15 citations · 40 across the 20 of their papers we have counts for
21 papers
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
STEP3-VL-10B Technical Report
Ailin Huang, Chengyuan Yao, Chunrui Han +90
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-…
Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
Bao Shu, Yan Cai, Jianjian Sun +11
Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superio…
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Yana Wei, Liang Zhao, Jianjian Sun +15
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates…
DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning
Dongxu Liu, Jiahui Zhu, Yuang Peng +6
Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have allevia…
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
En Yu, Kangheng Lin, Liang Zhao +11
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, ou…
Step1X-Edit: A Practical Framework for General Image Editing
Shiyu Liu, Yucheng Han, Peng Xing +21
In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has i…
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Haoran Wei, Chenglong Liu, Jinyue Chen +9
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper,…
DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
Yuang Peng, Yuxin Cui, Haomiao Tang +7
Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across var…
Focus Anywhere for Fine-grained Multi-page Document Understanding
Chenglong Liu, Haoran Wei, Jinyue Chen +7
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of t…
OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
Jinyue Chen, Lingyu Kong, Haoran Wei +6
Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of paramet…
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
Zekun Qi, Runpei Dong, Shaochen Zhang +5
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM) designed for embodied interaction, exploring a universal 3D object understanding with 3D point clou…
Small Language Model Meets with Reinforced Vision Vocabulary
Haoran Wei, Lingyu Kong, Jinyue Chen +6
Playing Large Vision Language Models (LVLMs) in 2023 is trendy among the AI community. However, the relatively large number of parameters (more than 7B) of popular LVLMs makes it d…
Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models
Haoran Wei, Lingyu Kong, Jinyue Chen +6
Modern Large Vision-Language Models (LVLMs) enjoy the same vision vocabulary -- CLIP, which can cover most common vision tasks. However, for some special vision task that needs den…
DreamLLM: Synergistic Multimodal Comprehension and Creation
Runpei Dong, Chunrui Han, Yuang Peng +11
This paper presents DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models (MLLMs) empowered with frequently overlooked synergy between multi…
SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers
Xijun Wang, Xiaojie Chu, Chunrui Han +1
This paper presents a module, Spatial Cross-scale Convolution (SCSC), which is verified to be effective in improving both CNNs and Transformers. Nowadays, CNNs and Transformers hav…
ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning
Liang Zhao, En Yu, Zheng Ge +8
Human-AI interactivity is a critical aspect that reflects the usability of multimodal large language models (MLLMs). However, existing end-to-end MLLMs only allow users to interact…
GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping
Zhuoling Li, Chunrui Han, Zheng Ge +5
Efficiency is quite important for 3D lane detection due to practical deployment demand. In this work, we propose a simple, fast, and end-to-end detector that still maintains high d…
The 1st-place Solution for CVPR 2023 OpenLane Topology in Autonomous Driving Challenge
Dongming Wu, Fan Jia, Jiahao Chang +7
We present the 1st-place solution of OpenLane Topology in Autonomous Driving Challenge. Considering that topology reasoning is based on centerline detection and traffic element det…
Triplet Knowledge Distillation
Xijun Wang, Dongyang Liu, Meina Kan +3
In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mi…
Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception
Chunrui Han, Jinrong Yang, Jianjian Sun +6
Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While p…