Knowledge catalogue
Routing and post-training open-source models won't only give you more accurate systems but also meaningfully faster and cheaper systems as most companies are currently learning (in addition to giving
arXiv:2606.03391v1 Announce Type: cross Abstract: Model merging has emerged as a cost-effective approach for consolidating the capabilities of multiple LLMs without retraining. However, existing mergi
Automatic behind the scene routing in user interfaces (instead of model picker) will redistribute value capture and usage towards many more models than just frontier ones (especially towards open-sour
This article discusses how prefix-aware routing and prefix caching techniques can reduce the computational overhead and costs associated with running large language models at scale by eliminating redu
arXiv:2603.09453v3 Announce Type: replace-cross Abstract: Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring res
arXiv:2605.28577v1 Announce Type: new Abstract: AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with diff
arXiv:2605.26776v1 Announce Type: cross Abstract: In recent years, Deep Reinforcement Learning (DRL) has achieved substantial progress on Vehicle Routing Problems (VRPs). However, existing DRL-based m
arXiv:2605.25558v1 Announce Type: new Abstract: Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Curre
arXiv:2602.15811v2 Announce Type: replace-cross Abstract: Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on
arXiv:2603.06626v2 Announce Type: replace-cross Abstract: Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneou
Artificial intelligence inference routing startup OpenRouter Inc. today announced it raised 113 million in new funding led by CapitalG, Alphabet Inc.’s independent growth fund, to push the envelope fo
arXiv:2605.24817v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become an increasingly important paradigm for scaling Large Language Models (LLMs). As MoE models are incr
arXiv:2605.18015v1 Announce Type: new Abstract: Production log analytics in self-hosted, resource-constrained environments requires natural-language access to massive log streams without the cost of r
arXiv:2605.15179v1 Announce Type: cross Abstract: Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of d
arXiv:2605.11380v1 Announce Type: new Abstract: Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stat
arXiv:2605.02946v1 Announce Type: new Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly
arXiv:2605.01574v1 Announce Type: new Abstract: Vehicle Routing Problem (VRP) is one of the most complex NP-hard combinatorial optimization problem in transportation and logistics that requires a dyna
arXiv:2604.28102v1 Announce Type: new Abstract: Solving practical multi-depot vehicle routing problems (MDVRP) is a challenging optimization task central to modern logistics, increasingly driven by e-
arXiv:2604.26955v1 Announce Type: cross Abstract: AI tutoring systems in engineering labs face a tension between providing sufficient assistance and preserving learning opportunities. Existing systems
arXiv:2604.22407v1 Announce Type: cross Abstract: Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backen
arXiv:2604.22442v1 Announce Type: new Abstract: We introduce HubRouter, a pluggable module that replaces O(n^2) attention layers with O(nM) hub-mediated routing, where M =20 shows increasing seed sens
arXiv:2604.22229v1 Announce Type: cross Abstract: One-step offline RL actors are attractive because they avoid backpropagating through long iterative samplers and keep inference cheap, but they still
arXiv:2603.12592v2 Announce Type: replace-cross Abstract: Routing algorithms for public transport, particularly the widely used RAPTOR and its variants, often face performance bottlenecks during the t
arXiv:2604.17228v1 Announce Type: new Abstract: Conditional depth execution routes a subset of tokens through a lightweight cheap FFN while the remainder execute the standard full FFN at each controll
arXiv:2604.15499v1 Announce Type: cross Abstract: Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabli
We are excited to have @baseten as a day 0 launch partner for Kimi K2.6! Their inference stack brings KV-aware routing, NVFP4 on Blackwell, multi-modal hierarchical caching, and prefill-decode disaggr
arXiv:2604.13441v1 Announce Type: new Abstract: Ensuring energy feasibility under wind uncertainty is critical for the safety and reliability of UAV delivery missions. In realistic truck-drone logisti
arXiv:2604.10335v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance in math reasoning benchmarks, but their performance varies inconsistently across problems wi
