Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper β’ 2601.22813 β’ Published 11 days ago β’ 55
MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models Paper β’ 2601.11969 β’ Published 24 days ago β’ 26
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning Paper β’ 2502.01100 β’ Published Feb 3, 2025 β’ 21
Alchemist: Turning Public Text-to-Image Data into Generative Gold Paper β’ 2505.19297 β’ Published May 25, 2025 β’ 84
Quartet: Native FP4 Training Can Be Optimal for Large Language Models Paper β’ 2505.14669 β’ Published May 20, 2025 β’ 78
Learning Adaptive Parallel Reasoning with Language Models Paper β’ 2504.15466 β’ Published Apr 21, 2025 β’ 44
PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters Paper β’ 2504.08791 β’ Published Apr 7, 2025 β’ 139
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention Paper β’ 2504.06261 β’ Published Apr 8, 2025 β’ 110 β’ 6
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though Paper β’ 2501.04682 β’ Published Jan 8, 2025 β’ 99
An Empirical Study of GPT-4o Image Generation Capabilities Paper β’ 2504.05979 β’ Published Apr 8, 2025 β’ 64