Author name cluster

Xiangyu Yue

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

1 author row

AAAI Conference 2026 Conference Paper

SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning

Xiaoda Yang
Shenzhou Gao
Can Wang
Jiahe Zhang
Menglan Tang
Jingyang Xue
Sheng Liu
Peijian Zhang

Vision-Language Models (VLMs) have made significant progress in static perception, but their ability to understand dynamic task-oriented reasoning remains unclear. Existing benchmarks mainly focus on static spatial relationships and lack systematic assessment of dynamic reasoning capabilities. To this end, we propose SpatialLogic-Bench, a novel benchmark designed to evaluate VLMs’ understanding of spatiotemporal logic and their ability to assess task progress. The benchmark assesses two critical capabilities: first, fine-grained visual discrimination to accurately perceive subtle physical changes between state frames; second, the logical capacity to connect these changes to task goals and judge whether they indicate progress. To mitigate temporal dependency biases, we introduce a dual-task paradigm, presenting image pairs in both chronological and reversed orders while keeping task descriptions consistent. We construct a multi-scale evaluation system by varying time intervals between frames: smaller intervals test the model's fine-grained perception, while larger intervals demand more sophisticated logical inference. Empirical evaluation reveals that most VLMs experience significant performance degradation on tasks presented in inverse chronological order, indicating an over-reliance on temporal cues rather than robust reasoning abilities. SpatialLogic-Bench clearly exposes critical limitations in current models and provides valuable guidance for improving dynamic spatial perception capabilities.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Xi Chen
Kaituo Feng
Changsheng Li
Xunhao Lai
Xiangyu Yue
Ye Yuan
Guoren Wang

Low-rank training has emerged as a promising approach for reducing memory usage in training Large Language Models (LLMs). Previous methods either rely on decomposing weight matrices (e. g. , LoRA), or seek to decompose gradient matrices (e. g. , GaLore) to ensure reduced memory consumption. However, both of them constrain the training in a low-rank subspace, thus inevitably leading to sub-optimal performance. To resolve this, we propose a new plug-and-play training framework for LLMs called Fira, as the first attempt to consistently preserve the low-rank constraint for memory efficiency, while achieving full-rank training (i. e. , training with full-rank gradients of full-rank weights) to avoid inferior outcomes. First, we observe an interesting phenomenon during LLM training: the scaling impact of adaptive optimizers (e. g. , Adam) on the gradient norm remains similar from low-rank to full-rank training. In light of this, we propose a \textit{norm-based scaling} method, which utilizes the scaling impact of low-rank optimizers as substitutes for that of original full-rank optimizers to achieve this goal. Moreover, we find that there are potential loss spikes during training. To address this, we further put forward a norm-growth limiter to smooth the gradient. Extensive experiments on the pre-training and fine-tuning of LLMs show that Fira outperforms both LoRA and GaLore. Notably, for pre-training LLaMA 7B, our Fira uses $8\times$ smaller memory of optimizer states than Galore, yet outperforms it by a large margin.

PDF Details

NeurIPS Conference 2025 Conference Paper

Learning to Integrate Diffusion ODEs by Averaging the Derivatives

Wenze Liu
Xiangyu Yue

To accelerate diffusion model inference, numerical solvers perform poorly at extremely small steps, while distillation techniques often introduce complexity and instability. This work presents an intermediate strategy, balancing performance and cost, by learning ODE integration using loss functions derived from the derivative-integral relationship, inspired by Monte Carlo integration and Picard iteration. From a geometric perspective, the losses operate by gradually extending the tangent to the secant, thus are named as secant losses. The target of secant losses is the same as that of diffusion models, or the diffusion model itself, leading to great training stability. By fine-tuning or distillation, the secant version of EDM achieves a $10$-step FID of $2. 14$ on CIFAR-10, while the secant version of SiT-XL/2 attains a $4$-step FID of $2. 27$ and an $8$-step FID of $1. 96$ on ImageNet-$256\times256$. Code is available at \url{https: //github. com/poppuppy/secant-expectation}.

