Publications
Efficient generative AI, multimodal models,
and embodied intelligence.
63 publications
2026
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
Multi-Block Diffusion Language Models
CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcing
MirrorPPR: Exemplar-Based Portrait Photo Retouching
ProductWebGen: Benchmarking Multimodal Product Webpage Generation
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
LightningRL: Breaking the Accuracy–Parallelism Trade-off of Block-wise dLLMs via Reinforcement Learning
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
UniCM: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
TPS-Bench: Evaluating AI Agents' Tool Planning & Scheduling Abilities in Compounding Tasks
LogCD: Local-to-global Consistency Distillation for Few-step Image Generation
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
2025
Neural Eigenfunctions Are Structured Representation Learners
Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions
Scaling Speculative Decoding with Lookahead Reasoning
Adaptive Discretization for Consistency Models
LOVECon: Text-driven Training-free Long Video Editing with ControlNet
SIFT: Grounding LLM Reasoning in Contexts via Stickers
Fast Quiet-STaR: Thinking Without Thought Tokens
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
3D-Properties: Identifying Challenges in DPO and Charting a Path Forward
SCott: Accelerating Diffusion Models with Stochastic Consistency Distillation
Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models
2024
Amortized Fourier Neural Operators
AdaMOE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models
Calibrating Deep Ensemble through Functional Variational Inference
Accurate and Reliable Forecasting using Stochastic Differential Equations
Lost in Translation: Latent Concept Misalignment in Text-to-Image Diffusion Models
Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model
SpikeZIP-TF: Conversion is All You Need for Transformer-based SNN
CLLMs: Consistency Large Language Models
Improved Operator Learning by Orthogonal Attention
Online Speculative Decoding
LOVECon: Text-driven Training-Free Long Video Editing with ControlNet
Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
2023
Towards Accelerated Model Training via Bayesian Data Selection
Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
On Calibrating Diffusion Probabilistic Models
Heterogeneous Multi-Task Gaussian Cox Processes
Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
Batch Virtual Adversarial Training for Graph Convolutional Networks
2022
BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning
Accelerated Linearized Laplace Approximation for Bayesian Deep Learning
Confidence-based Reliable Learning under Dual Noises
Efficient Inference for Dynamic Flexible Interactions of Neural Populations
NeuralEF: Deconstructing Kernels by Deep Neural Networks
Exploring Memorization in Adversarial Training
2021
Black-box Detection of Backdoor Attacks with Limited Information and Data
LiBRe: A Practical Bayesian Approach to Adversarial Detection
Measuring Uncertainty through Bayesian Learning of Deep Neural Network Structure
2020
Adversarial Distributional Training for Robust Deep Learning
Understanding and Exploring the Network with Stochastic Architectures
Autosync: Learning to Synchronize for Data-parallel Distributed Deep Learning
2019
Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
2018
Cavs: An Efficient Runtime System for Dynamic Neural Networks
2017
Structured Generative Adversarial Networks
No matching publications
Try a different title, author, venue, or research topic.