← Authors

Zihan Zhang

52 papers · 2019–2026 · 15 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (15) 🐝 Cross-Pollinator (9) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (11) 🧭 Keyword Pioneer πŸƒ Academic Marathon (7) πŸ† Grand Slam 🀝 Dynamic Duo (11) πŸ”¬ Deep Specialist (11) πŸ”₯ Unstoppable (8) ⚑ Prolific Year (5) ❓ The Questioner (3) πŸ—ƒοΈ Keyword Collector (237) πŸ’Ž Century Club (49)

Conferences

EMNLP (10) ACL (8) NIPS (7) COLT (6) AAAI (5) ICML (3) COLING (2) ICLR (2) INTERSPEECH (2) NAACL (2) CVPR (1) ECCV (1) IJCAI (1) JMLR (1) WACV (1)

Top co-authors

Qi Zhang (11) Haizhen Huang (11) Shaohan Huang (10) Weiwei Deng (10) Furu Wei (10) Xiangyang Ji (9) Feng Sun (8) Ling Chen (7) Meng Fang (7) Yuxin Chen (5)

Keywords

regret bound (8) large language model (8) sample complexity (7) reinforcement learning (6) markov decision process (5) sentence embedding (3) model-free reinforcement learning (3) speech enhancement (3) knowledge distillation (3) retrieval-augmented generation (3) pre-trained language model (2) diffusion model (2) language model (2) few-shot learning (2) curriculum learning (2) instruction tuning (2) multimodal learning (2) text generation (2) natural language processing (2) model compression (2)

Papers

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration AAAI 2026
NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction WACV 2026
Knowledge-Enhanced Explainable Hypergraph Convolution Network for Medication Recommendation AAAI 2026
GraphRAG-Induced Dual Knowledge Structure Graphs for Personalized Learning Path Recommendation AAAI 2026
Context-DPO: Aligning Language Models for Context-Faithfulness ACL 2025
Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback ICML 2025
NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning EMNLP 2025
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits ICLR 2025
Anytime Acceleration of Gradient Descent COLT 2025
Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving EMNLP 2025
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning ACL 2025
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement ACL 2025
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering ACL 2024
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs NIPS 2024
Text Diffusion with Reinforced Conditioning AAAI 2024
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition ACL 2024
ResLoRA: Identity Residual Mapping in Low-Rank Adaption ACL 2024
Calibrating LLM-Based Evaluator COLING 2024
Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition COLING 2024
Settling the sample complexity of online reinforcement learning COLT 2024
Optimal Multi-Distribution Learning COLT 2024
Vision-Language Dual-Pattern Matching for Out-of-Distribution Detection ECCV 2024
MedINST: Meta Dataset of Biomedical Instructions EMNLP 2024
Horizon-Free Regret for Linear Markov Decision Processes ICLR 2024
BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation INTERSPEECH 2024
Classification with Deep Neural Networks and Logistic Loss JMLR 2024
Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning NAACL 2024
Democratizing Reasoning Ability: Tailored Learning from Large Language Model EMNLP 2023
Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes COLT 2023
Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting NIPS 2023
Turn-Level Active Learning for Dialogue State Tracking EMNLP 2023
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances EMNLP 2023
Auto Search Indexer for End-to-End Document Retrieval EMNLP 2023
CITB: A Benchmark for Continual Instruction Tuning EMNLP 2023
Decoupling MaxLogit for Out-of-Distribution Detection CVPR 2023
Pre-training Language Model as a Multi-perspective Course Learner ACL 2023
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding ACL 2023
PromptBERT: Improving BERT Sentence Embeddings with Prompts EMNLP 2022
RoChBert: Towards Robust BERT Fine-tuning for Chinese EMNLP 2022
Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning NIPS 2022
The HCCL System for the NIST SRE21 INTERSPEECH 2022
Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies COLT 2022
Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics NAACL 2022
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon COLT 2021
Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity ICML 2021
Near Optimal Reward-Free Reinforcement Learning ICML 2021
Learning from My Friends: Few-Shot Personalized Conversation Systems via Social Networks AAAI 2021
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP NIPS 2021
Argot: Generating Adversarial Readable Chinese Texts IJCAI 2020
Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition NIPS 2020
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function NIPS 2019
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification NIPS 2019