Xiangyu Peng
17 papers · 2021–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Cross-Pollinator (10) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (7) π Renaissance Researcher (8)
π§
Keyword Pioneer
π
Cross-Pollinator
(10)
π₯
Unstoppable
(5)
π
Century Club
(16)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(65)
Conferences
ICLR (5)
ACL (4)
EMNLP (3)
CVPR (2)
ICCV (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
story generation
(3)
knowledge graph
(2)
retrieval-augmented generation
(2)
gradient matching
(2)
computer vision
(1)
self-supervised learning
(1)
contrastive learning
(1)
prompt engineering
(1)
benchmark evaluation
(1)
text generation
(1)
commonsense knowledge
(1)
narrative generation
(1)
model architecture
(1)
explainable ai
(1)
knowledge base
(1)
question answering
(1)
procedural generation
(1)
evaluation framework
(1)
natural language
(1)
natural language understanding
(1)
Papers
Donβt Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
ACL 2026
Unanswerability Evaluation for Retrieval Augmented Generation
ACL 2025
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
ACL 2025
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
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
ICLR 2024
Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs
ACL 2024
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
ICLR 2023
Dataset Quantization
ICCV 2023
Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning
ICLR 2023
Crafting Better Contrastive Views for Siamese Representation Learning
CVPR 2022
Guiding Neural Story Generation with Reader Models
EMNLP 2022
Inherently Explainable Reinforcement Learning in Natural Language
NIPS 2022
Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning
EMNLP 2022
CAFE: Learning To Condense Dataset by Aligning Features
CVPR 2022
Automatic Story Generation: Challenges and Attempts
NAACL 2021