16 papers
D-Loop: Looped Diffusion Drafting for Speculative Decoding
Kecheng Chen, Yuyang He, Cheng Gong +8
Block diffusion accelerates speculative decoding by drafting multiple tokens in one forward pass. However, each position predicts a marginal distribution without observing earlier…
SAP: State-Guided Data Synthesis with Argument Provenance for Multi-Turn Tool Use
Zichen Tian, Jinpeng Chen, Cheng Gong +2
High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-level dependencies that are cr…
From Dense Prediction to Visual Editing: Structured Supervision for Unified Image and Video Creation
Zhefan Rao, Bin Zou, Xuanhua He +5
Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from visual context. However, semantic-…
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Guoxuan Chen, Chufeng Xiao, Haoran Yang +30
We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers compet…
Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
Yaofang Liu, Kangning Cui, Meng Chu +7
Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to seria…
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +9
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generati…
SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
Liangyang Ouyang, Ruicong Liu, Caixin Kang +2
Video generation has advanced rapidly, producing photorealistic videos from text or image prompts. Meanwhile, film production and social robotics increasingly demand multi-person v…
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
Rui Liu, Dian Yu, Zhenwen Liang +6
Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over…
Reinforcing Multimodal Reasoning Against Visual Degradation
Rui Liu, Dian Yu, Haolin Liu +6
Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-wor…
AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models
Jintao Lin, Bowen Dong, Weikang Shi +4
The capability of Unified Multimodal Models (UMMs) to apply world knowledge across diverse tasks remains a critical, unresolved challenge. Existing benchmarks fall short, offering…
MMMamba: A Versatile Cross-Modal In Context Fusion Framework for Pan-Sharpening and Zero-Shot Image Enhancement
Yingying Wang, Xuanhua He, Chen Wu +5
Pan-sharpening aims to generate high-resolution multispectral (HRMS) images by integrating a high-resolution panchromatic (PAN) image with its corresponding low-resolution multispe…
VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis
Meng Chu, Senqiao Yang, Haoxuan Che +8
Generative models can now produce photorealistic imagery, yet they still struggle with the long, multi-goal prompts that professional designers issue. To expose this gap and better…
Efficient Reasoning via Reward Model
Yuhao Wang, Xiaopeng Li, Cheng Gong +4
Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reason…
GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
Ziru Liu, Cheng Gong, Xinyu Fu +7
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularl…
Pusa V1.0: Unlocking Temporal Control in Pretrained Video Diffusion Models via Vectorized Timestep Adaptation
Yaofang Liu, Yumeng Ren, Aitor Artola +9
The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchronization of frame evolution imposed…
Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
Hui Liu, Bin Zou, Suiyun Zhang +3
Instruction-guided image editing enables users to specify modifications using natural language, offering more flexibility and control. Among existing frameworks, Diffusion Transfor…