Minjia Zhang

Venues

Frequent coauthors

Papers

1. A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Task
   ACL 2026 ·

   Shuzheng Si

   DBLP profile ↗ORCID search ↗
2. FaithLens: Detecting and Explaining Faithfulness Hallucination
   ACL 2026 ·

   Shuzheng Si

   DBLP profile ↗ORCID search ↗
3. Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling
   ACL 2026 ·

   Zhixiang Liang

   DBLP profile ↗ORCID search ↗
4. MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control
   ACL 2026 ·

   Haozhe Zhao

   DBLP profile ↗ORCID search ↗
5. Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning
   AAAI 2026 ·

   Shuzheng Si

   DBLP profile ↗ORCID search ↗
6. VecFlow-Chamfer: A GPU-based Data Management System for High-Performance Multi-Vector Search on Superchips
   SIGMOD 2026 ·

   Chenghao Mo

   DBLP profile ↗ORCID search ↗
7. Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning
   EMNLP 2025 ·

   Mingyuan Wu

   DBLP profile ↗ORCID search ↗
8. FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting
   ACM MM 2025 ·

   Boyuan Tian

   DBLP profile ↗ORCID search ↗
9. InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
   ICCV 2025 ·

   Yiming Gong

   DBLP profile ↗ORCID search ↗
10. Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance
    EMNLP 2025 ·

    Haozhe Zhao

    DBLP profile ↗ORCID search ↗
11. MedCite: Can Language Models Generate Verifiable Text for Medicine?
    ACL 2025 ·

    Xiao Wang

    DBLP profile ↗ORCID search ↗
12. MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators
    MLSys 2025 ·

    Beichen Huang

    DBLP profile ↗ORCID search ↗
13. MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference
    ACL 2025 ·

    Akshat Sharma

    DBLP profile ↗ORCID search ↗
14. VecFlow: A High-Performance Vector Data Management System for Filtered-Search on GPUs
    SIGMOD 2025 ·

    Jingyi Xi

    DBLP profile ↗ORCID search ↗
15. DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing
    AAAI 2024 ·

    Conglong Li

    DBLP profile ↗ORCID search ↗
16. Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
    ICLR 2024 ·

    Suyu Ge

    DBLP profile ↗ORCID search ↗
17. UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
    NeurIPS 2024 ·

    Haozhe Zhao

    DBLP profile ↗ORCID search ↗
18. Vexless: A Serverless Vector Data Management System Using Cloud Functions
    SIGMOD 2024 ·

    Yongye Su

    DBLP profile ↗ORCID search ↗