Haiyun Guo
13 papers · 2019–2026 · 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (32)
π€
Dynamic Duo
(11)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(62)
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(8)
Deep Learning
(8)
Core AI
(8)
Computer Vision
(6)
Learning Types Β· Deep Learning
(6)
Machine Learning
(5)
Analysis
(2)
Application Areas
(2)
Applications
(2)
Architectures
(2)
Learning Paradigms
(2)
Learning Types Β· Machine Learning
(2)
Optimization & Theory
(2)
Processing
(2)
Robotics
(1)
Keywords
vision-language model
(4)
zero-shot learning
(2)
knowledge distillation
(2)
attention mechanism
(2)
continual learning
(2)
multimodal large language model
(2)
hallucination mitigation
(2)
composed image retrieval
(2)
large vision-language model
(2)
background subtraction
(1)
semantic alignment
(1)
image reconstruction
(1)
deep learning
(1)
facial landmark detection
(1)
image restoration
(1)
spatial representation
(1)
vision-language alignment
(1)
latent variable
(1)
probabilistic model
(1)
3d object detection
(1)
Papers
PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning
ACL 2026
ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval
CVPR 2026
WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval
CVPR 2026
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
ACL 2025
PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability
CVPR 2025
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
EMNLP 2025
SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models
EMNLP 2024
WaveMo: Learning Wavefront Modulations to See Through Scattering
CVPR 2024
ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection
CVPR 2023
PASS: Part-Aware Self-Supervised Pre-training for Person Re-identification
ECCV 2022
Adaptive Variance Based Label Distribution Learning For Facial Age Estimation
ECCV 2020
Identity-Guided Human Semantic Parsing for Person Re-Identification
ECCV 2020
Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection
CVPR 2019