inherent behavior of the network rather than a byproduct of optimization. Empirically, CaliTex produces seamless and view-consistent textures and outperforms both open-source and commercial baselines.

cs.CV↗

arXiv2025

Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation

Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong performance in general T2I tasks, our research reveals that these models initially struggle with subject-driven image generation compared to dominant diffusion models. To address this limitation, we introduce Proxy-Tuning, leveraging diffusion models to enhance AR models' capabilities in subject-specific image generation. Our method reveals a striking weak-to-strong phenomenon: fine-tuned AR models consistently outperform their diffusion model supervisors in both subject fidelity and prompt adherence. We analyze this performance shift and identify scenarios where AR models excel, particularly in multi-subject compositions and contextual understanding. This work not only demonstrates impressive results in subject-driven AR image generation, but also unveils the potential of weak-to-strong generalization in the image generation domain, contributing to a deeper understanding of different architectures' strengths and limitations.

cs.CV↗

arXiv2025

LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context

Physically-based rendering (PBR) provides a principled standard for realistic material-lighting interactions in computer graphics. Despite recent advances in generating PBR textures, existing methods fail to address two fundamental challenges: 1) materials decomposition from image prompts under limited illumination cues, and 2) seamless and view-consistent texture completion. To this end, we propose LumiTex, an end-to-end framework that comprises three key components: (1) a multi-branch generation scheme that disentangles albedo and metallic-roughness under shared illumination priors for robust material understanding, (2) a lighting-aware material attention mechanism that injects illumination context into the decoding process for physically grounded generation of albedo, metallic, and roughness maps, and (3) a geometry-guided inpainting module based on a large view synthesis model that enriches texture coverage and ensures seamless, view-consistent UV completion. Extensive experiments demonstrate that LumiTex achieves state-of-the-art performance in texture quality, surpassing both existing open-source and commercial methods.

cs.CV↗

arXiv2025

V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models

Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.

cs.CV↗

arXiv2025

CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects

Customized text-to-video generation aims to generate high-quality videos guided by text prompts and subject references. Current approaches for personalizing text-to-video generation suffer from tackling multiple subjects, which is a more challenging and practical scenario. In this work, our aim is to promote multi-subject guided text-to-video customization. We propose CustomVideo, a novel framework that can generate identity-preserving videos with the guidance of multiple subjects. To be specific, firstly, we encourage the co-occurrence of multiple subjects via composing them in a single image. Further, upon a basic text-to-video diffusion model, we design a simple yet effective attention control strategy to disentangle different subjects in the latent space of diffusion model. Moreover, to help the model focus on the specific area of the object, we segment the object from given reference images and provide a corresponding object mask for attention learning. Also, we collect a multi-subject text-to-video generation dataset as a comprehensive benchmark. Extensive qualitative, quantitative, and user study results demonstrate the superiority of our method compared to previous state-of-the-art approaches. The project page is https://kyfafyd.wang/projects/customvideo.

cs.CV↗

arXiv2025

Large Material Gaussian Model for Relightable 3D Generation

The increasing demand for 3D assets across various industries necessitates efficient and automated methods for 3D content creation. Leveraging 3D Gaussian Splatting, recent large reconstruction models (LRMs) have demonstrated the ability to efficiently achieve high-quality 3D rendering by integrating multiview diffusion for generation and scalable transformers for reconstruction. However, existing models fail to produce the material properties of assets, which is crucial for realistic rendering in diverse lighting environments. In this paper, we introduce the Large Material Gaussian Model (MGM), a novel framework designed to generate high-quality 3D content with Physically Based Rendering (PBR) materials, ie, albedo, roughness, and metallic properties, rather than merely producing RGB textures with uncontrolled light baking. Specifically, we first fine-tune a new multiview material diffusion model conditioned on input depth and normal maps. Utilizing the generated multiview PBR images, we explore a Gaussian material representation that not only aligns with 2D Gaussian Splatting but also models each channel of the PBR materials. The reconstructed point clouds can then be rendered to acquire PBR attributes, enabling dynamic relighting by applying various ambient light maps. Extensive experiments demonstrate that the materials produced by our method not only exhibit greater visual appeal compared to baseline methods but also enhance material modeling, thereby enabling practical downstream rendering applications.

