Zihao Yu

Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang et al.

In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable efficient long-horizon manipulation, we propose GTP-FA (Grasp-Then-Plan with Failure Attribution), a task-oriented two-stage grasp-then-plan framework that generates grasp candidates and performs downstream motion planning conditioned on the selected grasp. Given a failed manipulation trajectory, we learn a failure attribution model that generalizes to unseen grasps and produces a stable distribution over failure modes for diagnosis-guided optimization. Based on these attribution results, we then optimize both modules in a diagnosis-driven manner: on the grasping side, we inject task-level priors and risk penalties into grasp candidate scoring and optimization to suppress unstable or task-incompatible grasps; on the planning side, we target high-risk initial states through data collection and fine-tuning to address genuine planning bottlenecks. We evaluate the proposed framework in both simulation and real-robot experiments, and show that GTP-FA improves the corresponding base learners across RL, IL, diffusion-policy, and VLA-based settings, achieving substantially higher overall task success rates.

Yu Chen, Zihao Yu, Shu Song et al.

Despite the impressive results achieved by many existing Structure from Motion (SfM) approaches, there is still a need to improve the robustness, accuracy, and efficiency on large-scale scenes with many outlier matches and sparse view graphs. In this paper, we propose AdaSfM: a coarse-to-fine adaptive SfM approach that is scalable to large-scale and challenging datasets. Our approach first does a coarse global SfM which improves the reliability of the view graph by leveraging measurements from low-cost sensors such as Inertial Measurement Units (IMUs) and wheel encoders. Subsequently, the view graph is divided into sub-scenes that are refined in parallel by a fine local incremental SfM regularised by the result from the coarse global SfM to improve the camera registration accuracy and alleviate scene drifts. Finally, our approach uses a threshold-adaptive strategy to align all local reconstructions to the coordinate frame of global SfM. Extensive experiments on large-scale benchmark datasets show that our approach achieves state-of-the-art accuracy and efficiency.

Weiping Yu, Siqiang Luo, Zihao Yu et al.

We use machine learning to optimize LSM-tree structure, aiming to reduce the cost of processing various read/write operations. We introduce a new approach Camal, which boasts the following features: (1) ML-Aided: Camal is the first attempt to apply active learning to tune LSM-tree based key-value stores. The learning process is coupled with traditional cost models to improve the training process; (2) Decoupled Active Learning: backed by rigorous analysis, Camal adopts active learning paradigm based on a decoupled tuning of each parameter, which further accelerates the learning process; (3) Easy Extrapolation: Camal adopts an effective mechanism to incrementally update the model with the growth of the data size; (4) Dynamic Mode: Camal is able to tune LSM-tree online under dynamically changing workloads; (5) Significant System Improvement: By integrating Camal into a full system RocksDB, the system performance improves by 28% on average and up to 8x compared to a state-of-the-art RocksDB design.

Xin Li, Kun Yuan, Bingchen Li et al.

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

Feng Wang, Zihao Yu

Reinforcement Learning (RL) has recently emerged as a powerful technique for improving image and video generation in Diffusion and Flow Matching models, specifically for enhancing output quality and alignment with prompts. A critical step for applying online RL methods on Flow Matching is the introduction of stochasticity into the deterministic framework, commonly realized by Stochastic Differential Equation (SDE). Our investigation reveals a significant drawback to this approach: SDE-based sampling introduces pronounced noise artifacts in the generated images, which we found to be detrimental to the reward learning process. A rigorous theoretical analysis traces the origin of this noise to an excess of stochasticity injected during inference. To address this, we draw inspiration from Denoising Diffusion Implicit Models (DDIM) to reformulate the sampling process. Our proposed method, Coefficients-Preserving Sampling (CPS), eliminates these noise artifacts. This leads to more accurate reward modeling, ultimately enabling faster and more stable convergence for reinforcement learning-based optimizers like Flow-GRPO and Dance-GRPO. Code will be released at https://github.com/IamCreateAI/FlowCPS

Zhongkai Yu, Yue Guan, Zihao Yu et al.

