Ryo Hachiuma
16 papers · 2021–2026 · 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (47) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π
Renaissance Researcher
(6)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(77)
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(10)
Deep Learning
(9)
Computer Vision
(8)
Machine Learning
(7)
Learning Types Β· Deep Learning
(6)
Learning Types Β· Machine Learning
(5)
Analysis
(4)
Application Areas
(4)
Generation
(2)
Processing
(2)
Data Science & Analytics
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Speech & Audio
(1)
Keywords
vision-language model
(7)
gender bia
(3)
knowledge distillation
(3)
action recognition
(2)
image captioning
(2)
video understanding
(2)
societal bia
(2)
skeleton-based recognition
(2)
spatio-temporal action localization
(2)
model compression
(2)
spurious correlation
(2)
multimodal large language model
(2)
feature embedding
(1)
point cloud
(1)
temporal modeling
(1)
speech recognition
(1)
benchmark evaluation
(1)
dynamics modeling
(1)
visual question answering
(1)
offline reinforcement learning
(1)
Papers
4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
CVPR 2026
Interpretable Debiasing of Vision-Language Models for Social Fairness
CVPR 2026
Learning from Synthetic Data via Provenance-Based Input Gradient Guidance
CVPR 2026
Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
CVPR 2026
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception
ACL 2026
Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
ICCV 2025
CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting
WACV 2025
LOTUS: A Leaderboard for Detailed Image Captioning from Quality to Societal Bias and User Preferences
ACL 2025
Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
CVPR 2025
SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP
ICLR 2025
VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models
CVPR 2025
From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment
EMNLP 2024
Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition
ECCV 2024
Prompt-Guided Zero-Shot Anomaly Action Recognition Using Pretrained Deep Skeleton Features
CVPR 2023
Unified Keypoint-Based Action Recognition Framework via Structured Keypoint Pooling
CVPR 2023
Dynamics-regulated kinematic policy for egocentric pose estimation
NeurIPS 2021