video-llm

Tag

Cards List
#video-llm

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

Hugging Face Daily Papers ↗ · 2026-09-09 Cached

This survey examines inference-efficiency techniques for video large language models, analyzing cost reductions across frame sampling, encoding, token compression, and language model stages while identifying evaluation gaps.

0 favorites 0 likes
#video-llm

Video-Oasis: Rethinking Evaluation of Video Understanding

Hugging Face Daily Papers ↗ · 2026-07-02 Cached

Video-Oasis reveals that 55% of existing video benchmarks can be solved without visual input, exposing significant capability gaps in current video understanding models. State-of-the-art models perform only marginally above random guessing on the remaining video-native challenges.

0 favorites 0 likes
#video-llm

LiteFrame Scales Video LLM Efficiency (6 minute read)

TLDR AI ↗ · 2026-05-21 Cached

LiteFrame introduces a highly efficient video encoder for Video LLMs that uses Compressed Token Distillation to enable up to 8x more frames and 35% latency reduction while maintaining accuracy, setting a new Pareto frontier for long-form video understanding.

0 favorites 0 likes
← Back to home

Submit Feedback