activity
20242026
collaborators

14 papers

cs.AI2026

ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control

Zhentao Tang, Yuqi Cui, Shixiong Kai +10

Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle…

cs.CL2026

Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning

Zeyu Xing, Xing Li, Hui-Ling Zhen +2

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the…

cs.CL2026

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats

Manyi Zhang, Ji-Fu Li, Zhongao Sun +4

Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms bei…

cs.CL2026

Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence

Shengyin Sun, Yiming Li, Renxi Liu +5

Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we r…

cs.LG2025

MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling

Yu Zhang, Hui-Ling Zhen, Mingxuan Yuan +1

Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate traini…

cs.CL2025

Behavioral Fingerprinting of Large Language Models

Zehua Pei, Hui-Ling Zhen, Ying Zhang +5

Current benchmarks for Large Language Models (LLMs) primarily focus on performance metrics, often failing to capture the nuanced behavioral characteristics that differentiate them.…