1 citations · 4 across the 16 of their papers we have counts for
21 papers
FlashControl: One-Step Controllable Generator via Distillation-Friendly Single-Stream Teachers
Ngan Nguyen, Dung Nguyen, Quan Dao +4
Diffusion models have become a leading approach in visual generative modeling, particularly effective in text-to-image and controllable generation. Their main drawback is slow infe…
Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
Tunyu Zhang, Zihao Zhao, Yusong Zhao +5
LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel multi-age…
Turbo Harness: Instance-Adaptive Harness Optimization
Tunyu Zhang, Hao Wang, Kai Xu +1
Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single glo…
Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions
Quyen Tran, Hai Nguyen, Quan Dao +4
Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and hav…
Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
Anh Nguyen, Ngan Nguyen, Duc Vu +11
Modern one-step diffusion models achieve impressive quality through distribution-based timestep distillation. Yet, they rely on a critical assumption: Teacher and Student must inha…
Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision
Gerasimos Chatzoudis, Konstantinos D. Polyzos, Zhuowei Li +4
Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used…
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
Quan Dao, Dimitris Metaxas
Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to con…
Few-Step Diffusion Language Models via Trajectory Self-Distillation
Tunyu Zhang, Xinxi Zhang, Ligong Han +9
Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decoding. However, realizing this poten…
Overcoming the Curvature Bottleneck in MeanFlow
Xinxi Zhang, Shiwei Tan, Quang Nguyen +7
MeanFlow offers a promising framework for one-step generative modeling by directly learning a mean-velocity field, bypassing expensive numerical integration. However, we find that…
AutoEdit: Automatic Hyperparameter Tuning for Image Editing
Chau Pham, Quan Dao, Mahesh Bhosale +3
Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get th…
Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing
Quan Dao, Xiaoxiao He, Ligong Han +6
Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation…
Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
Gerasimos Chatzoudis, Zhuowei Li, Gemma E. Moran +2
Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. W…
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
Tunyu Zhang, Haizhou Shi, Yibin Wang +9
While Large Language Models (LLMs) have demonstrated impressive capabilities, their output quality remains inconsistent across various application scenarios, making it difficult to…
Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
Shiyu Zhao, Zhenting Wang, Felix Juefei-Xu +7
Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs)…
Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
Quan Dao, Hao Phung, Trung Dao +2
Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared…
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
Maitreya Patel, Song Wen, Dimitris N. Metaxas +1
Diffusion models (DMs) excel in photorealism, image editing, and solving inverse problems, aided by classifier-free guidance and image inversion techniques. However, rectified flow…
DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation
Hao Phung, Quan Dao, Trung Dao +3
We introduce a novel state-space architecture for diffusion models, effectively harnessing spatial and frequency information to enhance the inductive bias towards local features in…
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Xiaoxiao He, Quan Dao, Ligong Han +14
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (D…
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Yibin Wang, Haizhou Shi, Ligong Han +2
Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data. Previous work addre…
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models
Xinxi Zhang, Song Wen, Ligong Han +6
Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by…
Improving Compositional Text-to-image Generation with Large Vision-Language Models
Song Wen, Guian Fang, Renrui Zhang +3
Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficu…