Mingyu Liu
17 papers · 2022–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (13) 🌍 Conference Polyglot (8) 🌉 Interdisciplinary Bridge
🐝
Cross-Pollinator
(13)
🧭
Keyword Pioneer
🔥
Unstoppable
(5)
⚡
Prolific Year
(9)
💎
Century Club
(13)
❓
The Questioner
🗃️
Keyword Collector
(63)
Conferences
AAAI (4)
ICLR (3)
ECCV (2)
ICML (2)
IJCAI (2)
ACL (1)
CVPR (1)
ICCV (1)
WACV (1)
Top co-authors
Keywords
reinforcement learning
(3)
zero-shot learning
(2)
multimodal large language model
(2)
sim-to-real transfer
(1)
point cloud
(1)
transfer learning
(1)
semantic segmentation
(1)
scene understanding
(1)
video generation
(1)
chain-of-thought reasoning
(1)
distribution matching
(1)
channel attention
(1)
3d vision
(1)
image dehazing
(1)
visual recognition
(1)
image restoration
(1)
vector quantization
(1)
distribution shift
(1)
image deblurring
(1)
representation learning
(1)
Papers
Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment
ACL 2026
Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Models
AAAI 2026
SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models
AAAI 2026
ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
AAAI 2026
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequences
ICLR 2025
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
ICLR 2025
TUMTraf VideoQA: Dataset and Benchmark for Unified Spatio-Temporal Video Understanding in Traffic Scenes
ICML 2025
Seeing the Unseen: Composing Outliers for Compositional Zero-Shot Learning
IJCAI 2025
3D Understanding of Deformable Linear Objects: Datasets and Transferability Benchmark
WACV 2025
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
ICML 2025
MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation
CVPR 2025
VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
ICCV 2025
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
ICLR 2025
Hybrid Frequency Modulation Network for Image Restoration
IJCAI 2024
Take A Step Back: Rethinking the Two Stages in Visual Reasoning
ECCV 2024
FanoutNet: A Neuralized PCB Fanout Automation Method Using Deep Reinforcement Learning
AAAI 2023
3D Object Detection with a Self-Supervised Lidar Scene Flow Backbone
ECCV 2022