Large Language Models (LLMs) with Mixture of Experts (MoE) architectures achieve remarkable performance improvements, but their random expert selection mechanism introduces significant data movement overhead that becomes the dominant bottleneck in multi-unit serving systems. To forecast the patterns underlying this data movement, we conduct comprehensive data-movement-centric profiling across three state-of-the-art large-scale MoE models (200B- 671B) using over 24,000 requests spanning diverse workloads. With the resulting 150GB+ trace files, we perform systematic analysis from both temporal and spatial perspectives and distill six key insights to guide the design of diverse future serving systems. Taking wafer-scale GPUs as a case study, we demonstrate that minor architectural modifications leveraging our insights achieve substantial performance gains, delivering 6.3X and 4.0X average speedups on DeepSeek V3 and Qwen3, respectively. Our work provides the first comprehensive data-centric analysis of MoE models at scale. Our profiling traces and analysis results are publicly available at {https://huggingface.co/datasets/core12345/MoE_expert_selection_trace. We will also release our simulation framework shortly to facilitate future research in this area.

Jingyi Yang, Songsong Mo, Jiachen Shi et al.

The explosive growth of multimodal data - spanning text, image, video, spatial, and relational modalities, coupled with the need for real-time semantic search and retrieval over these data - has outpaced the capabilities of existing multimodal and real-time database systems, which either lack efficient ingestion and continuous query capability, or fall short in supporting expressive hybrid analytics. We introduce ARCADE, a real-time data system that efficiently supports high-throughput ingestion and expressive hybrid and continuous query processing across diverse data types. ARCADE introduces unified disk-based secondary index on LSM-based storage for vector, spatial, and text data modalities, a comprehensive cost-based query optimizer for hybrid queries, and an incremental materialized view framework for efficient continuous queries. Built on open-source RocksDB storage and MySQL query engine, ARCADE outperforms leading multimodal data systems by up to 7.4x on read-heavy and 1.4x on write-heavy workloads.

Fengbin Guan, Xin Li, Zihao Yu et al.

In this work, we take the first exploration of the recently popular foundation model, i.e., State Space Model/Mamba, in image quality assessment (IQA), aiming at observing and excavating the perception potential in vision Mamba. A series of works on Mamba has shown its significant potential in various fields, e.g., segmentation and classification. However, the perception capability of Mamba remains under-explored. Consequently, we propose QMamba by revisiting and adapting the Mamba model for three crucial IQA tasks, i.e., task-specific, universal, and transferable IQA, which reveals its clear advantages over existing foundational models, e.g., Swin Transformer, ViT, and CNNs, in terms of perception and computational cost. To improve the transferability of QMamba, we propose the StylePrompt tuning paradigm, where lightweight mean and variance prompts are injected to assist task-adaptive transfer learning of pre-trained QMamba for different downstream IQA tasks. Compared with existing prompt tuning strategies, our StylePrompt enables better perceptual transfer with lower computational cost. Extensive experiments on multiple synthetic, authentic IQA datasets, and cross IQA datasets demonstrate the effectiveness of our proposed QMamba. The code will be available at: https://github.com/bingo-G/QMamba.git

Xiaohong Liu, Xiongkuo Min, Guangtao Zhai et al.

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.

Shuhao Han, Haotian Fan, Fangyuan Kong et al.

This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. The aim of this challenge is to address the fine-grained quality assessment of text-to-image generation models. This challenge evaluates text-to-image models from two aspects: image-text alignment and image structural distortion detection, and is divided into the alignment track and the structural track. The alignment track uses the EvalMuse-40K, which contains around 40K AI-Generated Images (AIGIs) generated by 20 popular generative models. The alignment track has a total of 371 registered participants. A total of 1,883 submissions are received in the development phase, and 507 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. The structure track uses the EvalMuse-Structure, which contains 10,000 AI-Generated Images (AIGIs) with corresponding structural distortion mask. A total of 211 participants have registered in the structure track. A total of 1155 submissions are received in the development phase, and 487 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Almost all methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on T2I model quality assessment.

Xiaohong Liu, Xiongkuo Min, Qiang Hu et al.

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

Diandian Gu, Jing Lin, Gaohong Liu et al.

We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage pipeline decouples global structure learning from high-frequency detail recovery, while a locality-aware VAE achieves higher spatial compression and more efficient decoding. For texture and material generation, we replace the cascaded pipeline of Seed3D 1.0 with a unified PBR model that directly generates multi-view albedo and metallic-roughness maps, enhanced by Mixture-of-Experts scaling and VLM-based semantic conditioning for improved material precision and visual fidelity. Beyond single-object generation, Seed3D 2.0 introduces a simulation-ready model suite comprising scene layout planning, part-aware decomposition, and training-free articulation generation, enabling coherent scene construction and part-level physical interaction across physics and graphics engines. A large-scale human preference study against five recent commercial models shows that Seed3D 2.0 achieves consistent win rates of 69.0% to 89.9% in textured 3D asset generation. Seed3D 2.0 is available on https://exp.volcengine.com/ark/vision?_vtm_=0.0.c70961.d701978.0&mode=vision&modelId=doubao-seed3d-2-0-260328&tab=Gen3D

Dasong Li, Sizhuo Ma, Hang Hua et al.

