Xinyu Fang
10 papers · 2023–2026 · 6 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 ↑
🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (27) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI · Artificial Intelligence
(9)
Machine Learning
(7)
Learning Types
(4)
Computer Vision
(3)
Deep Learning
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Core AI · Computer Vision
(2)
Models
(2)
Resources & Methods
(2)
Interdisciplinary
(1)
Application Areas
(1)
Architectures
(1)
Cognitive Science
(1)
Keywords
benchmark evaluation
(4)
multimodal learning
(3)
multimodal large language model
(3)
visual reasoning
(2)
vision-language model
(2)
large language model
(2)
temporal reasoning
(1)
direct preference optimization
(1)
few-shot learning
(1)
video understanding
(1)
document understanding
(1)
visual grounding
(1)
embodied interaction
(1)
evaluation methodology
(1)
visual question answering
(1)
reward model
(1)
region detection
(1)
inverse planning
(1)
tool use
(1)
relation extraction
(1)
Papers
ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning
CVPR 2026
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLMs
ICCV 2025
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation
ACL 2025
MuMA-ToM: Multi-modal Multi-Agent Theory of Mind
AAAI 2025
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
ACL 2025
Redundancy Principles for MLLMs Benchmarks
ACL 2025
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
NeurIPS 2024
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
NeurIPS 2024
ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs
EMNLP 2024
Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting
NeurIPS 2023