Get started
Author

Hexuan Deng

Observed name: Deng, Hexuan
OpenAlex ID: A5043368238
Improving Simultaneous Machine Translation with Monolingual Data
2023 · Hexuan Deng, Liang Ding, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 5
PDF
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
2024 · Hexuan Deng, Wenxiang Jiao, et al. · neural information processing systems · 2
PDF
Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning
2026 · Jun Rao, Xuebo Liu, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 1
PDF
SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
2025 · Wang, Chen, Li, Zhaochun, et al. · arXiv (Cornell University) · 1
PDF
The Advancements and Progresses of Artificial Intelligence-Based Keyword Extraction Methods
2024 · Hexuan Deng · Advances in intelligent systems research/Advances in Intelligent Systems Research · 1
PDF
Curriculum Consistency Learning for Conditional Sentence Generation
2024 · Liangxin Liu, Xuebo Liu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction
2026 · Deng, Hexuan, Wang, Yue, et al. · arXiv (Cornell University)
PDF
GRPODropout: Less is More for Online Reinforcement Learning Rollouts
2026 · Deng, Hexuan, Yan, Zihao, et al. · arXiv (Cornell University)
PDF
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
2026 · Yang, Cheng, Wu, Yifan, et al. · arXiv (Cornell University)
PDF
CRISP: Critical Step Perception for Training Efficient Deep Search Agents
2026 · Mo, Haosi, Yan, Zihao, et al. · arXiv (Cornell University)
PDF
Distilled Reinforcement Learning for LLM Post-training
2026 · Wang, Chen, Li, Zhaochun, et al. · arXiv (Cornell University)
PDF
CoCoReviewBench: A Completeness- and Correctness-Oriented Benchmark for AI Reviewers
2026 · Deng, Hexuan, Ke, Xiaopeng, et al. · arXiv (Cornell University)
PDF
Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training
2026 · Wang, Chen, Deng, Hexuan, et al. · arXiv (Cornell University)
PDF
MemoNoveltyAgent: A Historical Research Memory-Aware Agent Workflow for Paper Novelty Assessment
2026 · Hou, Jiajun, Deng, Hexuan, et al. · arXiv (Cornell University)
PDF
RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
2026 · Yuan, Bo, Deng, Hexuan, et al. · arXiv (Cornell University)
PDF
Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
2026 · Nie, Shuo, Deng, Hexuan, et al. · arXiv (Cornell University)
PDF
MemoNoveltyAgent: A Historical-Memory-Augmented Multi-Agent System for Paper Novelty Assessment
2026 · JiaJun Hou, Hexuan Deng, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
AgentTAC: Mining Temporal Action-Context Error Patterns from Agent Traces
2026 · Chenchen Zhao, Muxi Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
2025 · Deng, Hexuan, Jiao, Wenxiang, et al. · arXiv (Cornell University)
PDF
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
2025 · Hexuan Deng, Wenxiang Jiao, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
2025 · Xiaopeng Ke, Hexuan Deng, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
2024 · Hexuan Deng, Xin Zhang, et al. · SIGHAN Workshop on Chinese Language Processing (SIGHAN)
PDF
Works count: 25
Citation count: 11
H-index: 2
I10-index:
Year
Topic
Type