Baoyuan Qi
9 papers · 2017–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (21) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(4)
π
Academic Marathon
(8)
π
Cross-Pollinator
(14)
β‘
Prolific Year
(6)
β
The Questioner
Conferences
ACL (3)
AAAI (2)
EMNLP (2)
ACML (1)
ICML (1)
Top co-authors
Keywords
large language model
(5)
kv cache
(3)
model compression
(2)
attention mechanism
(2)
speculative decoding
(2)
inference efficiency
(2)
information entropy
(1)
memory optimization
(1)
cross-modal retrieval
(1)
memory efficiency
(1)
recurrent neural network
(1)
inference optimization
(1)
prompt engineering
(1)
latency reduction
(1)
kv cache quantization
(1)
autoregressive model
(1)
knowledge graph
(1)
model acceleration
(1)
attention weight
(1)
in-context learning
(1)
Papers
Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios
AAAI 2026
End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering
AAAI 2026
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
ACL 2025
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding
ACL 2025
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding
EMNLP 2025
What Limits Bidirectional Modelβs 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
DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression
ACL 2025
Attentive Path Combination for Knowledge Graph Completion
ACML 2017