Image de couverture de livre

Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Yi, Ni, Bolin, Chen, Xin-Sheng, Zhang, Heng-Rui, Rao, Yongming, Peng, Houwen, Lu, Qinglin, Hu, Han, Guo, Meng-Hao, Hu, Shi-Min
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
par: Yang, Qi, et autres
Publié: (2025)

Xwin-LM: Strong and Scalable Alignment Practice for LLMs
par: Ni, Bolin, et autres
Publié: (2024)

SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs
par: Wang, Jiahui, et autres
Publié: (2025)

Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments \& Analysis]
par: Jia, Huaiyu, et autres
Publié: (2026)

ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws
par: Li, Ruihang, et autres
Publié: (2024)

R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation
par: Guo, Meng-Hao, et autres
Publié: (2025)

FullStack Bench: Evaluating LLMs as Full Stack Coders
par: Bytedance-Seed-Foundation-Code-Team, et autres
Publié: (2024)

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding
par: Hu, Rui, et autres
Publié: (2025)

Enhancing Visual Continual Learning with Language-Guided Supervision
par: Ni, Bolin, et autres
Publié: (2024)

Maxwell Demon and Einstein-Podolsky-Rosen Steering
par: Hu, Meng-Jun, et autres
Publié: (2021)

Unlocking Gravity and Gravitational Waves with Radio Pulsars: Advances and Challenges
par: Hu, Huanchen
Publié: (2025)

BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries
par: Li, Tianle, et autres
Publié: (2025)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
par: Wang, Wei, et autres
Publié: (2026)

HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations
par: Hu, Yujia, et autres
Publié: (2026)

CAVALRY-V: A Large-Scale Generator Framework for Adversarial Attacks on Video MLLMs
par: Zhang, Jiaming, et autres
Publié: (2025)

Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learning
par: Wu, Xinyi, et autres
Publié: (2025)

Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
par: Chen, Lin, et autres
Publié: (2026)

Unlocking the Forgery Detection Potential of Vanilla MLLMs: A Novel Training-Free Pipeline
par: Zuo, Rui, et autres
Publié: (2025)

LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
par: Zhang, Danqing, et autres
Publié: (2025)

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
par: Zeng, Xiangyu, et autres
Publié: (2024)

Channel Knowledge Map Construction: Recent Advances and Open Challenges
par: Ren, Zixiang, et autres
Publié: (2025)

Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs
par: Feng, Yigui, et autres
Publié: (2026)

String Scattering and Evolution of Ryu-Takayanagi Surface
par: Jiang, Xin, et autres
Publié: (2024)

Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localization
par: Chen, Yuqi, et autres
Publié: (2026)

VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
par: Yuan, Yuqian, et autres
Publié: (2024)

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
par: Li, Yunheng, et autres
Publié: (2026)

UDTIRI: An Online Open-Source Intelligent Road Inspection Benchmark Suite
par: Guo, Sicen, et autres
Publié: (2023)

Full‐Stack Architectures for Intelligent Brain‐Computer Interfaces
par: Hee Kyu Lee, et autres
Publié: (2026)

Full‐Color and High‐Resolution Femtosecond Laser Patterning of Perovskite Quantum Dots in Polyacrylonitrile Matrix
par: Jinming Hu, et autres
Publié: (2024)

When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
par: Cao, Fanpu, et autres
Publié: (2026)

When Eyes and Ears Disagree: Can MLLMs Discern Audio-Visual Confusion?
par: Ye, Qilang, et autres
Publié: (2025)

FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs
par: Hao, Jing, et autres
Publié: (2024)

OpenView: Empowering MLLMs with Out-of-view VQA
par: Chen, Qixiang, et autres
Publié: (2025)

Orbital Longitudinal Magnetoelectricity in Quasi-2D Parity-Violating Antiferromagnets: Interplay of Berry Phase and Stacking Order
par: Hu, Jin-Xin
Publié: (2025)

FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
par: Sun, Haoyu, et autres
Publié: (2025)

Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
par: Zhang, Huanyu, et autres
Publié: (2025)

Taiyi: A high-performance CKKS accelerator for Practical Fully Homomorphic Encryption
par: Fan, Shengyu, et autres
Publié: (2024)

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
par: Zhao, Min, et autres
Publié: (2026)

Strong non-vanishing of cohomologies and strong non-freeness of adjoint line bundles on $n$-Raynaud surfaces
par: Zhang, Yongming
Publié: (2022)

Exterior power of stable vector bundle destabilized by Frobenius pull-back
par: Zhang, Yongming
Publié: (2025)