activity
20242026
collaborators

11 papers

cs.LG2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.CL2025

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…