Junjie Hu
- Papers
- 15
Cite
Notes
Only stored in your browser.
Authored papers
15R-KV: Redundancy-aware KV Cache Compression for Training-Free Reasoning Models Acceleration
arXiv 2025
Search is All You Need for Few-shot Anomaly Detection
arXiv 2025
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
arXiv 2025
MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
arXiv 2025
MMGR: Multi-Modal Generative Reasoning
arXiv 2025
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
arXiv 2024
How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes
arXiv 2024
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
arXiv 2024
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
arXiv 2024
Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection
arXiv 2023
Automatic Personalized Impression Generation for PET Reports Using Large Language Models
arXiv 2023
Local Byte Fusion for Neural Machine Translation
arXiv 2022
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
EMNLP 2021 11
PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation
arXiv 2021
GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems
ACL 2022 5
Affiliations
Frequent co-authors
10from 15 papers