PDF Details

NeurIPS Conference 2025 Conference Paper

Native-Resolution Image Synthesis

Zidong Wang
Lei Bai
Xiangyu Yue
Wanli Ouyang
Yiyuan Zhang

We introduce native-resolution image synthesis, a novel paradigm in generative modeling capable of synthesizing images at arbitrary resolutions and aspect ratios. This approach overcomes the limitations of standard fixed-resolution, square-image methods by inherently handling variable-length visual tokens—a core challenge for conventional techniques. To this end, we propose the Native-resolution diffusion Transformer (NiT), an architecture that explicitly models varying resolutions and aspect ratios within its denoising process. Unconstrained by fixed formats, NiT learns intrinsic visual distributions from images encompassing a wide range of resolutions and aspect ratios. Notably, a single NiT model simultaneously achieves the state-of-the-art performance on both ImageNet-256x256 and 512x512 benchmarks. Surprisingly, akin to the robust zero-shot capabilities seen in advanced Large Language Models, NiT, pretrained solely on ImageNet, demonstrates excellent zero-shot generalization performance. It successfully generates high-fidelity images at previously unseen high resolutions (e. g. , 1024x1024, 1536x1536) and diverse aspect ratios (e. g. , 16: 9, 3: 1, 4: 3), as shown in Figure 1. These findings indicate the significant potential of native-resolution modeling as a bridge between visual generative modeling and advanced LLM methodologies.

PDF Details

NeurIPS Conference 2025 Conference Paper

ReSim: Reliable World Simulation for Autonomous Driving

Jiazhi Yang
Kashyap Chitta
Shenyuan Gao
Long Chen
Yuqian Shao
Xiaosong Jia
Hongyang Li
Andreas Geiger

How can we reliably simulate future driving scenarios under a wide range of ego driving behaviors? Recent driving world models, developed exclusively on real-world driving data composed mainly of safe expert trajectories, struggle to follow hazardous or non-expert behaviors, which are rare in such data. This limitation restricts their applicability to tasks such as policy evaluation. In this work, we address this challenge by enriching real-world human demonstrations with diverse non-expert data collected from a driving simulator (e. g. , CARLA), and building a controllable world model trained on this heterogeneous corpus. Starting with a video generator featuring diffusion transformer architecture, we devise several strategies to effectively integrate conditioning signals and improve prediction controllability and fidelity. The resulting model, ReSim, enables Reliable Simulation of diverse open-world driving scenarios under various actions, including hazardous non-expert ones. To close the gap between high-fidelity simulation and applications that require reward signals to judge different actions, we introduce a Video2Reward module that estimates reward from ReSim’s simulated future. Our ReSim paradigm achieves up to 44% higher visual fidelity, improves controllability for both expert and non-expert actions by over 50%, and boosts planning and policy selection performance on NAVSIM by 2% and 25%, respectively.

PDF Details

AAAI Conference 2025 Conference Paper

Training Matting Models Without Alpha Labels

Wenze Liu
Zixuan Ye
Hao Lu
Zhiguo Cao
Xiangyu Yue

The labeling difficulty has been a longstanding problem in deep image matting. To escape from fine labels, this work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present that the cooperation between learned semantics from indicated known regions and proper assumed matting rules can help infer alpha values at transition areas. Inspired by the nonlocal principle in traditional image matting, we build a directional distance consistency loss (DDC loss) at each pixel neighborhood to constrain the alpha values conditioned on the input image. DDC loss forces the distance of similar pairs on the alpha matte and on its corresponding image to be consistent. In this way, the alpha values can be propagated from learned known regions to unknown transition areas. With only images and trimaps, a matting model can be trained under the supervision of a known loss and the proposed DDC loss. Experiments on AM-2K and P3M-10K dataset show that our paradigm achieves comparable performance with the fine-label-supervised baseline, while sometimes offers even more satisfying results than human-labeled ground truth.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Video-R1: Reinforcing Video Reasoning in MLLMs

Kaituo Feng
Kaixiong Gong
Bohao Li
Zonghao Guo
Yibing Wang
Tianshuo Peng
Junfei Wu
Xiaoying Zhang

