model scaling

Scaling, Simplification, and Adaptation: Lessons from Pretraining on Machine-Translated Text EMNLP 2025 Scaling Trends for Data Poisoning in LLMs AAAI 2025 Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale ICLR 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Surprising Effectiveness of pretraining Ternary Language Model at Scale ICLR 2025 Temporal Scaling Law for Large Language Models EMNLP 2025 Towards Precise Scaling Laws for Video Diffusion Transformers CVPR 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 Towards the Roots of the Negation Problem: A Multilingual NLI Dataset and Model Scaling Analysis EMNLP 2025 Training Bilingual LMs with Data Constraints in the Targeted Language ACL 2025 Training compute-optimal transformer encoder models EMNLP 2025 Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language Models ACL 2025 U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models ICLR 2025 YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model ACL 2025 Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild NeurIPS 2024 An Emulator for Fine-tuning Large Language Models using Small Language Models ICLR 2024 A Recipe for Scaling up Text-to-Video Generation with Text-free Videos CVPR 2024 Are Large Language Model Temporally Grounded? NAACL 2024 CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts NeurIPS 2024 DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models ACL 2024 Differentiable Model Scaling using Differentiable Topk ICML 2024 From Sparse to Soft Mixtures of Experts ICLR 2024 I am a Strange Dataset: Metalinguistic Tests for Language Models ACL 2024 LLM Circuit Analyses Are Consistent Across Training and Scale NeurIPS 2024 MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts NeurIPS 2024