11 citations · 31 across the 26 of their papers we have counts for
9 papers · 1 filter
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Zuhao Yang, Sudong Wang, Kaichen Zhang +8
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when proc…
From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning
Hang Du, Jiayang Zhang, Guoshun Nan +8
Multi-image Interleaved Reasoning aims to improve Multi-modal Large Language Models (MLLMs) ability to jointly comprehend and reason across multiple images and their associated tex…
MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources
Sicong Leng, Jing Wang, Jiaxi Li +12
Large multimodal reasoning models have achieved rapid progress, but their advancement is constrained by two major limitations: the absence of open, large-scale, high-quality long c…
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Yuming Jiang, Siteng Huang, Shengke Xue +10
This paper presents RynnVLA-001, a vision-language-action(VLA) model built upon large-scale video generative pretraining from human demonstrations. We propose a novel two-stage pre…
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Ruifeng Yuan, Chenghao Xiao, Sicong Leng +9
Reinforcement learning has proven its effectiveness in enhancing the reasoning capabilities of large language models. Recent research efforts have progressively extended this parad…
Two Is Better Than One: Rotations Scale LoRAs
Hongcan Guo, Guoshun Nan, Yuan Yang +9
Scaling Low-Rank Adaptation (LoRA)-based Mixture-of-Experts (MoE) facilitates large language models (LLMs) to efficiently adapt to diverse tasks. However, traditional gating mechan…
Advancing Expert Specialization for Better MoE
Hongcan Guo, Haolang Lu, Guoshun Nan +8
Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly use…
Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
Jingxin Xu, Guoshun Nan, Sheng Guan +7
Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human inte…
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Boqiang Zhang, Kehan Li, Zesen Cheng +12
In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. T…