From the 1 of 5 linked papers with an AI index.
5 papers
Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA
Ming Ma, Yi Zhu, Yiran Zhong +6
The paper introduces Omni-Decision, a training‑free system that keeps a structured evidence state to guide agents in gathering and validating omni‑modal information (videos, audio,…
QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions
Jiayin Lei, Ming Ma, Yunxi Duan +2
Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult to detect with current metrics. E…
SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token
Ming Ma, Bowen Zheng, Zhongqiao Lin +1
Intermediate-layer predictions in large language models (LLMs) are informative but hard to decode accurately, especially at early layers. Existing lens-style methods typically rely…
Label Words as Local Task Vectors in In-Context Learning
Bowen Zheng, Ming Ma, Zhongqiao Lin +1
Large Language Models (LLMs) have demonstrated remarkable abilities, one of the most important being in-context learning (ICL). With ICL, LLMs can derive the underlying rule from a…
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
Bowen Zheng, Tianming Yang
Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be…