Gil Jae Song

j-song's activity

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

upvoted a paper 6 months ago

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

Paper • 2505.18231 • Published May 23, 2025 • 3

upvoted a paper 7 months ago

Gaussian Weight Sampling for Scalable, Efficient and Stable Pseudo-Quantization Training

Paper • 2505.11170 • Published May 16, 2025 • 3

upvoted 2 papers 8 months ago

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Paper • 2407.02490 • Published Jul 2, 2024 • 26

Reasoning Models Can Be Effective Without Thinking

Paper • 2504.09858 • Published Apr 14, 2025 • 12

upvoted a paper 10 months ago

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs

Paper • 2503.00979 • Published Mar 2, 2025 • 1

upvoted 2 papers 11 months ago

TokenSkip: Controllable Chain-of-Thought Compression in LLMs

Paper • 2502.12067 • Published Feb 17, 2025 • 3

Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation

Paper • 2503.22675 • Published Mar 28, 2025 • 36