Yixin Ji

19 papers · 2018–2026 · 8 conferences · across top CS/AI conferences

Achievements

+8 more ↓

🌍 Conference Polyglot (7) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7)

🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (7) 🏃 Academic Marathon (7) 🏆 Keyword Champion (2) 🧬 Topic Evolution 🗃️ Keyword Collector (80) 💎 Century Club (16) ⚡ Prolific Year (5)

Conferences

EMNLP (6) ACL (5) CVPR (2) IJCAI (2) COLING (1) EACL (1) ICLR (1) NAACL (1)

Top co-authors

Min Zhang (11) Juntao Li (11) Kaixin Wu (4) Xinchao Wang (3) Jingwen Ye (3) Mingli Song (3) Yang Xiang (3) Zhaorui Tan (2) Penglei Gao (2) Xu Jia (2)

Keywords

model compression (4) multi-task learning (3) large language model (3) knowledge distillation (3) in-context learning (3) question answering (2) zero-shot learning (2) retrieval-augmented generation (2) knowledge amalgamation (2) isotropic representation (2) convolutional neural network (2) transfer learning (2) preference alignment (1) machine translation (1) feature distribution (1) semantic segmentation (1) contrastive learning (1) deformable convolution (1) language modeling (1) domain adaptation (1)

Papers

GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection EACL 2026 DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward ACL 2026 When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning ACL 2026 CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search NAACL 2025 Beware of Calibration Data for Pruning Large Language Models ICLR 2025 GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models ACL 2025 IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing EMNLP 2024 Demonstration Augmentation for Zero-shot In-context Learning ACL 2024 Exploring and Mitigating Shortcut Learning for Generative Large Language Models COLING 2024 Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization EMNLP 2024 Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering EMNLP 2024 Isotropic Representation Can Improve Zero-Shot Cross-Lingual Transfer on Multilingual Language Models EMNLP 2023 Isotropy-Enhanced Conditional Masked Language Models EMNLP 2023 Early Exit with Disentangled Representation and Equiangular Tight Frame ACL 2023 Beware of Model Collapse! Fast and Stable Test-time Adaptation for Robust Question Answering EMNLP 2023 Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN CVPR 2020 Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers IJCAI 2019 Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More CVPR 2019 Semantic Locality-Aware Deformable Network for Clothing Segmentation IJCAI 2018