Junxian Guo
5 papers · 2025–2025 · 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
⭐
Rising Star
(5)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Keywords
model compression
(1)
attention mechanism
(1)
multimodal learning
(1)
efficient inference
(1)
neural network optimization
(1)
singular value decomposition
(1)
sparsity
(1)
diffusion model
(1)
vision-language model
(1)
computational cost
(1)
token pruning
(1)
inference efficiency
(1)
weight quantization
(1)
sparse attention
(1)
contextual sparsity
(1)
inference acceleration
(1)
kv cache
(1)
trainable parameter
(1)
4-bit quantization
(1)
block-sparse attention
(1)
Papers
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
ICLR 2025
SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
ICML 2025
SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference
ICCV 2025
SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
ICLR 2025
XAttention: Block Sparse Attention with Antidiagonal Scoring
ICML 2025