arXiv:2510.22329v2 Announce Type: replace Abstract: The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a fundamental NP-hard optimization problem in logistics. Solving large-scale i
arXiv:2604.09681v1 Announce Type: cross Abstract: With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time in
arXiv:2604.08541v1 Announce Type: cross Abstract: Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon t
arXiv:2604.07264v1 Announce Type: cross Abstract: Operating LEO mega-constellations requires translating high-level operator intents ('reroute financial traffic away from polar links under 80 ms') int
Nice paper on agent memory. It explores an effective routing mechanism for memory in agents. The overall finding is that you want a separate retrieval strategy for each type of memory instead of one e
arXiv:2607.16656v2 Announce Type: replace Abstract: Object removal aims to eliminate target objects specified by a mask while preserving visual consistency with the surrounding regions. Existing metho
arXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir
arXiv:2610.09272v1 Announce Type: new Abstract: Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, cu
arXiv:2610.09440v1 Announce Type: new Abstract: Pre-trained vision encoders contain layer-wise visual representations that differ in spatial granularity, semantic abstraction, and sensitivity to local
arXiv:2610.07720v1 Announce Type: new Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing d
arXiv:2610.06677v1 Announce Type: new Abstract: Mixture-of-experts (MoE) routers typically apply softmax to the router scores and keep the top-K experts, making every token use exactly K experts. Spar
arXiv:2610.00913v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models provide strong behavioral priors for robotic manipulation, yet efficiently adapting them to downstream tasks remains
arXiv:2609.38760v1 Announce Type: new Abstract: Scalable robotic fleets have become increasingly popular for various applications such as package delivery, warehouse management, and military operation
arXiv:2609.39007v1 Announce Type: cross Abstract: Sessionized interaction histories contain behavioral patterns that can improve sequential recommendation. However, existing models process all session
arXiv:2609.36301v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regime
arXiv:2609.35833v1 Announce Type: new Abstract: Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on
Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playin
arXiv:2609.36980v1 Announce Type: new Abstract: Despite recent advances in accuracy and efficiency, coarse matching remains an indispensable yet costly stage in existing semi-dense matchers due to den
arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de
arXiv:2609.34475v1 Announce Type: new Abstract: LLMs cannot forget the way we delete a file. Strangely, we are asked to remove something that was never put anywhere in particular. What the model took
arXiv:2609.32255v1 Announce Type: cross Abstract: Tool-using LLM agents must decide not only whether additional information is needed, but also which source can resolve the uncertainty. Existing proac
arXiv:2609.34503v1 Announce Type: new Abstract: Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong with
arXiv:2609.34358v1 Announce Type: new Abstract: In agentic AI systems, frozen foundation models are increasingly deployed as closed-weight API endpoints, making downstream adaptation possible only thr
arXiv:2609.29235v1 Announce Type: cross Abstract: Camera-LiDAR fusion has become a prevailing paradigm for 3D object detection in autonomous driving. However, existing fusion detectors often establish
arXiv:2609.25606v1 Announce Type: new Abstract: Cable routing requires coordinated control of global cable topology and changing local contacts. We present CableVLA, an end-to-end multimodal vision-la
arXiv:2609.25049v1 Announce Type: new Abstract: Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions. Prior stud
arXiv:2609.21953v1 Announce Type: new Abstract: Learning to defer asks a predictive system when to act autonomously and when to defer to a human expert. Population-adaptive deferral extends this probl
arXiv:2609.17940v1 Announce Type: new Abstract: Sparse mixture-of-experts models route each token through a sequence of expert selections. We ask whether the immediately preceding selection adequately
arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-flex
Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa
arXiv:2609.14383v1 Announce Type: new Abstract: Real-time pedestrian detection in driving scenes is constrained by three coupled failure modes: tiny targets lose discriminative evidence, occlusion wea
arXiv:2607.21411v1 Announce Type: cross Abstract: Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key que