Cover Image

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Ziang, Li, Zhilin, He, Yinan, Wang, Chenting, Li, Kunchang, Li, Xinhao, Zeng, Xiangyu, Wang, Zilei, Wang, Yali, Qiao, Yu, Wang, Limin, Wang, Yi
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
by: Zeng, Xiangyu, et al.
Published: (2024)

VideoMamba: State Space Model for Efficient Video Understanding
by: Li, Kunchang, et al.
Published: (2024)

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception
by: Yan, Ziang, et al.
Published: (2025)

Make Your Training Flexible: Towards Deployment-Efficient Video Models
by: Wang, Chenting, et al.
Published: (2025)

VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
by: Li, Xinhao, et al.
Published: (2024)

Unmasked Teacher: Towards Training-Efficient Video Foundation Models
by: Li, Kunchang, et al.
Published: (2023)

VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
by: Li, Xinhao, et al.
Published: (2025)

FreeRet: MLLMs as Training-Free Retrievers
by: Zhu, Yuhan, et al.
Published: (2025)

Harvest Video Foundation Models via Efficient Post-Pretraining
by: Li, Yizhuo, et al.
Published: (2023)

InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
by: Wang, Yi, et al.
Published: (2024)

InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
by: Wang, Yi, et al.
Published: (2025)

InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
by: Wang, Yi, et al.
Published: (2023)

VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
by: Li, Xinhao, et al.
Published: (2024)

InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision
by: Wang, Chenting, et al.
Published: (2025)

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
by: Li, Kunchang, et al.
Published: (2023)

TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
by: Guo, Yiwei, et al.
Published: (2024)

UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation
by: Yue, Zhengrong, et al.
Published: (2025)

Percept, Chat, and then Adapt: Multimodal Knowledge Transfer of Foundation Models for Open-World Video Recognition
by: Chen, Boyu, et al.
Published: (2024)

VideoChat: Chat-Centric Video Understanding
by: Li, KunChang, et al.
Published: (2023)

Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel
by: Wang, Zun, et al.
Published: (2024)

Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
by: Yu, Xudong, et al.
Published: (2024)

Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
by: Li, Songze, et al.
Published: (2025)

Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
by: Liu, Qinying, et al.
Published: (2022)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
by: Zeng, Xiangyu, et al.
Published: (2025)

QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
by: Wang, Xinhao, et al.
Published: (2026)

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
by: Zeng, Xiangyu, et al.
Published: (2026)

OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation
by: Wang, Yongxu, et al.
Published: (2025)

ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video
by: Li, Xinhao, et al.
Published: (2023)

MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration
by: Ding, Yanbo, et al.
Published: (2024)

Super Encoding Network: Recursive Association of Multi-Modal Encoders for Video Understanding
by: Chen, Boyu, et al.
Published: (2025)

Vlogger: Make Your Dream A Vlog
by: Zhuang, Shaobin, et al.
Published: (2024)

Exploring Motion-Language Alignment for Text-driven Motion Generation
by: Gu, Ruxi, et al.
Published: (2026)

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
by: Sheng, Lijun, et al.
Published: (2025)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
by: Guo, Kuangpu, et al.
Published: (2025)

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages
by: Wang, Zhilin, et al.
Published: (2025)

CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks
by: Qi, Yu, et al.
Published: (2025)

V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
by: Yue, Zhengrong, et al.
Published: (2025)

VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations
by: Dong, Lu, et al.
Published: (2025)

VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
by: Jiang, Tianxiang, et al.
Published: (2025)

ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
by: Yin, Hao, et al.
Published: (2025)