Li Lyna Zhang
11 papers · 2023–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (28) π£ Hot Topic Early Bird π€ Dynamic Duo (11)
ποΈ
Keyword Collector
(55)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(7)
Application Areas
(7)
Core AI
(6)
Deep Learning
(5)
Natural Language Processing
(4)
Optimization & Theory Β· Machine Learning
(3)
Learning Paradigms
(2)
Learning Types
(2)
Optimization & Theory Β· Deep Learning
(2)
Resources & Methods
(2)
Techniques
(2)
Computer Vision
(1)
Speech & Audio
(1)
Applications
(1)
Keywords
model compression
(4)
neural architecture search
(3)
fine tuning
(2)
inference optimization
(2)
context window
(2)
monte carlo tree search
(2)
latency optimization
(2)
embedding
(1)
transfer learning
(1)
post-training quantization
(1)
efficient computing
(1)
vector quantization
(1)
prompt engineering
(1)
second-order optimization
(1)
few-shot learning
(1)
weight quantization
(1)
knowledge distillation
(1)
variational autoencoder
(1)
hardware acceleration
(1)
mathematical reasoning
(1)
Papers
LongRoPE2: Near-Lossless LLM Context Window Scaling
ICML 2025
Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver
ICLR 2025
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
ICML 2025
Fewer is More: Boosting Math Reasoning with Reinforced Context Pruning
EMNLP 2024
LitePred: Transferable and Scalable Latency Prediction for Hardware-Aware Neural Architecture Search
NSDI 2024
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
ICML 2024
VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models
EMNLP 2024
Accurate and Structured Pruning for Efficient Automatic Speech Recognition
Interspeech 2023
ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices
ICCV 2023
On Modular Learning of Distributed Systems for Predicting End-to-End Latency
NSDI 2023
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 Inference
ICCV 2023