DiFiT: Distribution-Fidelity-guided Visual Token Pruning for Multimodal Large Language Models
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
- Qwen2.5-VL Technical Report
- LLaVA-OneVision: Easy Visual Task Transfer
- Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model
- See What You Are Told: Visual Attention Sink in Large Multimodal Models
- Distilling the Knowledge in a Neural Network
- FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
- Confidence under Visual Token Pruning: Removed Evidence and Risk-Controlled Token Budgets for MLLMs
- OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- LMMs-Eval: Reality Check on the Evaluation of Large Multimodal 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