collaborators

12 papers

cs.AI2026

Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe

Qian Zhao, Kunlong Chen, Changxin Tian +9

FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class…

cs.CL2026

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Ang Li, Ben Liu, Bin Han +215

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…

cs.CL2026

SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling

Quanen Sun, Changxin Tian, Ke Shi +5

Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream benchmark performance. Howeve…

cs.CL2026

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics

Jiapeng Wang, Changxin Tian, Kunlong Chen +5

Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscur…

cs.LG2026

Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design

Junzhuo Li, Peijie Jiang, Changxin Tian +3

This paper presents a novel extension of neural scaling laws to Mixture-of-Experts (MoE) models, focusing on the optimal allocation of compute between expert and attention sub-laye…

cs.LG2026

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging

Jiapeng Wang, Changxin Tian, Kunlong Chen +5

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive…