Copertina

VISTA: Mitigating Semantic Inertia in Video-LLMs via Training-Free Dynamic Chain-of-Thought Routing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jin, Hongbo, Ding, Jiayu, Xie, Siyi, Luo, Guibo, Li, Ge
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TIR-Flow: Active Video Search and Reasoning with Frozen VLMs
di: Jin, Hongbo, et al.
Pubblicazione: (2026)

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
di: Shen, Leqi, et al.
Pubblicazione: (2025)

Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning
di: Ou, Siqu, et al.
Pubblicazione: (2025)

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
di: Li, Jiaqi, et al.
Pubblicazione: (2026)

VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition
di: Jin, Hongbo, et al.
Pubblicazione: (2025)

Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
di: Ma, Ji, et al.
Pubblicazione: (2026)

VISD: Enhancing Video Reasoning via Structured Self-Distillation
di: Lin, Hao, et al.
Pubblicazione: (2026)

Training-Free Semantic Video Composition via Pre-trained Diffusion Model
di: Guo, Jiaqi, et al.
Pubblicazione: (2024)

CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
di: Guo, Haiyang, et al.
Pubblicazione: (2026)

DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation
di: Ge, Mingji, et al.
Pubblicazione: (2026)

Mitigating Perception Bias: A Training-Free Approach to Enhance LMM for Image Quality Assessment
di: Chen, Baoliang, et al.
Pubblicazione: (2024)

Training-Free Efficient Video Generation via Dynamic Token Carving
di: Zhang, Yuechen, et al.
Pubblicazione: (2025)

VORTA: Efficient Video Diffusion via Routing Sparse Attention
di: Sun, Wenhao, et al.
Pubblicazione: (2025)

FreeSpec: Training-Free Long Video Generation via Singular-Spectrum Reconstruction
di: Chen, Fangda, et al.
Pubblicazione: (2026)

Unfolding Videos Dynamics via Taylor Expansion
di: Chen, Siyi, et al.
Pubblicazione: (2024)

VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool
di: Wang, Yan, et al.
Pubblicazione: (2024)

DVI: Disentangling Semantic and Visual Identity for Training-Free Personalized Generation
di: Li, Guandong, et al.
Pubblicazione: (2025)

Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
di: Luo, Jiayi, et al.
Pubblicazione: (2026)

Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation
di: Shi, Yudi, et al.
Pubblicazione: (2024)

RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation
di: Wen, Junwei, et al.
Pubblicazione: (2026)

AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation
di: Ge, Jiannan, et al.
Pubblicazione: (2024)

Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
di: Huo, Yu, et al.
Pubblicazione: (2026)

Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
di: Wu, Yuan, et al.
Pubblicazione: (2026)

DriveCoT: Integrating Chain-of-Thought Reasoning with End-to-End Driving
di: Wang, Tianqi, et al.
Pubblicazione: (2024)

MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
di: Xie, Jianhao, et al.
Pubblicazione: (2025)

StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
di: Hu, Yuhang, et al.
Pubblicazione: (2025)

Training-Free Semantic Segmentation via LLM-Supervision
di: Sun, Wenfang, et al.
Pubblicazione: (2024)

Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
di: Tang, Yuanmin, et al.
Pubblicazione: (2024)

MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval
di: Park, Jeong-Woo, et al.
Pubblicazione: (2025)

X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
di: Pulakurthi, Prasanna Reddy, et al.
Pubblicazione: (2025)

Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
di: Huang, Chao, et al.
Pubblicazione: (2025)

Reinforcing Structured Chain-of-Thought for Video Understanding
di: Wang, Peiyao, et al.
Pubblicazione: (2026)

Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought
di: Zhang, Shuyi, et al.
Pubblicazione: (2025)

Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding
di: Luo, Bingjun, et al.
Pubblicazione: (2026)

SlideChain: Semantic Provenance for Lecture Understanding via Blockchain Registration
di: Manik, Md Motaleb Hossen, et al.
Pubblicazione: (2025)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
di: Jin, Hongbo, et al.
Pubblicazione: (2025)

CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
di: Kao, Shiu-hong, et al.
Pubblicazione: (2025)

C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation
di: Li, Yuhao, et al.
Pubblicazione: (2025)

Chain of Event-Centric Causal Thought for Physically Plausible Video Generation
di: Wang, Zixuan, et al.
Pubblicazione: (2026)

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering
di: Cai, Jianfeng, et al.
Pubblicazione: (2025)