Related papers: When Does Content-Based Routing Work? Representati…

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

We investigate the problem of optimal request routing and content caching in a heterogeneous network supporting in-network content caching with the goal of minimizing average content access delay. Here, content can either be accessed…

Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow…

AI tasks differ in complexity and are best addressed with different computation strategies (e.g., combinations of models and decoding methods). Hence, an effective routing system that maps tasks to the appropriate strategies is crucial.…

State space models (SSMs) for language modelling promise an efficient and performant alternative to quadratic-attention Transformers, yet show variable performance on recalling basic information from the context. While performance on…

A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as a large pretrained model or human expert), an approach known…

Traffic image restoration under adverse weather conditions remains a critical challenge for intelligent transportation systems. Existing methods primarily focus on spatial-domain modeling but neglect frequency-domain priors. Although the…

Model routing chooses which language model to use for each query. By sending easy queries to cheaper models and hard queries to stronger ones, it can significantly reduce inference cost while maintaining high accuracy. However, most…

Driver attention recognition in driving scenarios is a popular direction in traffic scene perception technology. It aims to understand human driver attention to focus on specific targets/objects in the driving scene. However, traffic scenes…

Multimodal large language models (MLLMs) have advanced rapidly, yet heterogeneity in architecture, alignment strategies, and efficiency means that no single model is uniformly superior across tasks. In practical deployments, workloads span…

Sparse Mixture-of-Experts (MoE) architectures employ increasingly sophisticated routing mechanisms -- learned routers, multi-hop trajectories, token-dependent gating. We ask: does routing topology actually determine language modeling…

Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called…

State-space models (SSMs), such as Mamba (Gu & Dao, 2023), have been proposed as alternatives to Transformer networks in language modeling, by incorporating gating, convolutions, and input-dependent token selection to mitigate the quadratic…

Efficient long-context language modeling remains a significant challenge in Natural Language Processing (NLP). While Transformers dominate language tasks, they struggle with long sequences due to quadratic computational complexity in…

The routing algorithms for parallel computers, on-chip networks, multi-core processors, and multiprocessors system-on-chip (MP-SoCs) exhibit router failures must be able to handle interconnect router failures that render a symmetrical mesh…

Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt to the smallest feasible LLM. Existing works focus on…

Consider the robust network design problem of finding a minimum cost network with enough capacity to route all traffic demand matrices in a given polytope. We investigate the impact of different routing models in this robust setting: in…

The rapid advancement of large language models (LLMs) and domain-specific AI agents has greatly expanded the ecosystem of AI-powered services. User queries, however, are highly diverse and often span multiple domains and task types,…

Quad Bayer demosaicing is the central challenge for enabling the widespread application of Hybrid Event-based Vision Sensors (HybridEVS). Although existing learning-based methods that leverage long-range dependency modeling have achieved…

Reconstructing high-fidelity MR images from undersampled k-space data requires recovering high-frequency details while maintaining anatomical coherence. We present HiFi-MambaV2, a hierarchical shared-routed Mixture-of-Experts (MoE) Mamba…