deokjae

bdbj's activity

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

upvoted a paper 14 days ago

Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming

Paper • 2301.12187 • Published Jan 28, 2023 • 1

upvoted a paper 21 days ago

Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment

Paper • 2509.20214 • Published Sep 24 • 1

upvoted 2 papers 6 months ago

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance

Paper • 2505.07004 • Published May 11 • 7

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Paper • 2505.23416 • Published May 29 • 11