Xiaozhe Ren
12 papers · 2021–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (5) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🧭 Keyword Pioneer 🏃 Academic Marathon (5)
🌍
Conference Polyglot
(6)
🐝
Cross-Pollinator
(5)
🏃
Academic Marathon
(5)
🧬
Topic Evolution
💎
Century Club
(11)
🔥
Unstoppable
(5)
Conferences
ICML (3)
AAAI (2)
ACL (2)
EMNLP (2)
NIPS (2)
ECCV (1)
Top co-authors
Keywords
attention mechanism
(4)
transformer architecture
(3)
neural network optimization
(2)
self-attention mechanism
(2)
neural architecture search
(2)
length extrapolation
(2)
model architecture
(1)
communication efficiency
(1)
language model training
(1)
distributed training
(1)
positional encoding
(1)
weight sharing
(1)
feature map
(1)
adaptive optimization
(1)
gradient estimation
(1)
gradient vanishing
(1)
edge computing
(1)
adaptive gradient method
(1)
memory efficiency
(1)
knowledge distillation
(1)
Papers
BitDP: Ultra-low-bit Communication for Data Parallelism in LLM Training
AAAI 2026
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
ICML 2025
Self-Adjust Softmax
EMNLP 2025
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
ACL 2025
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
NIPS 2024
PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
ECCV 2024
Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
NIPS 2023
CAME: Confidence-guided Adaptive Memory Efficient Optimization
ACL 2023
A Study on Transformer Configuration and Training Objective
ICML 2023
AutoBERT-Zero: Evolving BERT Backbone from Scratch
AAAI 2022
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation
EMNLP 2021
SparseBERT: Rethinking the Importance Analysis in Self-attention
ICML 2021