Wonjun Kang

wjkang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 4 months ago

XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization

Paper • 2508.10395 • Published Aug 14 • 42

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation

Paper • 2508.05399 • Published Aug 7 • 17

authored 5 papers 5 months ago

VersaPRM: Multi-Domain Process Reward Model via Synthetic Reasoning Data

Paper • 2502.06737 • Published Feb 10

Draft-based Approximate Inference for LLMs

Paper • 2506.08373 • Published Jun 10 • 4

Counting Guidance for High Fidelity Text-to-Image Synthesis

Paper • 2306.17567 • Published Jun 30, 2023

TabFlex: Scaling Tabular Learning to Millions with Linear Attention

Paper • 2506.05584 • Published Jun 5

Parameter-Efficient Fine-Tuning of State Space Models

Paper • 2410.09016 • Published Oct 11, 2024

authored 3 papers 10 months ago

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models

Paper • 2503.03499 • Published Mar 5 • 5

Can MLLMs Perform Text-to-Image In-Context Learning?

Paper • 2402.01293 • Published Feb 2, 2024

Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing

Paper • 2403.09468 • Published Mar 14, 2024