11 papers
ISO: An RLVR-Native Optimization Stack
Hanqing Zhu, Wenyan Cong, Zhizhou Sha +8
Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback i…
MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
Changsheng Zhao, Ernie Chang, Zechun Liu +8
The paradigm shift in large language models (LLMs) from instinctive responses to chain-of-thought (CoT) reasoning has fueled two prevailing assumptions: (1) reasoning capabilities…
STEM: Scaling Transformers with Embedding Modules
Ranajoy Sadhukhan, Sheng Cao, Harry Dong +5
Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication ove…
The Path Not Taken: RLVR Provably Learns Off the Principals
Hanqing Zhu, Zhenyu Zhang, Hanxian Huang +11
Reinforcement Learning with Verifiable Rewards (RLVR) reliably improves the reasoning performance of large language models, yet it appears to modify only a small fraction of parame…
ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
Zechun Liu, Changsheng Zhao, Hanxian Huang +13
The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, o…
Param for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost
Sheng Cao, Mingrui Wu, Karthik Prasad +2
The post-training phase of large language models is essential for enhancing capabilities such as instruction-following, reasoning, and alignment with human preferences. However, it…