Cover Image

Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Jiaze, Yin, Hao, Xu, Haoran, Xu, Boshen, Tan, Wenhui, He, Zewen, Ju, Jianzhong, Luo, Zhenbo, Luan, Jian
Format:	Preprint
Published:	2026
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

REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
by: Li, Jiaze, et al.
Published: (2025)

TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding
by: Xu, Boshen, et al.
Published: (2025)

Think-Clip-Sample: Slow-Fast Frame Selection for Video Understanding
by: Tan, Wenhui, et al.
Published: (2026)

MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
by: Tan, Wenhui, et al.
Published: (2026)

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
by: Wang, Ye, et al.
Published: (2025)

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
by: Tan, Wenhui, et al.
Published: (2025)

Federated Joint Learning for Domain and Class Generalization
by: Xu, Haoran, et al.
Published: (2026)

Xiaomi MiMo-VL-Miloco Technical Report
by: Li, Jiaze, et al.
Published: (2025)

Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
by: Xu, Haoran, et al.
Published: (2026)

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
by: Li, Ao, et al.
Published: (2026)

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models
by: Tan, Wenhui, et al.
Published: (2026)

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
by: Guan, Yiran, et al.
Published: (2026)

Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
by: Wu, Yecheng, et al.
Published: (2026)

Draft-OPD: On-Policy Distillation for Speculative Draft Models
by: Lei, Haodi, et al.
Published: (2026)

Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
by: Zhang, Shaojie, et al.
Published: (2025)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
by: Yang, Zhicheng, et al.
Published: (2026)

Federated Balanced Learning
by: Li, Jiaze, et al.
Published: (2026)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
by: Cao, Di, et al.
Published: (2026)

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
by: Zhu, Linghao, et al.
Published: (2025)

OPD+: Rethinking the Advantage Design for On-Policy Distillation
by: Zhao, Hanyang, et al.
Published: (2026)

Direction-Aware Diagonal Autoregressive Image Generation
by: Xu, Yijia, et al.
Published: (2025)

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation
by: Liang, Renjie, et al.
Published: (2023)

GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solving
by: Deng, Linger, et al.
Published: (2026)

Flow-OPD: On-Policy Distillation for Flow Matching Models
by: Fang, Zhen, et al.
Published: (2026)

Multilevel Semantic-Aware Model for AI-Generated Video Quality Assessment
by: Li, Jiaze, et al.
Published: (2025)

Multimodal Long Video Modeling Based on Temporal Dynamic Context
by: Hao, Haoran, et al.
Published: (2025)

Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
by: Yuan, Qianhao, et al.
Published: (2026)

VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding
by: Wang, Shihao, et al.
Published: (2025)

DP-OPD: Differentially Private On-Policy Distillation for Language Models
by: Khadem, Fatemeh, et al.
Published: (2026)

Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution
by: Liang, Dingkang, et al.
Published: (2025)

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
by: Tang, Yolo Y., et al.
Published: (2025)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
by: Zhou, Yuhang, et al.
Published: (2026)

Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
by: Hou, Wenjin, et al.
Published: (2026)

EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
by: Lazaridis, Aristotelis, et al.
Published: (2026)

DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
by: Li, Quanhao, et al.
Published: (2026)

Enrich and Detect: Video Temporal Grounding with Multimodal LLMs
by: Pramanick, Shraman, et al.
Published: (2025)

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
by: Wang, Jianze, et al.
Published: (2026)

T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding
by: Guo, Chaohong, et al.
Published: (2026)

ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
by: Guan, Yiran, et al.
Published: (2026)

Mamba-VMR: Multimodal Query Augmentation via Generated Videos for Precise Temporal Grounding
by: Sun, Yunzhuo, et al.
Published: (2026)