Jiacheng Liang

7 papers · 2023–2026 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird

Venues

ACL (2) EMNLP (2) AAAI (1) CVPR (1) ICLR (1)

Top co-authors

Ting Wang (4) Tanqiu Jiang (3) Fenglong Ma (2) Zian Wang (2) Yuhui Wang (2) Rongyi Zhu (2) Rahul Gupta (1) Yao Ma (1) Zhaohan Xi (1) Changjiang Li (1)

Research topics

Artificial Intelligence (7) Core AI (6) Deep Learning (2) Machine Learning (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Computer Vision (1) Application Areas (1) Learning Paradigms (1) Optimization & Theory (1) Processing (1)

Keywords

jailbreak attack (3) safety alignment (2) key-value cache (2) adversarial prompt (2) adversarial robustness (2) reinforcement learning from human feedback (1) model alignment (1) convolutional neural network (1) adversarial defense (1) text watermark (1) language model (1) reward model (1) vision-language model (1) edge computing (1) watermark detection (1) red teaming (1) video processing (1) model acceleration (1) data curation (1) model customization (1)

Papers

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System ACL 2026 AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models ACL 2026 Dynamic Token Reweighting for Robust Vision-Language Models CVPR 2026 Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise EMNLP 2025 RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction ICLR 2025 Watermark under Fire: A Robustness Evaluation of LLM Watermarking EMNLP 2025 PASS: Patch Automatic Skip Scheme for Efficient Real-Time Video Perception on Edge Devices AAAI 2023