Shiyu Ji

6 papers · 2025–2026 · 3 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) ⭐ Rising Star (6)

Venues

EMNLP (3) AAAI (2) NAACL (1)

Top co-authors

Farnoosh Hashemi (3) Wanxiang Che (3) Qingfu Zhu (3) Yixuan Wang (3) Yuzhuang Xu (3) Soroush Vosoughi (3) Hefan Zhang (3) Yijun Liu (3) Joice Chen (3) Michael Macy (3)

Research topics

Artificial Intelligence (4) Core AI (4) Machine Learning (3) Natural Language Processing (3) Application Areas (3) Generation (3) Deep Learning (2) Optimization & Theory · Machine Learning (2) Applications (1) Architectures (1) Models (1) Optimization & Theory · Deep Learning (1)

Keywords

large language model (3) cache eviction (2) key-value cache (2) dialogue generation (2) efficient inference (1) synthetic data generation (1) persuasion detection (1) query optimization (1) mixture of expert (1) memory optimization (1) inference optimization (1) inference efficiency (1) cultural awareness (1) kv cache (1) language model inference (1) global information (1) expert pruning (1) kv cache eviction (1) transformer classifier (1) debate analysis (1)

Papers

CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis AAAI 2026 Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction AAAI 2026 A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling EMNLP 2025 Communication Makes Perfect: Persuasion Dataset Construction via Multi-LLM Communication NAACL 2025 Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information EMNLP 2025 Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query EMNLP 2025