collaborators

7 papers

cs.CV2026

Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space

Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev +4

Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset more effective than another rem…

cs.CV2026

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

Sashuai Zhou, Qiang Zhou, Junpeng Ma +9

Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most…

cs.CV2026

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

SII-GAIR, Sand. ai, : +43

We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio…

cs.CV2026

AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network

Yu Hu, Jianyang Gu, Hao Liu +4

Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptabi…

cs.CV2025

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Zhe Chen, Weiyun Wang, Yue Cao +39

We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series that builds upon InternVL 2.0, maintaining its core model architecture while introducing signif…

cs.CL2025

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Weiyun Wang, Zhe Chen, Wenhai Wang +8

Existing open-source multimodal large language models (MLLMs) generally follow a training process involving pre-training and supervised fine-tuning. However, these models suffer fr…