Do Students Debias Like Teachers? On the Distillability of Bias Mitigation Methods
"模型压缩" 相关文章
The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
“压缩不减智”！EPIC让多模态大模型以更少 Token 跑得更快、更稳｜NeurIPS 2025
Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression
自媒体误读了 DeepSeek-OCR：一图胜千言
C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression
Karpathy盛赞DeepSeek-OCR“淘汰”tokenizer！实测如何用Claude Code 让新模型跑在N卡上
Neuronal Group Communication for Efficient Neural representation
Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
Stratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
NeurIPS 2025 | 仅用20B tokens蒸出SOTA，小模型的「低秩时刻」到了
DeepSeek又发新模型，小而美玩出新高度
微软BitDistill将LLM压缩到1.58比特：10倍内存节省、2.65倍CPU推理加速
微软BitDistill将LLM压缩到1.58比特：10倍内存节省、2.65倍CPU推理加速
Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation
Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup
Microsoft AI Proposes BitNet Distillation (BitDistill): A Lightweight Pipeline that Delivers up to 10x Memory Savings and about 2.65x CPU Speedup
Towards Reversible Model Merging For Low-rank Weights
LLM-Oriented Token-Adaptive Knowledge Distillation
