David Grangier
~David_Grangier1
9
论文总数
4.5
年均投稿
平均评分
接收情况7/9
会议分布
ICLR
5
ICML
2
NeurIPS
2
发表论文 (9 篇)
20258 篇
4
Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
ICLR 2025Poster
3
Need a Small Specialized Language Model? Plan Early!
ICLR 2025Rejected
5
Dynamic Gradient Alignment for Online Data Mixing
ICLR 2025Rejected
4
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
ICML 2025Poster
3
No Need to Talk: Asynchronous Mixture of Language Models
ICLR 2025Spotlight
5
The AdEMAMix Optimizer: Better, Faster, Older
ICLR 2025Poster
5
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging
ICML 2025Poster
4
Scaling Laws for Optimal Data Mixtures
NeurIPS 2025Poster