← Authors

Zhiyuan Zeng

26 papers · 2021–2025 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (48) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸ† Keyword Champion (2) 🀝 Dynamic Duo (10) πŸ—ƒοΈ Keyword Collector (88) ❓ The Questioner ⚑ Prolific Year (8) πŸ’Ž Century Club (26) πŸ”₯ Unstoppable (5)

Conferences

ACL (9) EMNLP (5) ICLR (3) IJCNLP (3) COLING (2) NAACL (2) ICML (1) IJCAI (1)

Top co-authors

Weiran Xu (10) Keqing He (9) Yanan Wu (8) Zhangyue Yin (7) Yuanmeng Yan (7) Xipeng Qiu (7) Hong Xu (6) Huixing Jiang (6) Qipeng Guo (5) Qinyuan Cheng (5)

Keywords

out-of-domain detection (7) dialogue system (5) intent detection (4) large language model (4) intent classification (4) adversarial augmentation (3) contrastive learning (3) unknown slot type (2) adversarial attack (2) attention distribution (2) dialog system (2) neural machine translation (2) autoregressive model (2) task-oriented dialogue (2) representation learning (2) mixture of expert (2) slot detection (2) bayesian inference (1) confidence calibration (1) domain adaptation (1)

Papers

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities? ACL 2025
Dynamic and Generalizable Process Reward Modeling ACL 2025
Evaluating Large Language Models at Evaluating Instruction Following ICLR 2024
Turn Waste into Worth: Rectifying Top-k Router of MoE EMNLP 2024
Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk EMNLP 2024
Exploring the Benefit of Activation Sparsity in Pre-training ICML 2024
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models COLING 2024
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning ICLR 2024
Explicit Memory Learning with Expectation Maximization EMNLP 2024
Reasoning in Flux: Enhancing Large Language Models Reasoning through Uncertainty-aware Adaptive Guidance ACL 2024
Emergent Modularity in Pre-trained Transformers ACL 2023
Unsupervised and Few-Shot Parsing from Pretrained Language Models (Extended Abstract) IJCAI 2023
Plug-and-Play Knowledge Injection for Pre-trained Language Models ACL 2023
SCoMoE: Efficient Mixtures of Experts with Structured Communication ICLR 2023
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold NAACL 2022
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning ACL 2022
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation COLING 2022
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning EMNLP 2022
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization EMNLP 2021
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning ACL 2021
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter ACL 2021
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System IJCNLP 2021
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter IJCNLP 2021
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning IJCNLP 2021
Adversarial Self-Supervised Learning for Out-of-Domain Detection NAACL 2021
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System ACL 2021