Zhiyuan Fan
21 papers · 2023–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (14) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Renaissance Researcher (9)
πΊοΈ
Taxonomy Completionist
(49)
π
Cross-Pollinator
(14)
π₯
Mega-Team
(25)
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(101)
π
Century Club
(18)
Conferences
ACL (7)
EMNLP (4)
NIPS (4)
COLT (2)
ICML (2)
MICCAI (1)
NAACL (1)
Top co-authors
Keywords
online learning
(2)
vision-language model
(2)
retrieval-augmented generation
(2)
regret bound
(2)
benchmark evaluation
(2)
multimodal learning
(2)
language model
(2)
hallucination mitigation
(2)
feature selection
(1)
question answering
(1)
game theory
(1)
model evaluation
(1)
named entity recognition
(1)
text generation
(1)
data augmentation
(1)
medical imaging
(1)
transfer learning
(1)
code generation
(1)
confidence calibration
(1)
direct preference optimization
(1)
Papers
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models
ACL 2026
Learning Diverse Responses with Prefix-Conditioned Supervised Fine-Tuning
ACL 2026
Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation
ACL 2026
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
NAACL 2025
MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibration
ACL 2025
SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs
ACL 2025
Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward
ACL 2025
Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries
COLT 2025
Prototype-Guided Cross-Modal Knowledge Enhancement for Adaptive Survival Prediction
MICCAI 2025
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation
EMNLP 2025
MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing
EMNLP 2025
Calibrated Self-Rewarding Vision Language Models
NIPS 2024
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games
NIPS 2024
Achieving Constant Regret in Linear Markov Decision Processes
NIPS 2024
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
NIPS 2024
Exploring the Potential of Dense Information in Multimodal Alignment
ACL 2024
SedarEval: Automated Evaluation using Self-Adaptive Rubrics
EMNLP 2024
OpenFE: Automated Feature Generation with Expert-level Performance
ICML 2023
On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
ICML 2023
Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
EMNLP 2023
Efficient Algorithms for Sparse Moment Problems without Separation
COLT 2023