Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models
Paper
•
2506.19697
•
Published
•
44
Compression
-
-
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
Paper • 2509.23873 • Published • 67 -
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Paper • 2510.00515 • Published • 39 -
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Paper • 2509.22944 • Published • 76 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 168 -
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
Paper • 2510.19779 • Published • 58