This paper presents an overview of the VQualA 2025 Challenge on Engagement Prediction for Short Videos, held in conjunction with ICCV 2025. The challenge focuses on understanding and modeling the popularity of user-generated content (UGC) short videos on social media platforms. To support this goal, the challenge uses a new short-form UGC dataset featuring engagement metrics derived from real-world user interactions. This objective of the Challenge is to promote robust modeling strategies that capture the complex factors influencing user engagement. Participants explored a variety of multi-modal features, including visual content, audio, and metadata provided by creators. The challenge attracted 97 participants and received 15 valid test submissions, contributing significantly to progress in short-form UGC video engagement prediction.

Vincent Siu, Nicholas Crispino, Zihao Yu et al.

Large Language Models (LLMs) encode behaviors such as refusal within their activation space, yet identifying these behaviors remains a significant challenge. Existing methods often rely on predefined refusal templates detectable in output tokens or require manual analysis. We introduce \textbf{COSMIC} (Cosine Similarity Metrics for Inversion of Concepts), an automated framework for direction selection that identifies viable steering directions and target layers using cosine similarity - entirely independent of model outputs. COSMIC achieves steering performance comparable to prior methods without requiring assumptions about a model's refusal behavior, such as the presence of specific refusal tokens. It reliably identifies refusal directions in adversarial settings and weakly aligned models, and is capable of steering such models toward safer behavior with minimal increase in false refusals, demonstrating robustness across a wide range of alignment conditions.

Fengbin Guan, Zihao Yu, Yiting Lu et al.

Video quality assessment tasks rely heavily on the rich features required for video understanding, such as semantic information, texture, and temporal motion. The existing video foundational model, InternVideo2, has demonstrated strong potential in video understanding tasks due to its large parameter size and large-scale multimodal data pertaining. Building on this, we explored the transferability of InternVideo2 to video quality assessment under compression scenarios. To design a lightweight model suitable for this task, we proposed a distillation method to equip the smaller model with rich compression quality priors. Additionally, we examined the performance of different backbones during the distillation process. The results showed that, compared to other methods, our lightweight model distilled from InternVideo2 achieved excellent performance in compression video quality assessment.

Ningyi Liao, Zihao Yu, Siqiang Luo

Graph Transformer (GT) has recently emerged as a promising neural network architecture for learning graph-structured data. However, its global attention mechanism with quadratic complexity concerning the graph scale prevents wider application to large graphs. While current methods attempt to enhance GT scalability by altering model architecture or encoding hierarchical graph data, our analysis reveals that these models still suffer from the computational bottleneck related to graph-scale operations. In this work, we target the GT scalability issue and propose DHIL-GT, a scalable Graph Transformer that simplifies network learning by fully decoupling the graph computation to a separate stage in advance. DHIL-GT effectively retrieves hierarchical information by exploiting the graph labeling technique, as we show that the graph label hierarchy is more informative than plain adjacency by offering global connections while promoting locality, and is particularly suitable for handling complex graph patterns such as heterophily. We further design subgraph sampling and positional encoding schemes for precomputing model input on top of graph labels in an end-to-end manner. The training stage thus favorably removes graph-related computations, leading to ideal mini-batch capability and GPU utilization. Notably, the precomputation and training processes of DHIL-GT achieve complexities linear to the number of graph edges and nodes, respectively. Extensive experiments demonstrate that DHIL-GT is efficient in terms of computational boost and mini-batch capability over existing scalable Graph Transformer designs on large-scale benchmarks, while achieving top-tier effectiveness on both homophilous and heterophilous graphs.

Yiting Lu, Wei Luo, Peiyan Tu et al.

