Jiayi Shi
11 papers · 2023–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐝 Cross-Pollinator (8) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🌈 Renaissance Researcher (5)
🌍
Conference Polyglot
(6)
🏆
Grand Slam
🗃️
Keyword Collector
(54)
⚡
Prolific Year
(7)
💎
Century Club
(10)
❓
The Questioner
Conferences
ACL (4)
EMNLP (2)
NIPS (2)
AAAI (1)
ICLR (1)
ICML (1)
Top co-authors
Keywords
large language model
(4)
mathematical reasoning
(2)
representation learning
(2)
language model alignment
(2)
language understanding
(1)
self-supervised learning
(1)
self-attention mechanism
(1)
code generation
(1)
coreset selection
(1)
bert model
(1)
text generation
(1)
time series forecasting
(1)
instruction tuning
(1)
model alignment
(1)
sampling distribution
(1)
attention mechanism
(1)
kernel density estimation
(1)
latent representation
(1)
data selection
(1)
embedding space
(1)
Papers
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
ACL 2026
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
ACL 2025
Speculative Decoding for Multi-Sample Inference
EMNLP 2025
UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
ICLR 2025
Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?
ICML 2025
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
ACL 2025
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen
ACL 2025
InsBank: Evolving Instruction Subset for Ongoing Alignment
EMNLP 2025
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
NIPS 2024
Trafformer: Unify Time and Space in Traffic Prediction
AAAI 2023
Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation
NIPS 2023