Knowledge catalogue
arXiv:2608.15261v1 Announce Type: new Abstract: Optical imagery provides rich appearance cues, whereas synthetic aperture radar (SAR) offers observations that are less sensitive to illumination and we
arXiv:2608.11519v1 Announce Type: new Abstract: Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems.
arXiv:2606.19079v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. Given s
arXiv:2608.00577v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have become a dominant architecture for large-scale AI services, yet deploying them over geo-distributed heterogeneous
arXiv:2608.00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it. A controller may answer dir
arXiv:2607.25532v1 Announce Type: new Abstract: Consider a model trained at a single hospital to predict patient recovery, where the measured feature X bundles the patient's true health signal (C) wit
arXiv:2607.25068v1 Announce Type: new Abstract: Routing decisions between a cheap heuristic and an expensive large language model (LLM) are typically framed as a difficulty problem: send the hard case
arXiv:2607.24801v1 Announce Type: cross Abstract: We study the problem of guarded query routing, where we assume that a user query first meets a router that either determines the ideal endpoint for in
arXiv:2607.23837v1 Announce Type: cross Abstract: Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially, leading to catastrophic forge
arXiv:2607.23467v1 Announce Type: new Abstract: We study an integrated pickup-and-delivery problem on sparse, non-Euclidean networks that jointly optimizes cyclic routing, cargo flow allocation, and c
arXiv:2607.03822v1 Announce Type: new Abstract: Vision-based 3D occupancy prediction fundamentally relies on the 2D-to-3D view transformation. Current paradigms predominantly utilize explicit physical
arXiv:2607.02829v1 Announce Type: new Abstract: Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often cont
arXiv:2607.04534v1 Announce Type: new Abstract: We present an empirical study of structural routing failure in large language models (LLMs) over a formally verified algebraic corpus. The task requires
arXiv:2607.03948v1 Announce Type: new Abstract: We study the online routing problem in large language model serving, where requests arrive sequentially and must be dispatched to parallel decode worker
introducing tinyrouter i reverse engineered the routing architecture behind Skana AI's Fugu and built replication for open frontier models. it's a tiny ~10K parameter LLM router that learns which mode
Vercel has introduced routing rules functionality for AI Gateway, enabling users to define custom logic for directing requests to different AI models or endpoints. This feature allows developers to im
arXiv:2607.00053v1 Announce Type: cross Abstract: Large language models (LLMs) embedded in multi-turn agentic harnesses are reshaping software engineering (SWE), but routing every task to a frontier m
arXiv:2606.31163v1 Announce Type: cross Abstract: Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifia
arXiv:2606.30680v1 Announce Type: cross Abstract: Truck-drone delivery is an emerging last-mile logistics mode combining the long-haul capacity of trucks with the flexible service capability of drones
arXiv:2606.29424v1 Announce Type: new Abstract: Model routing balances solution accuracy and computational cost by selecting among models of varying capabilities. While recent multi-round frameworks i
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose
arXiv:2606.25821v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) architectures have emerged as an increasingly influential paradigm as they offer a strategic balance between parameter s
arXiv:2606.20739v1 Announce Type: new Abstract: We present a unified framework that turns a set of 6-DoF inspection viewpoints into a time-optimal, collision-free route for a 9-DoF robotic system. Unl
arXiv:2606.11625v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) are increasingly explored as predictive experts within emerging agentic time-series systems. However, TSFMs exhibi
arXiv:2606.06564v1 Announce Type: cross Abstract: Residual connections are central to training deep Transformers, but standard PreNorm residual streams aggregate sublayer updates with fixed unit weigh
arXiv:2602.02823v2 Announce Type: replace Abstract: As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given quer
arXiv:2605.31043v1 Announce Type: cross Abstract: Cross-domain EEG decoding remains challenging despite advances in Riemannian deep learning: covariance matrices from different subjects occupy systema
arXiv:2605.29319v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on table reasoning tasks but incur substantial inference cost due to long reasoning traces. Ste
arXiv:2508.21046v3 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high com
arXiv:2605.24270v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models activate only a small subset of parameters for each token, making router behavior a central part of mode
arXiv:2605.25424v1 Announce Type: cross Abstract: Existing LLM routing frameworks treat queries as independent events, neglecting the sequential nature of real-world user sessions constrained by globa
arXiv:2605.20262v1 Announce Type: new Abstract: We study selective refusal editing as a three-way control problem: induce non-refusal on designated edit prompts while preserving benign behavior and ha
arXiv:2605.18859v1 Announce Type: cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user reque
arXiv:2605.14416v1 Announce Type: new Abstract: The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem with broad applications in logistics and transportation. Real-world CVRP
arXiv:2507.00029v2 Announce Type: replace-cross Abstract: Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs)
arXiv:2605.10199v1 Announce Type: new Abstract: Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (
arXiv:2605.08754v1 Announce Type: new Abstract: Taxiway routing and on-surface conflict avoidance are coupled safety-critical decision problems in airport surface operations. Existing planning and opt
arXiv:2605.00180v1 Announce Type: cross Abstract: As the large language model (LLM) ecosystem expands, individual models exhibit varying capabilities across queries, benchmarks, and domains, motivatin
arXiv:2601.00823v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it i
arXiv:2604.19399v1 Announce Type: new Abstract: Federated learning (FL) is a key paradigm for distributed model learning across decentralized data sources. Communication in each FL round typically con
arXiv:2604.16930v1 Announce Type: new Abstract: Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Expe
arXiv:2604.17695v1 Announce Type: cross Abstract: KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensio
arXiv:2604.16583v1 Announce Type: new Abstract: Edge deployment of large language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small reside
arXiv:2603.18280v2 Announce Type: replace-cross Abstract: Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the
arXiv:2512.13876v2 Announce Type: replace Abstract: Detection Transformers (DETR) formulate object detection as a set prediction problem and enable end-to-end training without post-processing. However
arXiv:2604.09377v1 Announce Type: new Abstract: Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems
arXiv:2610.13276v1 Announce Type: new Abstract: Set-based language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the num
arXiv:2610.10616v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for monitoring, debugging, load anal
arXiv:2610.07505v1 Announce Type: new Abstract: Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candi
arXiv:2610.07047v1 Announce Type: cross Abstract: Compact time-frequency separators that mask the mixture and refine through a shared cell face two limits. First, a bounded multiplicative mask only sc
arXiv:2610.06926v1 Announce Type: new Abstract: Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do
arXiv:2610.05744v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces
arXiv:2610.05891v1 Announce Type: new Abstract: Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an image classifier's predictions, yet nothing in ordinary
arXiv:2610.06012v1 Announce Type: new Abstract: In this work, we study transformer attention through the lens of spectral geometry and operator theory. We view each attention head as a functional map
arXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language
arXiv:2610.02487v1 Announce Type: new Abstract: High-fidelity simulations are essential to scientific and engineering design, but can be expensive to run repeatedly. Learned surrogates offer a faster
arXiv:2610.00262v1 Announce Type: cross Abstract: Selective intent routing allows an assistant to act on reliable predictions while deferring uncertain requests. Standard confidence scores primarily r
arXiv:2609.38227v1 Announce Type: new Abstract: We introduce the two-echelon covering tour vehicle routing problem (2E-CTVRP) for the distribution of relief supplies after a disaster. In the first ech
arXiv:2609.37200v1 Announce Type: new Abstract: Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary o
arXiv:2510.09373v2 Announce Type: replace Abstract: Constraint Programming (CP) offers an intuitive, declarative framework for modeling Vehicle Routing Problems (VRP). While classical successor-based