activity
20242026
collaborators

7 papers

cs.CV2026

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking

Zirui Zheng, Takashi Isobe, Tong Shen +12

Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the…

cs.CV2026

PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation

Xiaomin Li, Qian Liang, Yinan Li +5

Reinforcement Learning like Group Relative Policy Optimization (GRPO) has significantly advanced text-to-image post-training. However, current methods often favor superficial aesth…

cs.CV2026

WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization

Qian Liang, Xiaomin Li, Ying Zhang +6

Recent text-to-image generation models have demonstrated remarkable capabilities in synthesizing highly realistic images from text inputs alone. Although existing benchmarks can ev…

cs.CV2026

Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios

Xiaomin Li, Tala Wang, Zichen Zhong +7

Daily scenarios are characterized by visual richness, requiring Multimodal Large Language Models (MLLMs) to filter noise and identify decisive visual clues for accurate reasoning.…

cs.CV2025

CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting

Lei Tian, Xiaomin Li, Liqian Ma +6

Recent advances in 3D reconstruction techniques and vision-language models have fueled significant progress in 3D semantic understanding, a capability critical to robotics, autonom…

cs.CV2025

ReNeg: Learning Negative Embedding with Reward Guidance

Xiaomin Li, Yixuan Liu, Takashi Isobe +8

In text-to-image (T2I) generation applications, negative embeddings have proven to be a simple yet effective approach for enhancing generation quality. Typically, these negative em…