Fei Sun

41 papers · 2015–2026 · 11 conferences · across top CS/AI conferences

Achievements

+10 more ↓

🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (11) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (11)

🏃 Academic Marathon (10) 🗺️ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🤝 Dynamic Duo (11) 🏆 Grand Slam 🗃️ Keyword Collector (175) ❓ The Questioner ⚡ Prolific Year (10) 💎 Century Club (37) 🔥 Unstoppable (7)

Conferences

ACL (12) EMNLP (8) CVPR (6) AAAI (4) IJCAI (4) ICML (2) ICLR (1) IJCNLP (1) NAACL (1) NIPS (1) WACV (1)

Top co-authors

Huawei Shen (13) Xueqi Cheng (13) Du Su (7) Qi Cao (7) Wanli Yang (5) Hexiang Tan (5) Jingang Wang (4) Yuanzhuo Wang (4) Xinyu Ma (3) Yen-Kuang Chen (3)

Keywords

large language model (6) model compression (5) model editing (3) recommender system (3) retrieval-augmented generation (3) neural architecture search (2) sequential editing (2) efficient computing (2) knowledge editing (2) hardware-aware design (2) confidence calibration (2) autoregressive transformer (1) image classification (1) self-attention mechanism (1) algorithmic fairness (1) vision transformer (1) representation learning (1) causal inference (1) benchmark evaluation (1) bayesian inference (1)

Papers

BaseCal: Unsupervised Confidence Calibration via Base Model Signals ACL 2026 The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis ACL 2026 AuditAgent: LLM Agent for Risks Auditing in Recommender Systems AAAI 2026 LiR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation AAAI 2026 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs EMNLP 2025 The Mirage of Model Editing: Revisiting Evaluation in the Wild ACL 2025 InductionBench: LLMs Fail in the Simplest Complexity Class ACL 2025 Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector ACL 2025 PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025 KAN-AD: Time Series Anomaly Detection with Kolmogorov–Arnold Networks ICML 2025 Reinforced Lifelong Editing for Language Models ICML 2025 Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models EMNLP 2025 Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation NIPS 2024 PDE+: Enhancing Generalization via PDE with Adaptive Distributional Diffusion AAAI 2024 Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? ACL 2024 The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse ACL 2024 When to Trust LLMs: Aligning Confidence with Response Quality ACL 2024 Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts ACL 2024 EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything CVPR 2024 TEA: Test-time Energy Adaptation CVPR 2024 The Fall of ROME: Understanding the Collapse of LLMs in Model Editing EMNLP 2024 Pruning Foundation Models for High Accuracy without Retraining EMNLP 2024 ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation EMNLP 2023 Multi-Scale Distribution Deep Variational Autoencoder for Explanation Generation ACL 2022 Neural Re-ranking in Multi-stage Recommender Systems: A Review IJCAI 2022 Effective Model Sparsification by Scheduled Grow-and-Prune Methods ICLR 2022 CHEX: CHannel EXploration for CNN Model Compression CVPR 2022 Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation EMNLP 2021 Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization AAAI 2020 Learning in the Frequency Domain CVPR 2020 Intent Preference Decoupling for User Representation on Online Recommender System IJCAI 2020 Tag2Gauss: Learning Tag Representations via Gaussian Distribution in Tagged Networks IJCAI 2019 FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search CVPR 2019 Deep Session Interest Network for Click-Through Rate Prediction IJCAI 2019 Improving Multi-turn Dialogue Modelling with Utterance ReWriter ACL 2019 ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation CVPR 2019 Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations IJCNLP 2015 Learning Word Representations by Jointly Modeling Syntagmatic and Paradigmatic Relations ACL 2015 Component-Enhanced Chinese Character Embeddings EMNLP 2015