Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
cs.CV, cs.AI, cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
Code: https://github.com/thanku-all/parse_
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Qwen2.5-VL Technical Report
- Xetrieval: Explaining Dense Retrieval through Feature Elicitation
- PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning
- VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
- AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
- VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
- Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
- MACD: Model-Aware Contrastive Decoding via Counterfactual Data
- VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models
- EventHallusion: Diagnosing Event Hallucinations in Video LLMs
- Your Dense Retriever is Secretly an Expeditious Reasoner
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models