collaborators

11 papers

cs.LG2026

Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models

Shuai Wang, Zhenhua Liu, Jiaheng Wei +3

We present Athena-PRM, a multimodal process reward model (PRM) designed to evaluate the reward score for each step in solving complex reasoning problems. Developing high-performanc…

cs.CL2026

Beyond the Target: From Imitation to Collaboration in Speculative Decoding

Jinze Li, Yixing Xu, Guanchen Li +7

Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are verified in parallel by a large…

cs.LG2026

Theory-optimal Quantization Based on Flatness

Xiusheng Huang, Zhe Li, Xuanwu Yin +5

Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). The primary challenges in LLMs…

cs.CL2026

Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match

Jinze Li, Yixing Xu, Guanchen Li +6

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SP…

cs.LG2026

Learnable Permutation for Structured Sparsity on Transformer Models

Zekai Li, Ji Liu, Guanchen Li +5

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language mod…

cs.CL2026

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates

Yixing Xu, Chao Li, Xuanwu Yin +4

Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific dow…