Skip to content
conftrace_

Junyuan Hong

20 papers · 2021–2025 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+6 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Bronze πŸ—ΊοΈ Taxonomy Completionist (35) 🀝 Dynamic Duo (13)
πŸ† Grand Slam 🀝 Dynamic Duo (13) ⚑ Prolific Year Β· Productive πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (93) πŸ”₯ Unstoppable Β· Bronze

Venues

ICML (6) ICLR (5) NeurIPS (3) AAAI (2) NAACL (2) AISTATS (1) EMNLP (1)

Top co-authors

Jiayu Zhou (13) Zhangyang Wang (10) Haotao Wang (6) Lingjuan Lyu (3) Bo Li (3) Shuyang Yu (3) Tianlong Chen (3) Kaidi Xu (3) Mehrdad Mahdavi (2) Jinhao Duan (2)

Research topics

Artificial Intelligence (17) Machine Learning (15) Application Areas (10) Core AI (10) Learning Paradigms Β· Artificial Intelligence (8) Deep Learning (7) Natural Language Processing (4) Optimization & Theory Β· Machine Learning (4) Learning Types Β· Machine Learning (3) Learning Types Β· Deep Learning (3) Techniques (3) Core Methods (2) Learning Paradigms Β· Machine Learning (2) Optimization & Theory Β· Deep Learning (2) Resources & Methods (2)

Keywords

federated learning (5) distributed learning (3) knowledge distillation (3) model compression (3) differential privacy (2) adversarial robustness (2) communication efficiency (2) out-of-distribution detection (2) non-iid data (2) transfer learning (2) backdoor attack (2) deep neural network (2) large language model (2) model aggregation (2) knowledge transfer (1) knowledge extraction (1) unsupervised pretraining (1) ensemble learning (1) representation learning (1) prompt engineering (1)

Papers

Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025 GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning ICML 2025 GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing NAACL 2025 MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models EMNLP 2025 Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression ICML 2024 DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer ICLR 2024 On the Generalization Ability of Unsupervised Pretraining AISTATS 2024 Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ICML 2024 Safe and Robust Watermark Injection with a Single OoD Image ICLR 2024 Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning AAAI 2023 MECTA: Memory-Economic Continual Test-Time Model Adaptation ICLR 2023 Revisiting Data-Free Knowledge Distillation with Poisoned Teachers ICML 2023 Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection ICLR 2023 Understanding Deep Gradient Leakage via Inversion Influence Functions NeurIPS 2023 Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization ICLR 2022 Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling NeurIPS 2022 Resilient and Communication Efficient Learning for Heterogeneous Federated Systems ICML 2022 Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork NeurIPS 2022 Data-Free Knowledge Distillation for Heterogeneous Federated Learning ICML 2021 Learning Model-Based Privacy Protection under Budget Constraints AAAI 2021