Dual-Signal Adaptive KV-Cache Optimization for Long-Form Video Understanding in Vision-Language Models

Documenti analoghi

• VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
  di: Tu, Dezhan, et al.
  Pubblicazione: (2024)
• PEVLM: Parallel Encoding for Vision-Language Models
  di: Kang, Letian, et al.
  Pubblicazione: (2025)
• ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization
  di: Jafari, Sadegh, et al.
  Pubblicazione: (2025)
• Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
  di: Cheng, Hao, et al.
  Pubblicazione: (2024)
• Decouple and Cache: KV Cache Construction for Streaming Video Understanding
  di: Pang, Zhanzhong, et al.
  Pubblicazione: (2026)