39 citations · 59 across the 24 of their papers we have counts for
24 papers
VLM-in-Sandbox: Visual Workspaces for Agentic Visual Reasoning
Hexiong Yang, Mingrui Chen, Jie Cao +1
Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language models to vision-language mode…
OmniEdu: Open Foundation Models for Learning and Teaching
Hao Liang, Qihan Lin, Meiyi Qiang +5
Educational foundation models must solve problems, understand curriculum structure, diagnose learner difficulties, and provide appropriate instructional support. Existing education…
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Hao Liang, Mingrui Chen, Hengyi Feng +2
Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which domains contribute to subsequen…
FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
Qijie You, Hao Liang, Mingrui Chen +4
As video becomes increasingly central to information dissemination and multimodal large language models (MLLMs) continue to advance, evaluating video retrieval has become increasin…
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
Hengyi Feng, Hao Liang, Mingrui Chen +6
Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams, whereas existing benchmarks…
Advancing Vision Transformer with Enhanced Spatial Priors
Qihang Fan, Huaibo Huang, Mingrui Chen +2
In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-Attention, lacks exp…
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22
Data-centric training has emerged as a promising direction for improving large language models (LLMs) by optimizing not only model parameters but also the selection, composition, a…
Think 360°: Evaluating the Width-centric Reasoning Capability of MLLMs Beyond Depth
Mingrui Chen, Hexiong Yang, Haogeng Liu +2
In this paper, we present a holistic multimodal benchmark that evaluates the reasoning capabilities of MLLMs with an explicit focus on reasoning width, a complementary dimension to…
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…
Step-DeepResearch Technical Report
Chen Hu, Haikuo Du, Heng Wang +64
As LLMs shift toward autonomous agents, Deep Research has emerged as a pivotal metric. However, existing academic benchmarks like BrowseComp often fail to meet real-world demands f…
SciAgent: A Unified Multi-Agent System for Generalistic Scientific Reasoning
Xuchen Li, Ruitao Wu, Xuanbo Liu +17
Recent advances in large language models have enabled AI systems to achieve expert-level performance on domain-specific scientific tasks, yet these systems remain narrow and handcr…
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
Xukai Wang, Xuanbo Liu, Mingrui Chen +16
With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existin…
Step-Audio 2 Technical Report
Boyong Wu, Chao Yan, Chen Hu +106
This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent…
Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Ailin Huang, Bingxin Li, Bruce Wang +73
Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate na…
HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling
Hexiong Yang, Mingrui Chen, Huaibo Huang +4
Inspired by the great success of Masked Language Modeling (MLM) in the natural language domain, the paradigm of self-supervised pre-training and fine-tuning has also achieved remar…
Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
Mingrui Chen, Haogeng Liu, Hao Liang +3
In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reas…
Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction
Ailin Huang, Boyong Wu, Bruce Wang +142
Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such…
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
Qihang Fan, Huaibo Huang, Mingrui Chen +1
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial co…
Vision Transformer with Sparse Scan Prior
Yuguang Zhang, Qihang Fan, Huaibo Huang
In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in sta…
RMT: Retentive Networks Meet Vision Transformers
Qihang Fan, Huaibo Huang, Mingrui Chen +2
Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatia…
OccNet: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions
Miao Fan, Mingrui Chen, Chen Hu +1
Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate p…
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images
Wenwen Yu, Chengquan Zhang, Haoyu Cao +24
Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, an…
ICDAR 2023 Competition on Reading the Seal Title
Wenwen Yu, Mingyu Liu, Mingrui Chen +5
Reading seal title text is a challenging task due to the variable shapes of seals, curved text, background noise, and overlapped text. However, this important element is commonly f…
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
Ruihang Miao, Weizhou Liu, Mingrui Chen +4
3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems. It i…