mlsanityData to 14 Oct 2026

TasteRoute: Personalized Routing for Video Generation

arXiv 2610.05896 ↗First posted 5 Oct 2026cs.CV cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Rapid progress in video generation has led to a plethora of models that differ substantially in capability and generation cost. This raises a natural question: can each request be efficiently routed to an appropriate model? We find that even when the consensus of the other annotators is used as an oracle, it agrees with each annotator's own favorite only 34-55% of the time. Motivated by this observation, we introduce TasteRoute, a personalized video-generation router that selects a generator jointly based on the input request, user preferences, and available generation budget. Across text-to-video and image-to-video settings, TasteRoute is competitive with strong simple baselines on preference routing while reducing average generation cost. The cost saving increases under higher budget caps. Finally, we release TasteRoute-3k, a human-annotated dataset containing multi-model video comparisons, quality judgments, preference rankings, and user-profile signals to facilitate future research on personalized and cost-aware video routing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

21 of 26 references.

References · 21

  1. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  2. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 372
  3. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 372
  4. 2025Improving Video Generation with Human Feedbackcited by 284
  5. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 259
  6. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 238
  7. 2026LTX-2: Efficient Joint Audio-Visual Foundation Modelcited by 236
  8. 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Rankingcited by 230
  9. 2024GraphRouter: A Graph-based Router for LLM Selectionscited by 165
  10. 2024RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Modelscited by 88
  11. 2025Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learningcited by 72
  12. 2025Kling-Omni Technical Reportcited by 71
9 more
  1. 2024Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithmscited by 14
  2. 2024PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMscited by 12
  3. 2025Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routerscited by 11
  4. 2025Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethicscited by 6
  5. 2026OctoT2I: A Self-Evolving Agentic Text-to-Image Routercited by 5
  6. 2026VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generationcited by 5
  7. 2025PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modelingcited by 4
  8. 2026VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluationcited by 3
  9. 2026VDAR-Router: Adaptive LLMs Routing via Verbalized Query Difficulty Analysis Retrievalcited by 1

Built on by

Not cited yet.