Xingchao Liu
23 papers · 2020–2025 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (42) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(17)
π§
Keyword Pioneer
π
Grand Slam
π§¬
Topic Evolution
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(111)
Top co-authors
Research topics
Deep Learning
(15)
Machine Learning
(15)
Models
(11)
Computer Vision
(10)
Optimization & Theory
(8)
Generation
(7)
Artificial Intelligence
(6)
Mathematics & Optimization
(4)
Application Areas
(4)
Learning Types Β· Machine Learning
(4)
Architectures
(3)
Core AI
(3)
Learning Types Β· Deep Learning
(3)
Optimization
(3)
Techniques
(3)
Keywords
diffusion model
(7)
image generation
(5)
knowledge distillation
(3)
rectified flow
(3)
langevin dynamics
(3)
ordinary differential equation
(2)
autoregressive model
(2)
vision-language model
(2)
gradient-based sampling
(2)
multi-objective optimization
(2)
generative model
(2)
markov chain monte carlo
(2)
point cloud generation
(2)
multimodal understanding
(2)
model compression
(2)
multimodal learning
(2)
flow matching
(2)
neural network optimization
(2)
gradient descent
(2)
one-step generation
(2)
Papers
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
CVPR 2025
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
CVPR 2025
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies
NeurIPS 2024
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
ICLR 2024
LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows
NAACL 2024
Layer Compression of Deep Networks with Straight Flows
AAAI 2024
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
NeurIPS 2024
SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
ECCV 2024
DISCS: A Benchmark for Discrete Sampling
NeurIPS 2023
Fast Point Cloud Generation With Straight Flows
CVPR 2023
FlowGrad: Controlling the Output of Generative ODEs With Gradients
CVPR 2023
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
ICLR 2023
Learning Diffusion Bridges on Constrained Domains
ICLR 2023
A Langevin-like Sampler for Discrete Distributions
ICML 2022
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
NAACL 2022
Diffusion-based Molecule Generation with Informative Prior Bridges
NeurIPS 2022
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
EMNLP 2022
Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach
NeurIPS 2021
Conflict-Averse Gradient Descent for Multi-task learning
NeurIPS 2021
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
AAAI 2021
Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent
NeurIPS 2021
Sampling with Trusthworthy Constraints: A Variational Gradient Framework
NeurIPS 2021
Certified Monotonic Neural Networks
NeurIPS 2020