Inspired by DeepSeek-R1's success in eliciting reasoning abilities through rule-based reinforcement learning (RL), we introduce Video-R1 as the first attempt to systematically explore the R1 paradigm for incentivizing video reasoning within multimodal large language models (MLLMs). However, directly applying RL training with the GRPO algorithm to video reasoning presents two primary challenges: (i) a lack of temporal modeling for video reasoning, and (ii) the scarcity of high-quality video-reasoning data. To address these issues, we first propose the T-GRPO algorithm, which encourages models to utilize temporal information in videos for reasoning. Additionally, instead of relying solely on video data, we incorporate high-quality image-reasoning data into the training process. We have constructed two datasets: Video-R1-CoT-165k for SFT cold start and Video-R1-260k for RL training, both comprising image and video data. Experimental results demonstrate that Video-R1 achieves significant improvements on video reasoning benchmarks such as VideoMMMU and VSI-Bench, as well as on general video benchmarks including MVBench and TempCompass, etc. Notably, Video-R1-7B attains a 37. 1\% accuracy on video spatial reasoning benchmark VSI-bench, surpassing the commercial proprietary model GPT-4o. All code, models, and data will be released.

PDF Details

NeurIPS Conference 2025 Conference Paper

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Jiaming Han
Hao Chen
Yang Zhao
Hanyu Wang
Qi Zhao
Ziyan Yang
Hao He
Xiangyu Yue

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete tokens using a text-aligned codebook projected from a large language model's (LLM) vocabulary. By integrating vision and text into a unified space with an expanded vocabulary, our multimodal LLM, Tar, enables cross-modal input and output through a shared interface, without the need for modality-specific designs. Additionally, we propose scale-adaptive encoding and decoding to balance efficiency and visual detail, along with a generative de-tokenizer to produce high-fidelity visual outputs. To address diverse decoding needs, we utilize two complementary de-tokenizers: a fast autoregressive model and a diffusion-based model. To enhance modality fusion, we investigate advanced pre-training tasks, demonstrating improvements in both visual understanding and generation. Experiments across benchmarks show that Tar matches or surpasses existing multimodal LLM methods, achieving faster convergence and greater training efficiency. All code, models, and data will be made publicly available.

PDF Details

NeurIPS Conference 2024 Conference Paper

$\textit{Bifr\"ost}$: 3D-Aware Image Compositing with Language Instructions

Lingxiao Li
Kaixiong Gong
Weihong Li
Xili Dai
Tao Chen
Xiaojun Yuan
Xiangyu Yue

This paper introduces $\textit{Bifröst}$, a novel 3D-aware framework that is built upon diffusion models to perform instruction-based image composition. Previous methods concentrate on image compositing at the 2D level, which fall short in handling complex spatial relationships ($\textit{e. g. }$, occlusion). $\textit{Bifröst}$ addresses these issues by training MLLM as a 2. 5D location predictor and integrating depth maps as an extra condition during the generation process to bridge the gap between 2D and 3D, which enhances spatial comprehension and supports sophisticated spatial interactions. Our method begins by fine-tuning MLLM with a custom counterfactual dataset to predict 2. 5D object locations in complex backgrounds from language instructions. Then, the image-compositing model is uniquely designed to process multiple types of input features, enabling it to perform high-fidelity image compositions that consider occlusion, depth blur, and image harmonization. Extensive qualitative and quantitative evaluations demonstrate that $\textit{Bifröst}$ significantly outperforms existing methods, providing a robust solution for generating realistically composited images in scenarios demanding intricate spatial understanding. This work not only pushes the boundaries of generative image compositing but also reduces reliance on expensive annotated datasets by effectively utilizing existing resources in innovative ways.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

EMR-Merging: Tuning-Free High-Performance Model Merging

Chenyu Huang
Peng Ye
Tao Chen
Tong He
Xiangyu Yue
Wanli Ouyang

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention for its practicability. Existing model merging methods usually suffer from (1) significant performance degradation or (2) requiring tuning by additional data or training. In this paper, we rethink and analyze the existing model merging paradigm. We discover that using a single model's weights can hardly simulate all the models' performance. To tackle this issue, we propose Elect, Mask & Rescale-Merging (EMR-Merging). We first (a) elect a unified model from all the model weights and then (b) generate extremely lightweight task-specific modulators, including masks and rescalers, to align the direction and magnitude between the unified model and each specific model, respectively. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance. We find that EMR-Merging shows outstanding performance compared to existing merging methods under different classical and newly-established settings, including merging different numbers of vision models (up to 30), NLP models, PEFT models, and multi-modal models.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT

Le Zhuo
Ruoyi Du
Han Xiao
Yangguang Li
Dongyang Liu
Rongjie Huang
Wenze Liu
Xiangyang Zhu

Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers (Flag-DiT) that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabilities, Lumina-T2X still encounters challenges including training instability, slow inference, and extrapolation artifacts. In this paper, we present Lumina-Next, an improved version of Lumina-T2X, showcasing stronger generation performance with increased training and inference efficiency. We begin with a comprehensive analysis of the Flag-DiT architecture and identify several suboptimal components, which we address by introducing the Next-DiT architecture with 3D RoPE and sandwich normalizations. To enable better resolution extrapolation, we thoroughly compare different context extrapolation methods applied to text-to-image generation with 3D RoPE, and propose Frequency- and Time-Aware Scaled RoPE tailored for diffusion transformers. Additionally, we introduce a sigmoid time discretization schedule for diffusion sampling, which achieves high-quality generation in 5-10 steps combined with higher-order ODE solvers. Thanks to these improvements, Lumina-Next not only improves the basic text-to-image generation but also demonstrates superior resolution extrapolation capabilities as well as multilingual generation using decoder-based LLMs as the text encoder, all in a zero-shot manner. To further validate Lumina-Next as a versatile generative framework, we instantiate it on diverse tasks including visual recognition, multi-views, audio, music, and point cloud generation, showcasing strong performance across these domains. By releasing all codes and model weights at https: //github. com/Alpha-VLLM/Lumina-T2X, we aim to advance the development of next-generation generative AI capable of universal modeling.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data

Hari Prasanna Das
Ryan Tran
Japjot Singh
Xiangyu Yue
Geoffrey Tison
Alberto Sangiovanni-Vincentelli
Costas J. Spanos

Background: At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine Learning (ML) models trained with the available data, which is limited in quantity and poor in diversity, will often be biased and inaccurate. At the same time, ML algorithms designed to fight pandemics must have good performance and be developed in a time-sensitive manner. To tackle the challenges of limited data, and label scarcity in the available data, we propose generating conditional synthetic data, to be used alongside real data for developing robust ML models. Methods: We present a hybrid model consisting of a conditional generative flow and a classifier for conditional synthetic data generation. The classifier decouples the feature representation for the condition, which is fed to the flow to extract the local noise. We generate synthetic data by manipulating the local noise with fixed conditional feature representation. We also propose a semi-supervised approach to generate synthetic samples in the absence of labels for a majority of the available data. Results: We performed conditional synthetic generation for chest computed tomography (CT) scans corresponding to normal, COVID-19, and pneumonia afflicted patients. We show that our method significantly outperforms existing models both on qualitative and quantitative performance, and our semi-supervised approach can efficiently synthesize conditional samples under label scarcity. As an example of downstream use of synthetic data, we show improvement in COVID-19 detection from CT scans with conditional synthetic data augmentation.

PDF Details

NeurIPS Conference 2019 Conference Paper

Multi-source Domain Adaptation for Semantic Segmentation

Sicheng Zhao
Bo Li
Xiangyu Yue
Yang Gu
Pengfei Xu
Runbo Hu
Hua Chai
Kurt Keutzer

Simulation-to-real domain adaptation for semantic segmentation has been actively studied for various applications such as autonomous driving. Existing methods mainly focus on a single-source setting, which cannot easily handle a more practical scenario of multiple sources with different distributions. In this paper, we propose to investigate multi-source domain adaptation for semantic segmentation. Specifically, we design a novel framework, termed Multi-source Adversarial Domain Aggregation Network (MADAN), which can be trained in an end-to-end manner. First, we generate an adapted domain for each source with dynamic semantic consistency while aligning at the pixel-level cycle-consistently towards the target. Second, we propose sub-domain aggregation discriminator and cross-domain cycle discriminator to make different adapted domains more closely aggregated. Finally, feature-level alignment is performed between the aggregated domain and target domain while training the segmentation network. Extensive experiments from synthetic GTA and SYNTHIA to real Cityscapes and BDDS datasets demonstrate that the proposed MADAN model outperforms state-of-the-art approaches. Our source code is released at: https: //github. com/Luodian/MADAN.

PDF Details

IJCAI Conference 2018 Conference Paper

Counterexample-Guided Data Augmentation

Tommaso Dreossi
Shromona Ghosh
Xiangyu Yue
Kurt Keutzer
Alberto Sangiovanni-Vincentelli
Sanjit A. Seshia

We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a \textit{counterexample generator}, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model's vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks.

PDF Details