Haiyang Sun
16 papers · 2019–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (18) π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (6)
π
Interdisciplinary Bridge
π
Century Club
(11)
β‘
Prolific Year
(5)
Conferences
AAAI (4)
ECCV (3)
ICML (3)
ACL (2)
INTERSPEECH (2)
ICCV (1)
IJCAI (1)
Top co-authors
Keywords
multimodal large language model
(2)
speech emotion recognition
(2)
visual perception
(1)
event camera
(1)
question answering
(1)
autonomous driving
(1)
neural architecture search
(1)
world model
(1)
adversarial training
(1)
bird's eye view
(1)
deepfake detection
(1)
mixed integer programming
(1)
text retrieval
(1)
knowledge graph embedding
(1)
point cloud
(1)
motion estimation
(1)
ai-generated image detection
(1)
cross-modal embedding
(1)
sample average approximation
(1)
3d reconstruction
(1)
Papers
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning
ACL 2026
BAT: Learning Event-based Optical Flow with Bidirectional Adaptive Temporal Correlation
AAAI 2026
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images
ACL 2026
CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving
AAAI 2026
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
AAAI 2026
BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving
AAAI 2025
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
ICCV 2025
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models
ICML 2025
OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition
ICML 2025
S2-Track: A Simple yet Strong Approach for End-to-End 3D Multi-Object Tracking
ICML 2025
MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition
INTERSPEECH 2024
OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection
ECCV 2024
Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
ECCV 2024
TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
ECCV 2024
EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition
INTERSPEECH 2023
Improving Law Enforcement Daily Deployment Through Machine Learning-Informed Optimization under Uncertainty
IJCAI 2019