token routing

Adapting Hybrid Parallel-Head Large Language Models for Southeast Asia AAAI 2026 Adaptive Depth Lightweight RGB-T Tracking with Holistic Token Routing CVPR 2026 Efficient Segmentation with Multimodal Large Language Model via Token Routing AAAI 2026 EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models AAAI 2026 FlowHN: Adaptive Token Routing for Efficient Parallel Hybrid Networks ACL 2026 MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models ACL 2026 OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models CVPR 2026 UEP: Portable Expert-Parallel Communication OSDI 2026 Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models ACL 2025 Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts NAACL 2025 LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant CVPR 2025 Memory Efficient Matting with Adaptive Token Routing AAAI 2025 Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning EMNLP 2025 MoEP: Modular Expert Paths for Sample-Efficient Language Modeling EMNLP 2025 Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model ICLR 2025 Token Level Routing Inference System for Edge Devices ACL 2025 ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts ICLR 2025 TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025 An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing ACL 2024 Routing in Sparsely-gated Language Models responds to Context EMNLP 2024 Turn Waste into Worth: Rectifying Top-k Router of MoE EMNLP 2024 XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection ACL 2024 CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval ACL 2023 CoLT5: Faster Long-Range Transformers with Conditional Computation EMNLP 2023 Leap-of-Thought: Accelerating Transformers via Dynamic Token Routing EMNLP 2023