Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/7ICML 2026Poster· General Machine Learning / Hardware and Software

HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

Yuxuan Yang · Feiyang Ren · Bowen Zeng · Dalin Zhang · Jinpeng Chen · Gang Chen · Huan Li

代码效率与系统OpenReview

作者位次 #3/7ACL 2026Poster· Natural Language Processing

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLM s

Yicheng Ji · Jun Zhang · Jinpeng Chen · Cong Wang · Lidan Shou · Gang Chen · Huan Li

摘要

Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency due to autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing methods are constrained by rigid exact-match rules, severel...

效率与系统多模态代码OpenReview 项目页

作者位次 #2/9AAAI 2026Poster· Artificial Intelligence

DiMA: Distinguishing Resident and Tourist Preferences via Multi-Modal LLM Alignment for Out-of-Town Cross-Domain Recommendation

Fan Zhang · Jinpeng Chen · Tao Wang · Huan Li · Senzhang Wang · Feifei Kou · Ye Ji · Kaimin Wei · Zhenye Yang

对齐与偏好多模态OpenReview

Jinpeng Chen

获取完整研究档案

联系方式

2026 顶会论文

HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLM s

DiMA: Distinguishing Resident and Tourist Preferences via Multi-Modal LLM Alignment for Out-of-Town Cross-Domain Recommendation

常见合作者