PPaperPicks

Jie Peng

University of Science and Technology of China, Hefei, China

19 papers at tracked venues · 10 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0003-3805-9326 ↗Homepage ↗

Venues

ACL ×3ICML ×3AAAI ×2ICRA ×2IROS ×2NAACL ×2NeurIPS ×2EACL ×1ECCV ×1EMNLP ×1

Frequent coauthors

Junrui Zhang
DBLP profile ↗ORCID search ↗
×2
Shuqing Luo
DBLP profile ↗ORCID search ↗
×2
Sukwon Yun
DBLP profile ↗ORCID search ↗
×2
Wenhao Yu
DBLP profile ↗ORCID search ↗
×2
Zijie Liu
DBLP profile ↗ORCID search ↗
×1
Xinyu Zhao
DBLP profile ↗ORCID search ↗
×1
Mohan Zhang
DBLP profile ↗ORCID search ↗
×1
Mufan Qiu
DBLP profile ↗ORCID search ↗
×1
Pingzhi Li
DBLP profile ↗ORCID search ↗
×1
Jiayi Xin
DBLP profile ↗ORCID search ↗
×1
Yang Ouyang
DBLP profile ↗ORCID search ↗
×1
Xuyang Zhang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations
    EACL 2026 ·
    Zijie Liu
    DBLP profile ↗ORCID search ↗
  2. Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations
    ACL 2026 ·
    Xinyu Zhao
    DBLP profile ↗ORCID search ↗
  3. Vulnerability-Aware Robust Multimodal Adversarial Training
    AAAI 2026 ·
    Junrui Zhang
    DBLP profile ↗ORCID search ↗
  4. Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
    NAACL 2025 ·
    Mohan Zhang
    DBLP profile ↗ORCID search ↗
  5. CAFE-AD: Cross-Scenario Adaptive Feature Enhancement for Trajectory Planning in Autonomous Driving
    ICRA 2025 ·
    Junrui Zhang
    DBLP profile ↗ORCID search ↗
  6. GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models
    ACL 2025 ·
    Mufan Qiu
    DBLP profile ↗ORCID search ↗
  7. Glider: Global and Local Instruction-Driven Expert Router
    EMNLP 2025 ·
    Pingzhi Li
    DBLP profile ↗ORCID search ↗
  8. I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts
    ICML 2025 ·
    Jiayi Xin
    DBLP profile ↗ORCID search ↗
  9. Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
    NAACL 2025 ·
    Yang Ouyang
    DBLP profile ↗ORCID search ↗
  10. Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing
    ICML 2025 · Jie Peng
  11. Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
    NeurIPS 2025 ·
    Shuqing Luo
    DBLP profile ↗ORCID search ↗
  12. NaviDiffuser: Tackling Multi-Objective Robot Navigation by Weight Range Guided Diffusion Model
    IROS 2025 ·
    Xuyang Zhang
    DBLP profile ↗ORCID search ↗
  13. Occult: Optimizing Collaborative Communications across Experts for Accelerated Parallel MoE Training and Inference
    ICML 2025 ·
    Shuqing Luo
    DBLP profile ↗ORCID search ↗
  14. Tuning-Free Accountable Intervention for LLM Deployment - a Metacognitive Approach
    AAAI 2025 ·
    Zhen Tan
    DBLP profile ↗ORCID search ↗
  15. UQ-Merge: Uncertainty Guided Multimodal Large Language Model Merging
    ACL 2025 ·
    Huaizhi Qu
    DBLP profile ↗ORCID search ↗
  16. Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts
    NeurIPS 2024 ·
    Sukwon Yun
    DBLP profile ↗ORCID search ↗
  17. LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance
    IROS 2024 ·
    Wenhao Yu
    DBLP profile ↗ORCID search ↗
  18. Mew: Multiplexed Immunofluorescence Image Analysis Through an Efficient Multiplex Network
    ECCV 2024 ·
    Sukwon Yun
    DBLP profile ↗ORCID search ↗
  19. PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning
    ICRA 2024 ·
    Wenhao Yu
    DBLP profile ↗ORCID search ↗