SPOD: Recovering Suppressed Temporal Evidence in Video-LLMs via Single-Pass Orthogonal Decomposition
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/VioAgnes/SPOD
Terminology
Sources
- Qwen2.5-VL Technical Report
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- PaMi-VDPO: Mitigating Video Hallucinations by Prompt-Aware Multi-Instance Video Preference Learning
- VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
- Video-R1: Reinforcing Video Reasoning in MLLMs
- Principles of Visual Tokens for Efficient Video Understanding
- Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
- Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
- A Survey on Hallucination in Large Vision-Language Models
- ARGUS: Hallucination and Omission Evaluation in Video-LLMs
- InternVideo: General Video Foundation Models via Generative and Discriminative Learning
- VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models
- EventHallusion: Diagnosing Event Hallucinations in Video LLMs
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
- VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs