SOTAVerified

LAMBADA

Papers

Showing 110 of 30 papers

TitleStatusHype
Matryoshka Model Learning for Improved Elastic Student Models0
AdaGC: Improving Training Stability for Large Language Model Pretraining0
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LMCode1
Beyond Autoregression: Fast LLMs via Self-Distillation Through TimeCode1
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at ScaleCode2
SymBa: Symbolic Backward Chaining for Structured Natural Language Reasoning0
PIXAR: Auto-Regressive Language Modeling in Pixel Space0
Concise and Organized Perception Facilitates Reasoning in Large Language Models0
Headless Language Models: Learning without Predicting with Contrastive Weight Tying0
Stay on topic with Classifier-Free Guidance0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.