No article text was recorded for this version.
task-specific expert routing
Version 1 of 122 papers30 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
- Blog: M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
- Blog: One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
- Blog: UniSAR: Modeling User Transition Behaviors between Search and Recommendation
- Blog: MateRobot: Material Recognition in Wearable Robotics for People with Visual Impairments
- Blog: LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR
- Blog: Pluralistic Salient Object Detection
- Blog: MetaBEV: Solving Sensor Failures for 3D Detection and Map Segmentation
- Blog: Dynamic Modeling of Patients, Modalities and Tasks via Multi-modal Multi-task Mixture of Experts
- Blog: MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning
- Blog: SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization
- Blog: Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding
- Blog: CodeT5Mix: A Pretrained Mixture of Encoder-decoder Transformers for Code Understanding and Generation
- Blog: GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
- Blog: Research on a Decision Prediction Method Based on Causal Inference and a Multi-Expert FTOPJUDGE Mechanism
- Blog: Efficient Reinforcement Learning by Discovering Neural Pathways
- Blog: MoE-Loco: Mixture of Experts for Multitask Locomotion
- Blog: Sparse MoE as a New Treatment: Addressing Forgetting, Fitting, Learning Issues in Multi-Modal Multi-Task Learning
- Blog: Towards Smart Point-and-Shoot Photography
- Blog: Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data
- Blog: Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition
- Blog: Denoising Task Routing for Diffusion Models
History & citation
Current · Permanent link
- This direction split from Mitigating Gradient Interference with Sparse Mixture of Experts (91% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_task_specific_expert_routing_e2bfb51b,
title = {task-specific expert routing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/task-specific-expert-routing/rdr_e2bfb51b963140768122ea8f2de48598},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_task_specific_expert_routing_e2bfb51b_v1,
title = {task-specific expert routing},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/task-specific-expert-routing/rdr_e2bfb51b963140768122ea8f2de48598/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}