11 papers
HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement
Yiyang Cai, Nan Chen, Rongchang Xie +8
Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most app…
DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation
Nan Chen, Yiyang Cai, Rongchang Xie +7
Open domain subject-driven text-to-video (S2V) generation has drawn significant interest in academia and industry. Open domain S2V mainly involves two scenarios: in-domain, which r…
SEED: Targeted Data Selection by Weighted Independent Set
Yuan Zhang, Lifeng Guo, Junwen Pan +5
Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this proble…
MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
Tao Shen, Xin Wan, Taicai Chen +10
Unified multimodal models aim to integrate understanding and generation within a single framework, yet bridging the gap between discrete semantic reasoning and high-fidelity visual…
ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
Yuan Zhang, Ming Lu, Junwen Pan +4
Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when…
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Junwen Pan, Qizhe Zhang, Rui Zhang +5
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding.…
On the Faithfulness of Visual Thinking: Measurement and Enhancement
Zujing Liu, Junwen Pan, Qi She +2
Recent large vision-language models (LVLMs) can generate vision-text multimodal chain-of-thought (MCoT) traces after reinforcement fine-tuning (RFT). However, we observe that the v…
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
Qizhe Zhang, Mengzhen Liu, Lichen Li +5
In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference c…
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
Yuan Zhang, Chun-Kai Fan, Sicheng Yu +6
Inspired by text prompts in large language models, visual prompts have been explored to enhance the perceptual capabilities of large vision-language models (LVLMs). However, perfor…
ZoomV: Temporal Zoom-in for Efficient Long Video Understanding
Yuan Zhang, Junwen Pan, Rui Zhang +5
Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context thr…
MammothModa: Multi-Modal Large Language Model
Qi She, Junwen Pan, Xin Wan +3
In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline.…