Knowledge catalogue
Demand for AI infrastructure is at an all-time high. Global accelerator shortages mean engineering teams can rarely get all the compute they need from just one data center — capacity comes a cluster h
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual
arXiv:2605.01710v1 Announce Type: new Abstract: AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before res
arXiv:2604.00421v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) layers increase model capacity by activating only a small subset of experts per token, and typically rely on a learned rout
arXiv:2609.35066v1 Announce Type: new Abstract: Most neural constructive solvers for the vehicle routing problem (VRP) use route-by-route construction, extending one route until completion before star
arXiv:2609.32821v1 Announce Type: cross Abstract: Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mi
arXiv:2609.32581v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become a standard way to scale model capacity while keeping computation sparse, yet routing remains a key
arXiv:2609.34326v1 Announce Type: new Abstract: Large Language Model (LLM) routers commonly rely on neural query embeddings, with larger encoders expected to better capture query intent and difficulty
arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, how
arXiv:2609.06815v1 Announce Type: cross Abstract: An open, networked web will allow agents to run frozen models from multiple vendors, keep their history private, and teach each other which tool to ca
arXiv:2606.31820v1 Announce Type: new Abstract: Large-scale capacitated vehicle routing problems (CVRPs) are commonly addressed using cluster-first route-second (CFRS) approaches that split a routing
arXiv:2609.37362v1 Announce Type: new Abstract: Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--effi
arXiv:2609.37402v1 Announce Type: new Abstract: Large language model (LLM) routing reduces serving cost by assigning each query to an appropriate model while preserving response quality. Learning such
arXiv:2609.36724v1 Announce Type: new Abstract: Sparse expert models can distribute traffic evenly while still grouping incompatible training signals within the same experts. We study routing as a gra
arXiv:2609.16206v1 Announce Type: new Abstract: Disaggregated LLM serving places compute heavy prefill and memory heavy decode on separate GPU pools. Systems such as DistServe, Splitwise, and Mooncake
arXiv:2603.02227v2 Announce Type: replace-cross Abstract: Learned gates can approximate sparse attention patterns on frozen transformers, yet provide limited benefit over random gates when trained joi
arXiv:2607.28670v1 Announce Type: new Abstract: A stochastic Gumbel-Top-K router defines, for every token of a mixture-of-experts (MoE) model, a routing law: a distribution over ordered expert lists a
arXiv:2605.10235v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-s
arXiv:2605.10057v1 Announce Type: new Abstract: Compositional spatiotemporal reasoning often requires a system to invoke multiple heterogeneous specialists, such as geometric, temporal, topological, a
arXiv:2605.09301v1 Announce Type: cross Abstract: The Capacitated Vehicle Routing Problem (CVRP) underpins modern last-mile logistics. Current Neural Combinatorial Optimization (NCO) methods construct
arXiv:2605.09850v1 Announce Type: cross Abstract: Post-hoc calibration is usually evaluated as a function of logits or softmax confidence alone, even as routing-augmented architectures increasingly ac
arXiv:2604.02927v2 Announce Type: replace Abstract: Routing algorithms are crucial for efficient computer network operations, and in many settings they must be able to react to traffic bursts within m
arXiv:2609.27822v1 Announce Type: cross Abstract: A common multi-agent design asks agents to report confidence and lets the highest-scoring agent speak next, implicitly using one scalar both to route
arXiv:2608.14140v1 Announce Type: new Abstract: The problem of route optimization with realistic constraints is becoming extremely relevant in the face of global urban population growth. While we are
arXiv:2610.01495v1 Announce Type: new Abstract: Dynamic architectures leave a per-example routing trace beside each prediction, and diffuse routing is easy to read as a sign that the prediction is unr
arXiv:2604.07030v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures are increasingly popular for frontier large language models (LLM) but they introduce training challenges d
arXiv:2609.38956v1 Announce Type: new Abstract: Routing signals of modern vision transformers -- expert gates, attention-residual weights and halting scores -- often improve probes that predict whethe
arXiv:2609.39749v1 Announce Type: new Abstract: Routing and switch placement are fundamental combinatorial optimization problems in chip design, requiring the joint optimization of routing topology an
arXiv:2609.39445v1 Announce Type: new Abstract: Time series foundation models (TSFMs) commonly adapt to new data by attaching a single trainable head to a frozen backbone, a one-size-fits-all setup th
