Fangzhi Xu
18 papers · 2023–2026 · 5 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 (39) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π€ Dynamic Duo (10)
π
Renaissance Researcher
(6)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(88)
Venues
Top co-authors
Research topics
Artificial Intelligence
(16)
Core AI
(16)
Machine Learning
(7)
Deep Learning
(6)
Natural Language Processing
(5)
Learning Types Β· Machine Learning
(5)
Learning Types Β· Deep Learning
(3)
Resources & Methods
(3)
Computer Vision
(2)
Knowledge & Reasoning
(2)
Application Areas
(2)
Applications
(2)
Architectures
(2)
Core Methods
(2)
Optimization & Theory
(2)
Keywords
large language model
(6)
vision-language model
(6)
multimodal learning
(3)
gui agent
(2)
logical reasoning
(2)
reward model
(2)
task automation
(2)
image captioning
(1)
uncertainty quantification
(1)
benchmark evaluation
(1)
question answering
(1)
entity linking
(1)
document-level extraction
(1)
visual grounding
(1)
transfer learning
(1)
formal verification
(1)
instruction tuning
(1)
attention mechanism
(1)
iterative refinement
(1)
synthetic data generation
(1)
Papers
MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
AAAI 2026
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
ACL 2026
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
ACL 2026
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents
ACL 2026
AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant
ACL 2025
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
ACL 2025
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
ACL 2025
Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
ACL 2025
OS-ATLAS: Foundation Action Model for Generalist GUI Agents
ICLR 2025
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
ACL 2025
Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models
ACL 2025
Vision-Language Models Can Self-Improve Reasoning via Reflection
NAACL 2025
π-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
ACL 2025
A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction
COLING 2024
PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering
ACL 2024
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
ACL 2024
Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
ACL 2024
TECHS: Temporal Logical Graph Networks for Explainable Extrapolation Reasoning
ACL 2023