Publications (10)
ViCO: A Training Strategy towards Semantic Aware Dynamic High-Resolution
Long Cui, Weiyun Wang, Jie Shao +6
Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Vis…
Collaborative Attention Network for Person Re-identification
Wenpeng Li, Yongli Sun, Jinjun Wang +3
Jointly utilizing global and local features to improve model accuracy is becoming a popular approach for the person re-identification (ReID) problem, because previous works using g…
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
Weiyun Wang, Zhangwei Gao, Lixin Gu +72
We introduce InternVL 3.5, a new family of open-source multimodal models that significantly advances versatility, reasoning capability, and inference efficiency along the InternVL…
Intern-S1: A Scientific Multimodal Foundation Model
Lei Bai, Zhongrui Cai, Yuhang Cao +173
In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that…
General relativistic stochastic thermodynamics
Tao Wang, Yifan Cai, Long Cui +1
Based on the recent work [1,2], we formulate the first law and the second law of stochastic thermodynamics in the framework of general relativity. These laws are established for a…
A general relativistic kinetic theory approach to linear transport in generic hydrodynamic frame
Long Cui, Xin Hao, Liu Zhao
In this study, we investigate the linear transport of neutral system within the framework of relativistic kinetic theory. Under the relaxation time approximation, we obtain an iter…
Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts
Jiahao Ying, Yixin Cao, Kai Xiong +3
This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will not only help to understand LLMs'…
HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models
Li Pang, Xiangyu Rui, Long Cui +3
Hyperspectral image (HSI) restoration aims at recovering clean images from degraded observations and plays a vital role in downstream tasks. Existing model-based methods have limit…
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Inclusion AI, Tiwei Bie, Haoxing Chen +15
We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its…
Linear response in a charged gas in curved spacetime and covariant heat equation
Long Cui, Xin Hao, Liu Zhao
We consider the linear response of a near-equilibrium charged relativistic gas in the presence of electromagnetic and gravitational field in a generic stationary spacetime up to th…