arXiv:2609.11414v1 Announce Type: new Abstract: Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing
arXiv:2609.00662v1 Announce Type: new Abstract: A multi-model language service must route each request while preserving workload-level budgets for compute, latency, memory, or monetary cost. Two featu
arXiv:2609.01100v1 Announce Type: new Abstract: In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting exp
arXiv:2608.27380v1 Announce Type: new Abstract: AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This fram
arXiv:2603.03230v2 Announce Type: replace-cross Abstract: The electric vehicle routing problem with time windows (EVRPTW) extends the classical VRPTW by introducing battery capacity constraints and ch
arXiv:2608.06171v1 Announce Type: new Abstract: Web agents observe a browser through text, pixels, or both, and the choice is usually fixed once for all tasks. We measure six observation modes across
arXiv:2607.26807v1 Announce Type: new Abstract: While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across
arXiv:2604.21335v1 Announce Type: cross Abstract: Sub-token routing offers a finer control axis for transformer efficiency than the coarse units used in most prior work, such as tokens, pages, heads,
arXiv:2509.14255v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models improve efficiency through sparse activation, but their learned gating functions provide limited insight into routin
arXiv:2603.20997v2 Announce Type: replace Abstract: We identify a routing paradox in hybrid sequence models: content-based routing - deciding which tokens deserve expensive attention - requires pairwi
arXiv:2610.13439v1 Announce Type: cross Abstract: Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes t
arXiv:2607.24471v1 Announce Type: new Abstract: A central question in the in-context learning literature is whether transformers can organize episode-level adaptation around different inductive-bias f
arXiv:2607.22806v1 Announce Type: new Abstract: Modern cloud deployments distribute applications across multiple geographic regions, yet standard routing mechanisms prioritize latency while ignoring t
arXiv:2606.18774v2 Announce Type: replace Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://route
have been thinking a bunch about model routing and related things current thoughts here, would love feedback: 1/ there is a difference between 'model routing' and 'model council' 'model routing' = rou
arXiv:2609.02404v1 Announce Type: cross Abstract: Sparse mixture-of-experts (MoE) models use an independently parameterized router at each sparse layer to select experts for every token. Prior work ha
arXiv:2602.00488v3 Announce Type: replace Abstract: Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generaliz
arXiv:2605.19378v1 Announce Type: new Abstract: This paper systematically diagnoses the training failure modes of Token-Choice sparse Mixture-of-Experts (MoE) on video Diffusion Transformers. Starting
arXiv:2609.03150v1 Announce Type: cross Abstract: Multi-domain fine-tuning often combines MoE routing with LoRA, assuming that token-level routing separates domain-specific updates. We test this assum
arXiv:2606.15315v2 Announce Type: replace Abstract: Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user pr
arXiv:2608.17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts
arXiv:2608.16375v1 Announce Type: cross Abstract: We introduce Multinomial Subset Routing (MSR), a new online routing framework over K experts in which the learner keeps a multinomial routing policy i
arXiv:2605.28384v1 Announce Type: new Abstract: Standard transformer architectures apply a single attention mechanism uniformly across all tokens and sequence positions, irrespective of local context
arXiv:2605.07260v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token to a small subset of experts, but whether the routes selected by a trained top-k router are
arXiv:2610.12242v1 Announce Type: new Abstract: Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While
arXiv:2610.06725v1 Announce Type: new Abstract: Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers c
arXiv:2609.20347v1 Announce Type: cross Abstract: LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes diffi
arXiv:2602.20723v3 Announce Type: replace Abstract: Multimodal recommenders combine collaborative behavior with visual and textual item evidence, whose usefulness varies across user-item interactions.
arXiv:2607.28308v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models route each token to multiple experts, suggesting a geometric account of their benefit: co-selected exper
arXiv:2607.04118v1 Announce Type: cross Abstract: With the rise of parametric memory, LoRA-based External Parametric Memory (EPM) has emerged as a modular solution, but existing routing methods often
arXiv:2606.08814v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) scales model capacity efficiently by selectively routing inputs to a specialized subset of experts. However, input-expert speci