7 papers · 1 filter
Xiaomi MiMo-VL-Miloco Technical Report
Jiaze Li, Jingyang Chen, Yuxun Qu +9
We open-source MiMo-VL-Miloco-7B and its quantized variant MiMo-VL-Miloco-7B-GGUF, a pair of home-centric vision-language models that achieve strong performance on both home-scenar…
TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
Boshen Xu, Zihan Xiao, Jiaze Li +4
We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architectur…
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
Jiaze Li, Hao Yin, Wenhui Tan +7
Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understandin…
Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
Linghao Zhu, Yiran Guan, Dingkang Liang +6
Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM). However, current…
Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
Shaojie Zhang, Jiahui Yang, Jianqin Yin +2
Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video compreh…
Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
Wenhui Tan, Jiaze Li, Jianzhong Ju +3
Large Language Models (LLMs) achieve superior performance through Chain-of-Thought (CoT) reasoning, but these token-level reasoning chains are computationally expensive and ineffic…
Direction-Aware Diagonal Autoregressive Image Generation
Yijia Xu, Jianzhong Ju, Jian Luan +1
The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation.…