Xiangyu Peng
17 papers · 2021–2026 · 7 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 ↓+5 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (46) 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird
🌈
Renaissance Researcher
(6)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(91)
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(10)
Machine Learning
(9)
Natural Language Processing
(8)
Deep Learning
(5)
Application Areas
(4)
Generation
(4)
Learning Types · Machine Learning
(4)
Optimization & Theory
(4)
Applications
(3)
Architectures
(2)
Core Methods
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Data Science & Analytics
(1)
Keywords
story generation
(3)
large language model
(3)
gradient matching
(2)
retrieval-augmented generation
(2)
knowledge graph
(2)
few-shot learning
(1)
semi-supervised learning
(1)
contrastive learning
(1)
self-supervised learning
(1)
text classification
(1)
knowledge transfer
(1)
knowledge distillation
(1)
conversational ai
(1)
question answering
(1)
benchmark evaluation
(1)
narrative generation
(1)
commonsense knowledge
(1)
computer vision
(1)
content moderation
(1)
text generation
(1)
Papers
Don’t Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
ACL 2026
Benchmarking Deep Search over Heterogeneous Enterprise Data
EMNLP 2025
BingoGuard: LLM Content Moderation Tools with Risk Levels
ICLR 2025
ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
ICLR 2025
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
ACL 2025
Unanswerability Evaluation for Retrieval Augmented Generation
ACL 2025
Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs
ACL 2024
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
ICLR 2024
Dataset Quantization
ICCV 2023
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
ICLR 2023
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
ICLR 2023
CAFE: Learning To Condense Dataset by Aligning Features
CVPR 2022
Crafting Better Contrastive Views for Siamese Representation Learning
CVPR 2022
Guiding Neural Story Generation with Reader Models
EMNLP 2022
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning
EMNLP 2022
Inherently Explainable Reinforcement Learning in Natural Language
NeurIPS 2022
Automatic Story Generation: Challenges and Attempts
NAACL 2021