Skip to content
conftrace_

Ziqian Zeng

31 papers · 2017–2026 · 10 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 ↓
+5 more ↓ πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Gold πŸŒ‰ Interdisciplinary Bridge Β· Silver πŸ—ΊοΈ Taxonomy Completionist (75) 🀝 Dynamic Duo (16)
πŸ—ƒοΈ Keyword Collector (148) πŸ”₯ Unstoppable Β· Bronze ⚑ Prolific Year Β· Prolific 🌈 Renaissance Researcher (6) πŸ’Ž Century Club Β· Bronze

Venues

ACL (7) EMNLP (6) AAAI (4) CVPR (3) COLING (2) ICML (2) IJCAI (2) NAACL (2) NeurIPS (2) EACL (1)

Top co-authors

HUIPING ZHUANG (16) Cen Chen (13) Run He (7) Haoran Li (6) Yangqiu Song (6) Di Fang (4) Jianwei Wang (4) Kai Tong (4) Hao Peng (4) Libo Zhao (3)

Research topics

Machine Learning (27) Artificial Intelligence (21) Learning Types Β· Machine Learning (17) Core AI (15) Deep Learning (11) Natural Language Processing (10) Application Areas (9) Learning Types Β· Deep Learning (9) Optimization & Theory Β· Machine Learning (7) Applications (6) Core Methods (6) Learning Paradigms (6) Optimization & Theory Β· Deep Learning (4) Resources & Methods (4) Security & Privacy (2)

Keywords

large language model (5) class-incremental learning (5) analytic learning (5) weakly supervised learning (4) catastrophic forgetting (4) adaptive policy (3) continual learning (3) closed-form solution (3) simultaneous machine translation (3) differential privacy (2) translation latency (2) variational inference (2) reinforcement learning (2) exemplar-free learning (2) word embedding (2) safety alignment (2) multimodal large language model (2) sentiment classification (2) few-shot learning (2) read-write policy (2)

Papers

Activation-Guided Local Editing for Jailbreaking Attacks ACL 2026 ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior CVPR 2026 MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning ACL 2026 Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography AAAI 2026 RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior AAAI 2026 AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models CVPR 2025 Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning EMNLP 2025 DrFrattn: Directly Learn Adaptive Policy from Attention for Simultaneous Machine Translation EMNLP 2025 GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models ACL 2025 L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning ICML 2025 PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration ACL 2025 RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis EMNLP 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025 SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings ACL 2025 Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning ICML 2025 ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference AAAI 2024 Dissecting Fine-Tuning Unlearning in Large Language Models EMNLP 2024 DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning AAAI 2024 F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning NeurIPS 2024 GACL: Exemplar-Free Generalized Analytic Continual Learning NeurIPS 2024 On the Use of Silver Standard Data for Zero-shot Classification Tasks in Information Extraction COLING 2024 PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation EMNLP 2024 Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator COLING 2024 Adaptive Policy with Wait-k Model for Simultaneous Translation EMNLP 2023 From Ultra-Fine to Fine: Fine-tuning Ultra-Fine Entity Typing Models to Fine-grained ACL 2023 GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task CVPR 2023 Weakly Supervised Text Classification using Supervision Signals from a Language Model NAACL 2022 Variational Weakly Supervised Sentiment Analysis with Posterior Regularization EACL 2021 A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification NAACL 2019 Biased Random Walk based Social Regularization for Word Embeddings IJCAI 2018 Socialized Word Embeddings IJCAI 2017