Can LLMs Design Video Coding Tools? A Case Study on Planar Mode

arXiv:2609.01535 · cs.MM, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.MM, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Core — 8× in this paper · explained in 2 episodes
• Enhanced Compression Model — 3× in this paper
• Quantization — 3× in this paper · explained in 12 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Joint Video Experts Team — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• From Advanced Video Coding — 1× in this paper
• Overview of the Versatile Video Coding — 1× in this paper
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• LLM-Driven Heuristic Frame-Level Quantization Parameter Adaptation for VVenC

Related papers

• ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling
• Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models
• Mitigating GenAI-powered Evidence Pollution for Out-of-Context Multimodal Misinformation Detection
• A Rate-Distortion-Classification Approach for Lossy Image Compression