Cover Image

PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Bowen, Cai, Yujun, Yang, Ming-Hsuan, Wu, Hang, Wang, Yiwei
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
by: Wu, Hang, et al.
Published: (2026)

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
by: Ge, Haonan, et al.
Published: (2025)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
by: Ge, Haonan, et al.
Published: (2025)

CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning
by: Wu, Hang, et al.
Published: (2026)

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
by: Fu, Honghao, et al.
Published: (2026)

Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models
by: Wang, Zhaochen, et al.
Published: (2025)

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning
by: Wu, Hang, et al.
Published: (2025)

ChainMPQ: Interleaved Text-Image Reasoning Chains for Mitigating Relation Hallucinations
by: Wu, Yike, et al.
Published: (2025)

Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models
by: Wang, Zhaochen, et al.
Published: (2025)

Mitigating Coordinate Prediction Bias from Positional Encoding Failures
by: Tao, Xingjian, et al.
Published: (2025)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
by: Hyun, Jeongseok, et al.
Published: (2025)

Hierarchical, Interpretable, Label-Free Concept Bottleneck Model
by: Xie, Haodong, et al.
Published: (2026)

Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
by: Han, Kai, et al.
Published: (2024)

Finding Distributed Object-Centric Properties in Self-Supervised Transformers
by: Rawlekar, Samyak, et al.
Published: (2026)

FreeVA: Offline MLLM as Training-Free Video Assistant
by: Wu, Wenhao
Published: (2024)

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding
by: Tang, Yolo Yunlong, et al.
Published: (2024)

BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models
by: Shi, Fengyuan, et al.
Published: (2023)

STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing
by: Lee, Junsung, et al.
Published: (2025)

Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
by: Lai, Yixuan, et al.
Published: (2026)

Lost in Edits? A $λ$-Compass for AIGC Provenance
by: You, Wenhao, et al.
Published: (2025)

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

VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT
by: Xu, Yifang, et al.
Published: (2024)

VISTA: Mitigating Semantic Inertia in Video-LLMs via Training-Free Dynamic Chain-of-Thought Routing
by: Jin, Hongbo, et al.
Published: (2025)

PAS: Estimating the target accuracy before domain adaptation
by: Diniz, Raphaella, et al.
Published: (2026)

Enhancing Perception Capabilities of Multimodal LLMs with Training-Free Fusion
by: Chen, Zhuokun, et al.
Published: (2024)

Learning Spatial-Semantic Features for Robust Video Object Segmentation
by: Li, Xin, et al.
Published: (2024)

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
by: Cai, Zhaolin, et al.
Published: (2025)

A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos
by: He, Allen, et al.
Published: (2026)

EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory
by: Xiao, Ruiqiang, et al.
Published: (2026)

HawkEye: Training Video-Text LLMs for Grounding Text in Videos
by: Wang, Yueqian, et al.
Published: (2024)

Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs
by: Yang, Yuezhe, et al.
Published: (2025)

D3: Training-Free AI-Generated Video Detection Using Second-Order Features
by: Zheng, Chende, et al.
Published: (2025)

4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting
by: Zhou, Sifan, et al.
Published: (2026)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
by: Hu, Taihang, et al.
Published: (2024)

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
by: Wang, Songping, et al.
Published: (2025)

FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
by: Zhong, Haonan, et al.
Published: (2026)

Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
by: Liu, Xiaolin, et al.
Published: (2026)

Few-shot Semantic Encoding and Decoding for Video Surveillance
by: Cheng, Baoping, et al.
Published: (2025)

TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
by: Li, Baiqi, et al.
Published: (2026)

Xiaoice: Training-Free Video Understanding via Self-Supervised Spatio-Temporal Clustering of Semantic Features
by: Ji, Shihao, et al.
Published: (2025)