Manyuan Zhang
13 papers · 2020–2026 · 4 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (28) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🔥 Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(52)
Top co-authors
Research topics
Deep Learning
(8)
Computer Vision
(5)
Artificial Intelligence
(4)
Architectures
(4)
Core AI · Artificial Intelligence
(4)
Machine Learning
(3)
Analysis
(3)
Models
(3)
Generation
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory
(2)
Core AI · Computer Vision
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Keywords
optical flow estimation
(2)
supervised fine-tuning
(2)
reinforcement learning
(2)
optical flow
(2)
object detection
(1)
motion estimation
(1)
representation learning
(1)
cross-domain learning
(1)
temporal modeling
(1)
video understanding
(1)
neural architecture search
(1)
visual reasoning
(1)
parameter efficient
(1)
label noise
(1)
chain-of-thought reasoning
(1)
feature encoding
(1)
direct preference optimization
(1)
diffusion model
(1)
reward model
(1)
transformer architecture
(1)
Papers
OneThinker: All-in-one Reasoning Model for Image and Video
CVPR 2026
Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
CVPR 2026
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
CVPR 2026
Let's Verify and Reinforce Image Generation Step by Step
CVPR 2025
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding
EMNLP 2025
Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
ECCV 2024
Three Things We Need to Know About Transferring Stable Diffusion to Visual Dense Prediciton Tasks
ECCV 2024
Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection
ICCV 2023
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
CVPR 2023
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
ICCV 2023
Towards Robust Face Recognition with Comprehensive Search
ECCV 2022
Switchable K-Class Hyperplanes for Noise-Robust Representation Learning
ICCV 2021
Discriminability Distillation in Group Representation Learning
ECCV 2020