World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct realistic, dynamic, and physically consistent 3D/4D worlds from images, videos, or text. These models not only need to produce high-fidelity visual content but also maintain coherence across space, time, physics, and instruction control, enabling applications in virtual reality, autonomous driving, embodied intelligence, and content creation. However, prior benchmarks emphasize different evaluation dimensions and lack a unified assessment of world-realism capability. To systematically evaluate World Models, we introduce the 4DWorldBench, which measures models across four key dimensions: Perceptual Quality, Condition-4D Alignment, Physical Realism, and 4D Consistency. The benchmark covers tasks such as Image-to-3D/4D, Video-to-4D, Text-to-3D/4D. Beyond these, we innovatively introduce adaptive conditioning across multiple modalities, which not only integrates but also extends traditional evaluation paradigms. To accommodate different modality-conditioned inputs, we map all modality conditions into a unified textual space during evaluation, and further integrate LLM-as-judge, MLLM-as-judge, and traditional network-based methods. This unified and adaptive design enables more comprehensive and consistent evaluation of alignment, physical realism, and cross-modal coherence. Preliminary human studies further demonstrate that our adaptive tool selection achieves closer agreement with subjective human judgments. We hope this benchmark will serve as a foundation for objective comparisons and improvements, accelerating the transition from "visual generation" to "world generation." Our project can be found at https://yeppp27.github.io/4DWorldBench.github.io/.

Jiashi Feng, Xiu Li, Jing Lin et al.

Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D

Jianhong Tu, Zhuohao Ni, Nicholas Crispino et al.

We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the importance of each modality in the instruction tuning stage, often using a majority of vision-language data while keeping text-only data limited and fixing mixtures of modalities. By incorporating diverse text-only data in the visual instruction tuning stage, we vary vision-language data in various controlled experiments to investigate the importance of modality in visual instruction tuning. Our comprehensive evaluation shows that the text-heavy instruction tuning approach is able to perform on-par with traditional vision-heavy mixtures on both modalities across 12 general datasets while using as low as half the total training tokens. We find that simply increasing sufficiently diverse text-only data enables transfer of instruction following ability and domain knowledge across modalities while being more efficient than the vision-language approach.

Ningyi Liao, Zihao Yu, Ruixiao Zeng et al.

Graph Neural Networks (GNNs) have shown promising performance, but at the cost of resource-intensive operations on graph-scale matrices. To reduce computational overhead, previous studies attempt to sparsify the graph or network parameters, but with limited flexibility and precision boundaries. In this work, we propose Unifews, a joint sparsification technique to unify graph and weight matrix operations and enhance GNN learning efficiency. The Unifews design enables adaptive compression across GNN layers with progressively increased sparsity, and is applicable to a variety of architectures with on-the-fly simplification. Theoretically, we establish a novel framework to characterize sparsified GNN learning in view of the graph optimization process, showing that Unifews effectively approximates the learning objective with bounded error and reduced computational overhead. Extensive experiments demonstrate that Unifews achieves efficiency improvements with comparable or better accuracy, including 10-20x matrix operation reduction and up to 100x acceleration on graphs up to billion-edge scale.

Zihao Yu, Fengbin Guan, Yiting Lu et al.

The objective of non-reference video quality assessment is to evaluate the quality of distorted video without access to reference high-definition references. In this study, we introduce an enhanced spatial perception module, pre-trained on multiple image quality assessment datasets, and a lightweight temporal fusion module to address the no-reference visual quality assessment (NR-VQA) task. This model implements Swin Transformer V2 as a local-level spatial feature extractor and fuses these multi-stage representations through a series of transformer layers. Furthermore, a temporal transformer is utilized for spatiotemporal feature fusion across the video. To accommodate compressed videos of varying bitrates, we incorporate a coarse-to-fine contrastive strategy to enrich the model's capability to discriminate features from videos of different bitrates. This is an expanded version of the one-page abstract.

Zihao Yu, Haoyang Li, Fangcheng Fu et al.

Due to the recent success of diffusion models, text-to-image generation is becoming increasingly popular and achieves a wide range of applications. Among them, text-to-image editing, or continuous text-to-image generation, attracts lots of attention and can potentially improve the quality of generated images. It's common to see that users may want to slightly edit the generated image by making minor modifications to their input textual descriptions for several rounds of diffusion inference. However, such an image editing process suffers from the low inference efficiency of many existing diffusion models even using GPU accelerators. To solve this problem, we introduce Fast Image Semantically Edit (FISEdit), a cached-enabled sparse diffusion model inference engine for efficient text-to-image editing. The key intuition behind our approach is to utilize the semantic mapping between the minor modifications on the input text and the affected regions on the output image. For each text editing step, FISEdit can automatically identify the affected image regions and utilize the cached unchanged regions' feature map to accelerate the inference process. Extensive empirical results show that FISEdit can be $3.4\times$ and $4.4\times$ faster than existing methods on NVIDIA TITAN RTX and A100 GPUs respectively, and even generates more satisfactory images.