Baoyuan Qi
9 papers · 2017–2026 · 5 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (23) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🏆
Keyword Champion
(2)
🧭
Keyword Pioneer
📈
Trend Setter
🗃️
Keyword Collector
(54)
❓
The Questioner
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(9)
Machine Learning
(8)
Deep Learning
(7)
Application Areas
(5)
Optimization & Theory · Machine Learning
(5)
Optimization & Theory · Deep Learning
(5)
Natural Language Processing
(4)
Architectures
(3)
Resources & Methods
(3)
Knowledge & Reasoning
(1)
Applications
(1)
Core Methods
(1)
Learning Types
(1)
Models
(1)
Keywords
large language model
(6)
kv cache
(3)
attention mechanism
(3)
grouped-query attention
(2)
inference efficiency
(2)
speculative decoding
(2)
model compression
(2)
information entropy
(1)
memory optimization
(1)
cross-modal retrieval
(1)
memory efficiency
(1)
inference optimization
(1)
recurrent neural network
(1)
latency reduction
(1)
prompt engineering
(1)
model acceleration
(1)
kv cache quantization
(1)
autoregressive model
(1)
attention weight
(1)
knowledge graph
(1)
Papers
End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering
AAAI 2026
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
AAAI 2026
DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression
ACL 2025
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding
EMNLP 2025
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
ACL 2025
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
ACL 2025
What Limits Bidirectional Model’s Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
ICML 2025
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
EMNLP 2025
Attentive Path Combination for Knowledge Graph Completion
ACML 2017