Search: “routing”

I’ve been experimenting with a custom inference/runtime research project called CRANE V2, mostly because I wanted to answer a stupid question: How far can you push absurdly large MoE models on an ordi

arXiv:2608.17711v1 Announce Type: new Abstract: Prediction cascades significantly reduce energy consumption of Artificial Intelligence (AI) models while maintaining high predictive performance. The id

arXiv:2608.15051v1 Announce Type: new Abstract: This paper proposes a Mamba surrogate model with mixture-of-experts (MoE) routing to represent the transient dynamics of inverter-based resources. A Mam

arXiv:2608.14332v1 Announce Type: cross Abstract: Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing

arXiv:2607.12986v1 Announce Type: new Abstract: Plan evaluators can reward a strategic plan for becoming less explicit. This paper studies that failure in a staged expected-value scorer for LLM-genera

arXiv:2606.30709v1 Announce Type: cross Abstract: Hierarchical Global Attention (HGA) is a drop-in replacement for dense causal attention in pretrained long-context transformers. HGA preserves the ori

arXiv:2606.20772v1 Announce Type: new Abstract: Camera-first autonomous-driving models predict future ego waypoints from images, ego-state features, and route commands, but waypoint supervision alone

arXiv:2606.11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes. We introduce My Chem

arXiv:2512.13996v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-k routing imposes a rigid sparsit

arXiv:2601.03425v2 Announce Type: replace-cross Abstract: Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumptio

arXiv:2605.16508v1 Announce Type: cross Abstract: As agent systems scale, skills accumulate into large reusable libraries, yet their scaling laws remain poorly understood. Across 15 frontier LLMs, 1,1

arXiv:2605.12952v1 Announce Type: new Abstract: Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this paper de

arXiv:2605.00604v1 Announce Type: new Abstract: Sparse MoE routing fails at domain transitions, where the current token belongs to one distribution and the next to another. In a controlled experiment

arXiv:2604.22785v1 Announce Type: new Abstract: Large language model (LLM) deployments increasingly rely on multi-agent architectures in which multiple models either compete through routing mechanisms

arXiv:2604.23996v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert

At Google Cloud, every day is Developer Day, but none so much as day 2 of Google Cloud Next, when we hold the developer keynote. This year’s topic? An in-depth look at Gemini Enterprise Agent Platform

arXiv:2502.15315v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts (MoE) architectures have emerged as a promising approach to decoupling model capacity from computational cost. At the core

For decades, expense automation relied on a simple premise: If the machine can read the text, it can do the work. But anyone who has ever tried to scan a crumpled, smudged, or sun-bleached receipt fro

AI Gateway combines content deletion with provider routing agreements; model exceptions, caching, metadata and application storage limit the ZDR promise.

arXiv:2610.20209v1 Announce Type: new Abstract: Routability prediction enables rapid evaluation of placement quality without routing, providing effective feedback for routability-driven placement opti

arXiv:2610.08457v1 Announce Type: new Abstract: Integrated circuit design involves multiple design stages: logic synthesis, floorplanning, placement, and routing, with each stage taking hours to weeks

arXiv:2610.07276v1 Announce Type: cross Abstract: Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verification

arXiv:2610.04953v1 Announce Type: new Abstract: Euclidean combinatorial optimization problems (ECOPs), such as the Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP), poss

Introducing Agr, an open decision model by Command Code. · Agr (31B) and Agr-flash (360M) · 58.15 on Decision Index 0.2.1 · Focus on: tool calls & routing · TypeSafe SDK support Agr is best-in-class o

arXiv:2609.36221v1 Announce Type: new Abstract: The way a model distributes activity over each layer's attention heads offers a coarse view of how it routes information through depth; how this changes

arXiv:2609.36062v1 Announce Type: new Abstract: Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear att

arXiv:2609.33780v1 Announce Type: new Abstract: Verified solutions are not equally useful for preparing reasoning models for reinforcement learning (RL). We present a comprehensive study of route dive

arXiv:2609.31360v1 Announce Type: new Abstract: Inference in LLMs is conventionally a fixed-depth, fixed-order forward pass through every layer, regardless of how difficult the input is. The human bra

arXiv:2609.29397v1 Announce Type: new Abstract: Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-se

arXiv:2607.09694v2 Announce Type: replace-cross Abstract: Attention Residuals (AttnRes) replace the fixed residual sum with depth-wise attention over previous sub-layer outputs in Large Language Model

TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture

arXiv:2609.18860v1 Announce Type: cross Abstract: When a large vision-language model misclassifies a harmful meme, the failure may reflect missing internal evidence or an inability to route represente

arXiv:2609.16610v1 Announce Type: new Abstract: Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that i

arXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large fo

arXiv:2609.00155v1 Announce Type: cross Abstract: Latent language identification is often used to argue that multilingual language models route computation through language-specific states, such as En

arXiv:2609.01024v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However

arXiv:2608.13911v1 Announce Type: new Abstract: Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific mo

arXiv:2608.10207v1 Announce Type: new Abstract: Bus bunching degrades service regularity and increases passenger waiting in high-frequency transit. Existing reinforcement-learning-based holding contro

arXiv:2608.06912v1 Announce Type: new Abstract: The top-k operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and atten

arXiv:2608.03738v1 Announce Type: new Abstract: As Moore's law slows, the industry is turning to three-dimensional integration; yet in merged 3D-IC flows, routed designs expose bond-level defects with

arXiv:2607.26304v1 Announce Type: new Abstract: Editing character motion often requires transferring a gesture or gait from one or more reference motions while preserving the source action, timing, ro

arXiv:2607.21400v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions. However, route-level instructions commonly encod

arXiv:2607.13373v1 Announce Type: cross Abstract: Column generation (CG) is central to many large-scale optimization algorithms, including branch-price-and-cut methods for vehicle routing problems, bu

arXiv:2607.04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor 'oracle' code, or an entangled perceptual vector -- shape

arXiv:2607.00673v1 Announce Type: new Abstract: Robots deployed in unstructured outdoor environments often plan from scene reconstructions collected before deployment because operators cannot remap la

Model council as a tool to push performance definitely works, I think the interesting next frontier is trying to scale this at the agent level have been thinking a bunch about model routing and relate