Yaohua Tang
4 papers · 2024–2026 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Silver
๐บ๏ธ
Taxonomy Completionist
(13)
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
large language model
(4)
key-value cache
(2)
inference acceleration
(2)
model serving
(1)
model alignment
(1)
inference optimization
(1)
retrieval-augmented generation
(1)
token prediction
(1)
full-duplex dialogue
(1)
real-time inference
(1)
voice interaction
(1)
interruption handling
(1)
kv cache
(1)
full-duplex communication
(1)
latency optimization
(1)
dialogue system
(1)
text chunking
(1)
group relative policy optimization
(1)
prefill computation
(1)
full-duplex speech
(1)
Papers
URPO: A Unified Reward & Policy Optimization Framework for Large Language Models
AAAI 2026
Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference
ACML 2025
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
EMNLP 2025
A Full-duplex Speech Dialogue Scheme Based On Large Language Model
NeurIPS 2024