3 citations · 5 across the 25 of their papers we have counts for
26 papers
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
Deyuan Liu, Yihao Hu, Jingxuan Zhang +13
Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation…
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
Yansen Han, Shengyi Liao, Peng Sun +4
Preference alignment for flow and diffusion models now spans online reinforcement learning and offline preference optimization, but the relation between these methods remains uncle…
When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood?
Yansen Han, Hongxin Sun, Tao Lin
Flow matching enables likelihood-free training, yet alignment methods increasingly reuse conditional flow matching (CFM) losses as endpoint negative log-likelihoods (NLLs) and thei…
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Chuyan Chen, Haoxing Chen, Kun Chen +27
We introduce LLaDA-Image, a unified framework that pairs a 6B Diffusion Transformer (DiT) trained from scratch with a frozen vision-language understanding module built on the LLaDA…
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Yansen Han, Shengyi Liao, Yuanxing Zhang +2
Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven upda…
Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs
Tao Lin, Gaojie Jin, Zongxin Liu +2
Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets bef…
Three-Body Scattering for Generative Modeling
Peng Sun, Zhenglin Cheng, Deyuan Liu +3
Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional…
Condensing Large-Scale Datasets Directly with Minimal Information Loss
Xinyi Shang, Peng Sun, Bei Shi +2
Recent advancements in scaling dataset distillation rely heavily on decoupled information extraction pipelines, comprising SQUEEZE, RECOVER, and RELABEL stages. Despite their scala…
Self-Adversarial One Step Generation via Condition Shifting
Deyuan Liu, Peng Sun, Yansen Han +3
The push for efficient text to image synthesis has moved the field toward one step sampling, yet existing methods still face a three way tradeoff among fidelity, inference speed, a…
Duality Models: An Embarrassingly Simple One-step Generation Paradigm
Peng Sun, Xinyi Shang, Tao Lin +1
Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such m…
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
Zhenglin Cheng, Peng Sun, Jianguo Li +1
Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are t…
A Collision-Free Hot-Tier Extension for Engram-Style Conditional Memory: A Controlled Study of Training Dynamics
Tao Lin
We investigate whether high-frequency key collisions are a primary bottleneck in Engram-style conditional memory. To isolate the effect of collisions, we introduce Engram-Nine, a c…
Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty
Ziyu Chen, Xinbei Jiang, Peng Sun +1
Masked Diffusion Models (MDMs) offer flexible, non-autoregressive generation, but this freedom introduces a challenge: final output quality is highly sensitive to the decoding orde…
Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning
Qiwei Liang, Boyang Cai, Minghao Lai +6
Despite strong results on recognition and segmentation, current 3D visual pre-training methods often underperform on robotic manipulation. We attribute this gap to two factors: the…
Fast and Stable Diffusion Planning through Variational Adaptive Weighting
Zhiying Qiu, Tao Lin
Diffusion models have recently shown promise in offline RL. However, these methods often suffer from high training costs and slow convergence, particularly when using transformer-b…
Unified Continuous Generative Models
Peng Sun, Yi Jiang, Tao Lin
Recent advances in continuous generative models, including multi-step approaches like diffusion and flow-matching (typically requiring 8-1000 sampling steps) and few-step methods s…
Equally Critical: Samples, Targets, and Their Mappings in Datasets
Runkang Yang, Peng Sun, Xinyi Shang +2
Data inherently possesses dual attributes: samples and targets. For targets, knowledge distillation has been widely employed to accelerate model convergence, primarily relying on t…
Collaborative Unlabeled Data Optimization
Xinyi Shang, Peng Sun, Fengyuan Liu +1
This paper pioneers a novel data-centric paradigm to maximize the utility of unlabeled data, tackling a critical question: How can we enhance the efficiency and sustainability of d…
Efficient Generative Model Training via Embedded Representation Warmup
Deyuan Liu, Peng Sun, Xufeng Li +1
Generative models face a fundamental challenge: they must simultaneously learn high-level semantic concepts (what to generate) and low-level synthesis details (how to generate it).…
GMem: A Modular Approach for Ultra-Efficient Generative Models
Yi Tang, Peng Sun, Zhenglin Cheng +1
Recent studies indicate that the denoising process in deep generative diffusion models implicitly learns and memorizes semantic information from the data distribution. These findin…
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors
Tao Lin, Lijia Yu, Gaojie Jin +3
In recent years, the study of adversarial robustness in object detection systems, particularly those based on deep neural networks (DNNs), has become a pivotal area of research. Tr…
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
Haobo Song, Hao Zhao, Soumajit Majumder +1
Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods h…
GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
Xinyi Shang, Peng Sun, Tao Lin
Recent advancements in dataset distillation have demonstrated the significant benefits of employing soft labels generated by pre-trained teacher models. In this paper, we introduce…
Efficiency for Free: Ideal Data Are Transportable Representations
Peng Sun, Yi Jiang, Tao Lin
Data, the seminal opportunity and challenge in modern machine learning, currently constrains the scalability of representation learning and impedes the pace of model evolution. In…