cs.CV↗

arXiv2025

DanceGRPO: Unleashing GRPO on Visual Generation

Recent advances in generative AI have revolutionized visual content creation, yet aligning model outputs with human preferences remains a critical challenge. While Reinforcement Learning (RL) has emerged as a promising approach for fine-tuning generative models, existing methods like DDPO and DPOK face fundamental limitations - particularly their inability to maintain stable optimization when scaling to large and diverse prompt sets, severely restricting their practical utility. This paper presents DanceGRPO, a framework that addresses these limitations through an innovative adaptation of Group Relative Policy Optimization (GRPO) for visual generation tasks. Our key insight is that GRPO's inherent stability mechanisms uniquely position it to overcome the optimization challenges that plague prior RL-based approaches on visual generation. DanceGRPO establishes several significant advances: First, it demonstrates consistent and stable policy optimization across multiple modern generative paradigms, including both diffusion models and rectified flows. Second, it maintains robust performance when scaling to complex, real-world scenarios encompassing three key tasks and four foundation models. Third, it shows remarkable versatility in optimizing for diverse human preferences as captured by five distinct reward models assessing image/video aesthetics, text-image alignment, video motion quality, and binary feedback. Our comprehensive experiments reveal that DanceGRPO outperforms baseline methods by up to 181\% across multiple established benchmarks, including HPS-v2.1, CLIP Score, VideoAlign, and GenEval. Our results establish DanceGRPO as a robust and versatile solution for scaling Reinforcement Learning from Human Feedback (RLHF) tasks in visual generation, offering new insights into harmonizing reinforcement learning and visual synthesis.

cs.CV↗

arXiv2025

AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization

Recent research on generative models has primarily focused on creating product-ready visual outputs; however, designers often favor access to standardized asset libraries, a domain that has yet to be significantly enhanced by generative capabilities. Although open-world scenes provide ample raw materials for designers, efficiently extracting high-quality, standardized assets remains a challenge. To address this, we introduce AssetDropper, the first framework designed to extract assets from reference images, providing artists with an open-world asset palette. Our model adeptly extracts a front view of selected subjects from input images, effectively handling complex scenarios such as perspective distortion and subject occlusion. We establish a synthetic dataset of more than 200,000 image-subject pairs and a real-world benchmark with thousands more for evaluation, facilitating the exploration of future research in downstream tasks. Furthermore, to ensure precise asset extraction that aligns well with the image prompts, we employ a pre-trained reward model to fulfill a closed-loop with feedback. We design the reward model to perform an inverse task that pastes the extracted assets back into the reference sources, which assists training with additional consistency and mitigates hallucination. Extensive experiments show that, with the aid of reward-driven optimization, AssetDropper achieves the state-of-the-art results in asset extraction. Project page: AssetDropper.github.io.

cs.CV↗

arXiv2025

StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation

In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation. However, complex tasks such as style-aligned text-to-image generation present significant challenges, particularly in data acquisition. In analogy to instruction-following tuning for image editing of AR models, style-aligned generation requires a reference style image and prompt, resulting in a text-image-to-image triplet where the output shares the style and semantics of the input. However, acquiring large volumes of such triplet data with specific styles is considerably more challenging than obtaining conventional text-to-image data used for training generative models. To address this issue, we propose StyleAR, an innovative approach that combines a specially designed data curation method with our proposed AR models to effectively utilize text-to-image binary data for style-aligned text-to-image generation. Our method synthesizes target stylized data using a reference style image and prompt, but only incorporates the target stylized image as the image modality to create high-quality binary data. To facilitate binary data training, we introduce a CLIP image encoder with a perceiver resampler that translates the image input into style tokens aligned with multimodal tokens in AR models and implement a style-enhanced token technique to prevent content leakage which is a common issue in previous work. Furthermore, we mix raw images drawn from large-scale text-image datasets with stylized images to enhance StyleAR's ability to extract richer stylistic features and ensure style consistency. Extensive qualitative and quantitative experiments demonstrate our superior performance.

cs.CV↗

arXiv2025

AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance

Character video generation is a significant real-world application focused on producing high-quality videos featuring specific characters. Recent advancements have introduced various control signals to animate static characters, successfully enhancing control over the generation process. However, these methods often lack flexibility, limiting their applicability and making it challenging for users to synthesize a source character into a desired target scene. To address this issue, we propose a novel framework, AnyCharV, that flexibly generates character videos using arbitrary source characters and target scenes, guided by pose information. Our approach involves a two-stage training process. In the first stage, we develop a base model capable of integrating the source character with the target scene using pose guidance. The second stage further bootstraps controllable generation through a self-boosting mechanism, where we use the generated video in the first stage and replace the fine mask with the coarse one, enabling training outcomes with better preservation of character details. Extensive experimental results demonstrate the superiority of our method compared with previous state-of-the-art methods.

cs.CV↗

arXiv2025

Generalizable Human Gaussians from Single-View Image

In this work, we tackle the task of learning 3D human Gaussians from a single image, focusing on recovering detailed appearance and geometry including unobserved regions. We introduce a single-view generalizable Human Gaussian Model (HGM), which employs a novel generate-then-refine pipeline with the guidance from human body prior and diffusion prior. Our approach uses a ControlNet to refine rendered back-view images from coarse predicted human Gaussians, then uses the refined image along with the input image to reconstruct refined human Gaussians. To mitigate the potential generation of unrealistic human poses and shapes, we incorporate human priors from the SMPL-X model as a dual branch, propagating image features from the SMPL-X volume to the image Gaussians using sparse convolution and attention mechanisms. Given that the initial SMPL-X estimation might be inaccurate, we gradually refine it with our HGM model. We validate our approach on several publicly available datasets. Our method surpasses previous methods in both novel view synthesis and surface reconstruction. Our approach also exhibits strong generalization for cross-dataset evaluation and in-the-wild images.

cs.CV↗