Wei Song

Channel-wise Vector Quantization

arXiv 2026

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

arXiv 2026

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

arXiv 2026

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

arXiv 2026

DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

arXiv 2026

Kimi-Audio Technical Report

arXiv 2025

Kimi-VL Technical Report

arXiv 2025

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

arXiv 2025

EfficientLLM: Efficiency in Large Language Models

arXiv 2025

Baichuan-Omni-1.5 Technical Report

arXiv 2025

DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies

arXiv 2025

Baichuan-Omni Technical Report

arXiv 2024

M3GIA: A Cognition Inspired Multilingual and Multimodal General Intelligence Ability Benchmark

arXiv 2024

Jiaqi Wang

Kaicheng Yu

Jianhua Xu

Tianhang Wang

Yadong Li

Dianyi Wang

Haoze Sun

Siyuan Wang

WeiPeng Chen

Zenan Zhou