5 papers
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning
Zhiyin Yu, Bo Zhang, Qibin Hou +3
Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, the…
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Modi Jin, Yiming Zhang, Boyuan Sun +3
This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions. Previous RL-based methods have achieved breakthroughs…
Depth Anything at Any Condition
Boyuan Sun, Modi Jin, Bowen Yin +1
We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous fo…
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs
Boyuan Sun, Jiaxing Zhao, Xihan Wei +1
In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress…
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
Boyuan Sun, Jiaxing Zhao, Xiang Chen +2
In this paper, we introduce LLaVA-Octopus, a novel video multimodal large language model. LLaVA-Octopus adaptively weights features from different visual projectors based on user i…