Yuxiang Huang
5 papers · 2024–2026 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(13)
👥
Mega-Team · Squad
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Machine Learning
(3)
Application Areas
(3)
Optimization & Theory · Deep Learning
(3)
Natural Language Processing
(2)
Optimization & Theory · Machine Learning
(2)
Computer Science
(1)
Computer Vision
(1)
Generation
(1)
Processing
(1)
Resources & Methods
(1)
Systems
(1)
Techniques
(1)
Keywords
inference acceleration
(3)
approximate attention
(2)
draft verification
(2)
large language model
(2)
sequence parallelism
(2)
vocabulary compression
(1)
training efficiency
(1)
language model
(1)
large multimodal model
(1)
multimodal large language model
(1)
flash attention
(1)
speculative decoding
(1)
draft model
(1)
long video understanding
(1)
speculative sampling
(1)
key-value cache
(1)
load balancing
(1)
parallel decoding
(1)
long-context inference
(1)
text recognition
(1)
Papers
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
ACL 2026
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
CVPR 2026
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs
ACL 2025
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
ACL 2025
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
EMNLP 2024