Jiwon Song

jiwonsong's activity

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

upvoted 3 papers 5 days ago

WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models

Paper • 2609.23033 • Published 8 days ago • 8

KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems

Paper • 2609.34060 • Published 6 days ago • 4

PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction

Paper • 2609.34054 • Published 6 days ago • 4

upvoted a paper about 2 months ago

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference

Paper • 2605.19218 • Published May 19 • 2

upvoted a paper 2 months ago

Loop the Loopies!

Paper • 2607.16051 • Published Jul 17 • 53

upvoted 2 papers 5 months ago

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

Paper • 2605.16839 • Published May 16 • 13

Teaching Language Models to Think in Code

Paper • 2605.07237 • Published May 11 • 32

upvoted 3 papers 7 months ago

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 198

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published Feb 27 • 18

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published Feb 26 • 154

upvoted 5 papers 8 months ago

Squeezing Large-Scale Diffusion Models for Mobile

Paper • 2307.01193 • Published Jul 3, 2023 • 2

RelayGen: Intra-Generation Model Switching for Efficient Reasoning

Paper • 2602.06454 • Published Feb 6 • 12

L4Q: Parameter Efficient Quantization-Aware Training on Large Language Models via LoRA-wise LSQ

Paper • 2402.04902 • Published Feb 7, 2024 • 5

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Paper • 2602.01053 • Published Feb 1 • 8

Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection

Paper • 2602.03216 • Published Feb 3 • 14

upvoted 4 papers 11 months ago

Retrospective Sparse Attention for Efficient Long-Context Generation

Paper • 2508.09001 • Published Aug 12, 2025 • 4

Kimi Linear: An Expressive, Efficient Attention Architecture

Paper • 2510.26692 • Published Oct 30, 2025 • 138

Exploring Conditions for Diffusion models in Robotic Control

Paper • 2510.15510 • Published Oct 17, 2025 • 40

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published Oct 21, 2025 • 116

upvoted a paper 12 months ago

Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning

Paper • 2510.19338 • Published Oct 22, 2025 • 116