Copertina

FreeRet: MLLMs as Training-Free Retrievers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Yuhan, Zeng, Xiangyu, Wang, Chenting, Li, Xinhao, Liu, Chunxu, Xu, Yicheng, Yan, Ziang, Wang, Yi, Wang, Limin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
di: Yan, Ziang, et al.
Pubblicazione: (2024)

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

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

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

Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
di: Liu, Chunxu, et al.
Pubblicazione: (2025)

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

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

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

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

SORCE: Small Object Retrieval in Complex Environments
di: Liu, Chunxu, et al.
Pubblicazione: (2025)

Training-Free Reasoning and Reflection in MLLMs
di: Wei, Hongchen, et al.
Pubblicazione: (2025)

History-Aware Transformation of ReID Features for Multiple Object Tracking
di: Gao, Ruopeng, et al.
Pubblicazione: (2025)

VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking
di: Meng, Desen, et al.
Pubblicazione: (2025)

ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection
di: Sun, Yi, et al.
Pubblicazione: (2026)

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

Sparse Global Matching for Video Frame Interpolation with Large Motion
di: Liu, Chunxu, et al.
Pubblicazione: (2024)

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
di: Zhang, Zhiqi, et al.
Pubblicazione: (2026)

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

Training-Free Personalization via Retrieval and Reasoning on Fingerprints
di: Das, Deepayan, et al.
Pubblicazione: (2025)

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
di: Han, Su Ho, et al.
Pubblicazione: (2025)

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

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

Training-Free Pretrained Model Merging
di: Xu, Zhengqi, et al.
Pubblicazione: (2024)

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

RetCompletion:High-Speed Inference Image Completion with Retentive Network
di: Cang, Yueyang, et al.
Pubblicazione: (2024)

Generating a Paracosm for Training-Free Zero-Shot Composed Image Retrieval
di: Wang, Tong, et al.
Pubblicazione: (2026)

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
di: Wang, Jiahao, et al.
Pubblicazione: (2025)

ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins
di: Liu, Xinhao, et al.
Pubblicazione: (2026)

RIVER: A Real-Time Interaction Benchmark for Video LLMs
di: Shi, Yansong, et al.
Pubblicazione: (2026)

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
di: Liu, Yuanxin, et al.
Pubblicazione: (2025)

TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction
di: Zheng, Zhijie, et al.
Pubblicazione: (2026)

EventVAD: Training-Free Event-Aware Video Anomaly Detection
di: Shao, Yihua, et al.
Pubblicazione: (2025)

CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval
di: Xu, Yifan, et al.
Pubblicazione: (2024)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
di: Jiao, Qirui, et al.
Pubblicazione: (2024)

WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval
di: Wang, Tianyue, et al.
Pubblicazione: (2026)

GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing
di: Zhu, Zifeng, et al.
Pubblicazione: (2026)