collaborators

9 papers

cs.LG2026

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization

Li Lin, Xiaojun Wan

NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales. However, existing NVFP4 scale initi…

cs.LG2026

NeUQI: Near-Optimal Uniform Quantization Parameter Initialization for Low-Bit LLMs

Li Lin, Xinyu Hu, Xiaojun Wan

Large language models (LLMs) achieve impressive performance across domains but face significant challenges when deployed on consumer-grade GPUs or personal devices such as laptops,…

cs.CL2026

MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text

Junzhe Zhang, Huixuan Zhang, Xinyu Hu +4

Evaluation is important for multimodal generation tasks, while traditional multimodal evaluation metrics suffer from several limitations. With the rapid progress of MLLMs, there is…

cs.CL2026

LEDOM: Reverse Language Model

Xunjian Yin, Sitao Cheng, Yuxi Xie +6

Autoregressive language models are trained exclusively left-to-right. We explore the complementary factorization, training right-to-left at scale, and ask what reasoning patterns e…

cs.CL2026

CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria

Xinyu Hu, Yancheng He, Weixun Wang +6

Automatic evaluation is crucial yet challenging for open-ended natural language generation, especially when rule-based metrics are infeasible. Compared with traditional methods, th…

cs.LG2026

LoaQ: Layer-wise Output Approximation Quantization

Li Lin, Xiaojun Wan

A natural and intuitive idea in model quantization is to approximate each component's quantized output to match its original. Motivated by this idea, most layer-wise post-training…