Cover Image

RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nie, Yunshuang, Lin, Bingqian, Niu, Minzhe, Xiang, Kun, Han, Jianhua, Huang, Guowei, Quan, Xingyue, Xu, Hang, Chen, Bokui, Liang, Xiaodan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
by: Lin, Bingqian, et al.
Published: (2025)

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning
by: Lin, Bingqian, et al.
Published: (2024)

Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
by: Wei, Ziming, et al.
Published: (2025)

Correctable Landmark Discovery via Large Models for Vision-Language Navigation
by: Lin, Bingqian, et al.
Published: (2024)

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
by: Xiang, Kun, et al.
Published: (2024)

CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation
by: Liang, Xiwen, et al.
Published: (2023)

Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?
by: Xiang, Kun, et al.
Published: (2025)

Revealing the Learning Dynamics of Long-Context Continual Pre-training
by: Liang, Yupu, et al.
Published: (2026)

A visualization method for data domain changes in CNN networks and the optimization method for selecting thresholds in classification tasks
by: Huang, Minzhe, et al.
Published: (2024)

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning
by: Li, Haoyuan, et al.
Published: (2026)

Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
by: Lin, Bingqian, et al.
Published: (2023)

PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures
by: Wu, Tianxiang, et al.
Published: (2024)

PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion
by: Lu, Guansong, et al.
Published: (2023)

MagicSeg: Open-World Segmentation Pretraining via Counterfactural Diffusion-Based Auto-Generation
by: Cai, Kaixin, et al.
Published: (2026)

VidMan: Exploiting Implicit Dynamics from Video Diffusion Model for Effective Robot Manipulation
by: Wen, Youpeng, et al.
Published: (2024)

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
by: Huang, Runhui, et al.
Published: (2025)

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
by: Zhang, Kaidong, et al.
Published: (2024)

PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
by: Ma, Liang, et al.
Published: (2025)

Leveraging LLMs and attention-mechanism for automatic annotation of historical maps
by: Yuan, Yunshuang, et al.
Published: (2025)

CoSense3D: an Agent-based Efficient Learning Framework for Collective Perception
by: Yuan, Yunshuang, et al.
Published: (2024)

MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
by: Wei, Ziming, et al.
Published: (2025)

Elysium: Exploring Object-level Perception in Videos via MLLM
by: Wang, Han, et al.
Published: (2024)

Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
by: Nie, Ming, et al.
Published: (2026)

StreamLTS: Query-based Temporal-Spatial LiDAR Fusion for Cooperative Object Detection
by: Yuan, Yunshuang, et al.
Published: (2024)

HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance
by: Fang, Guian, et al.
Published: (2024)

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
by: Yao, Lewei, et al.
Published: (2024)

EasyControl: Transfer ControlNet to Video Diffusion for Controllable Generation and Interpolation
by: Wang, Cong, et al.
Published: (2024)

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation
by: Zhang, Tao, et al.
Published: (2025)

TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation
by: Wang, Peng, et al.
Published: (2024)

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons
by: Kojima, Takeshi, et al.
Published: (2024)

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models
by: Zhang, Jiaxin, et al.
Published: (2026)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
by: Pi, Renjie, et al.
Published: (2024)

Psychological Counseling Ability of Large Language Models
by: Peng, Fangyu, et al.
Published: (2025)

Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting
by: Zhao, Haoyu, et al.
Published: (2024)

Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation
by: Chen, Jiaqi, et al.
Published: (2024)

Development of Cognitive Intelligence in Pre-trained Language Models
by: Shah, Raj Sanjay, et al.
Published: (2024)

OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM
by: Wang, Jinhong, et al.
Published: (2025)

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning
by: Zhou, Yuhao, et al.
Published: (2025)

RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment
by: Jiang, Zutao, et al.
Published: (2023)

Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer
by: Yang, Yu, et al.
Published: (2024)