Suchergebnisse - Huang, Linjiang

FR-TTS: Test-Time Scaling for NTP-based Image Generation with Effective Filling-based Reward Signal von Xu, Hang, Huang, Linjiang, Zhao, Feng

Volltext

Highly Efficient Test-Time Scaling for T2I Diffusion Models with Text Embedding Perturbation von Xu, Hang, Huang, Linjiang, Zhao, Feng

Volltext

GaussianPainter: Painting Point Cloud into 3D Gaussians with Normal Guidance von Zhou, Jingqiu, Fan, Lue, Chen, Xuesong, Huang, Linjiang, Liu, Si, Li, Hongsheng

Volltext

SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving von Chen, Xuesong, Huang, Linjiang, Ma, Tao, Fang, Rongyao, Shi, Shaoshuai, Li, Hongsheng

Volltext

FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment von Xu, Hang, Huang, Jie, Huang, Linjiang, Li, Dong, Liu, Yidi, Zhao, Feng

Volltext

"Hi AirStar, Guide Me to the Badminton Court." von Wang, Ziqin, Chen, Jinyu, Zheng, Xiangyi, Liao, Qinan, Huang, Linjiang, Liu, Si

Volltext

AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert von Gao, Yuting, Lan, Wang, Zhao, Hengyuan, Huang, Linjiang, Liu, Si, Guo, Qingpei

Volltext

FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis von Huang, Linjiang, Fang, Rongyao, Zhang, Aiping, Song, Guanglu, Liu, Si, Liu, Yu, Li, Hongsheng

Volltext

FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering von Zhou, Jingqiu, Fan, Lue, Huang, Linjiang, Shi, Xiaoyu, Liu, Si, Zhang, Zhaoxiang, Li, Hongsheng

Volltext

InfoScale: Unleashing Training-free Variable-scaled Image Generation via Effective Utilization of Information von Zhang, Guohui, Tan, Jiangtong, Huang, Linjiang, Yuan, Zhonghang, Yao, Mingde, Huang, Jie, Zhao, Feng

Volltext

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning von Duan, Chengqi, Fang, Rongyao, Wang, Yuqing, Wang, Kun, Huang, Linjiang, Zeng, Xingyu, Li, Hongsheng, Liu, Xihui

Volltext

SkeNa: Learning to Navigate Unseen Environments Based on Abstract Hand-Drawn Maps von Xu, Haojun, Xiang, Jiaqi, Wei, Wu, Chen, Jinyu, Zhong, Linqing, Huang, Linjiang, Yang, Hongyu, Liu, Si

Volltext

AeroDuo: Aerial Duo for UAV-based Vision and Language Navigation von Wu, Ruipu, Zhang, Yige, Chen, Jinyu, Huang, Linjiang, Zhang, Shifeng, Zhou, Xu, Wang, Liang, Liu, Si

Volltext

FreeEdit: Mask-free Reference-based Image Editing with Multi-modal Instruction von He, Runze, Ma, Kai, Huang, Linjiang, Huang, Shaofei, Gao, Jialin, Wei, Xiaoming, Dai, Jiao, Han, Jizhong, Liu, Si

Volltext

VaccineRAG: Boosting Multimodal Large Language Models' Immunity to Harmful RAG Samples von Sun, Qixin, Wang, Ziqin, Zhao, Hengyuan, Li, Yilin, Song, Kaiyou, Huang, Linjiang, Hu, Xiaolin, Guo, Qingpei, Liu, Si

Volltext

Group Critical-token Policy Optimization for Autoregressive Image Generation von Zhang, Guohui, Yu, Hu, Ma, Xiaoxiao, Zhang, JingHao, Pan, Yaning, Yao, Mingde, Xiao, Jie, Huang, Linjiang, Zhao, Feng

Volltext

FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark von Fang, Rongyao, Yu, Aldrich, Duan, Chengqi, Huang, Linjiang, Bai, Shuai, Cai, Yuxuan, Wang, Kun, Liu, Si, Liu, Xihui, Li, Hongsheng

Volltext

VCBench: A Streaming Counting Benchmark for Spatial-Temporal State Maintenance in Long Videos von Liu, Pengyiang, Shi, Zhongyue, Hao, Hongye, Fu, Qi, Bi, Xueting, Zhang, Siwei, Hu, Xiaoyang, Wang, Zitian, Huang, Linjiang, Liu, Si

Volltext

GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing von Fang, Rongyao, Duan, Chengqi, Wang, Kun, Huang, Linjiang, Li, Hao, Yan, Shilin, Tian, Hao, Zeng, Xingyu, Zhao, Rui, Dai, Jifeng, Liu, Xihui, Li, Hongsheng

Volltext

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning von Shi, Weikang, Yu, Aldrich, Fang, Rongyao, Ren, Houxing, Wang, Ke, Zhou, Aojun, Tian, Changyao, Fu, Xinyu, Hu, Yuxuan, Lu, Zimu, Huang, Linjiang, Liu, Si, Liu, Rui, Li, Hongsheng

Volltext