Knowledge catalogue
arXiv:2606.12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validat
arXiv:2606.09514v1 Announce Type: new Abstract: Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Tr
arXiv:2606.09131v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the sa
Coinbase : 'At Coinbase we're working hot on routing prompts to cheaper models where appropriate, & in some cases have been able to keep costs roughly flat, while token usage continues to grow exponen
I really do think we'll see a lot of value accrue in AI startups building 'model routing as a service' Not just OpenRouter - this includes a much broader set of verticalized agents and infrastructure.
Model routing is growing a lot these days Good take My guess is - demand for intelligence is near infinite - but 80% of workloads will be running on 99% cheaper models within 12-18 months - 20% of wor
New research from Renmin University. Treat skill selection as a harness in its own right. If you design skill routing for personal or edge agents, this work argues that the selection layer is a first-
arXiv:2606.06467v1 Announce Type: new Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate l
arXiv:2503.03137v3 Announce Type: replace Abstract: Constructive neural combinatorial optimization (NCO) offers a promising paradigm for solving vehicle routing problems (VRPs) by directly learning to
arXiv:2606.02463v1 Announce Type: cross Abstract: In 3D environments, Embodied Agents answer spatially relevant questions through reasoning from a mixture of modalities including natural language, RGB
arXiv:2605.30898v1 Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing a
'Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn' wtf? how?? Introducing Claude Opus 4.8: it builds on Opus 4.7 with sh
OpenCode now integrates with DigitalOcean's Inference Router, enabling intelligent routing of AI model requests across distributed infrastructure. This integration allows developers to optimize model
arXiv:2511.14584v3 Announce Type: replace-cross Abstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commi
arXiv:2605.27959v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based appro
arXiv:2605.28764v1 Announce Type: new Abstract: Vast quantities of compute (GPU cycles on personal workstations, idle inference servers, and edge devices between jobs) go unused because no incentive-a
arXiv:2605.26147v1 Announce Type: new Abstract: Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited vis
arXiv:2601.02144v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sp
arXiv:2605.20618v1 Announce Type: new Abstract: Although Vehicle Routing Problems (VRP) are essential to many real-world systems, they remain computationally intractable at scale due to their combinat
arXiv:2605.22057v1 Announce Type: new Abstract: Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarel
arXiv:2605.20644v1 Announce Type: new Abstract: Design for manufacturing plays a critical role in advanced aeroengine development, where complex components necessitate careful consideration of manufac
arXiv:2510.12773v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and i
arXiv:2605.19975v1 Announce Type: cross Abstract: Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current train
arXiv:2605.17106v1 Announce Type: new Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary st
arXiv:2605.18209v1 Announce Type: cross Abstract: Spatial question answering over egocentric video is a challenging task that requires Vision-Language Models (VLMs) to reason about 3D object positions
arXiv:2605.15484v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) networks promise favorable accuracy-compute trade-offs, yet practical vision deployments are hindered by expert collapse and li
arXiv:2605.14323v1 Announce Type: cross Abstract: We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General
arXiv:2605.08686v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typ
arXiv:2605.08830v1 Announce Type: cross Abstract: End-to-end autonomous driving requires models to understand traffic scenes, infer driving intent, and generate executable motion plans. Recent vision-
In this post, we dive deep into the architecture and techniques we used to improve Miro’s bug routing, achieving six times fewer team reassignments and five times shorter time-to-resolution powered by
arXiv:2504.05407v2 Announce Type: replace-cross Abstract: Autonomous surveillance missions in Internet of Things (IoT) networks often involve solving NP-hard combinatorial optimization problems to ens
arXiv:2604.23577v1 Announce Type: new Abstract: Serving diverse NLP workloads with large language models is costly: at one enterprise partner, inference costs exceeded $200K/month despite over 70% of
arXiv:2604.20860v1 Announce Type: cross Abstract: Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g
arXiv:2604.17822v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Langua
arXiv:2509.18169v3 Announce Type: replace-cross Abstract: Tasks on complex systems require high-precision numerical computation to support decisions, but current large language models (LLMs) cannot in
arXiv:2604.15489v1 Announce Type: cross Abstract: The Internet of Medical Things (IoMT) enables intelligent healthcare services but faces challenges such as dynamic topology, energy constraints, and d
arXiv:2603.00663v4 Announce Type: replace Abstract: The Moving Target Vehicle Routing Problem (MT-VRP) seeks trajectories for several agents that intercept a set of moving targets, subject to speed, t
arXiv:2604.15090v1 Announce Type: new Abstract: Any-Time Person Re-identification (AT-ReID) necessitates the robust retrieval of target individuals under arbitrary conditions, encompassing both modali
arXiv:2604.10652v1 Announce Type: new Abstract: Vehicle routing problems (VRPs) constitute a core optimization challenge in modern logistics and supply chain management. The recent neural combinatoria
arXiv:2604.09306v1 Announce Type: cross Abstract: Quantum networks are expected to become a key enabler for interconnecting quantum devices. In contrast to classical communication networks, however, i
arXiv:2506.19420v2 Announce Type: replace Abstract: Multimodal sarcasm understanding is a high-order cognitive task. Although large language models (LLMs) have shown impressive performance on many dow
arXiv:2610.13035v1 Announce Type: cross Abstract: Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences mak
arXiv:2610.04499v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to convert medical images into diagnostic texts to assist in clinical decision-making and alleviate the workload
arXiv:2610.01787v1 Announce Type: new Abstract: Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies t
arXiv:2609.39109v1 Announce Type: cross Abstract: Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalam
arXiv:2609.36366v1 Announce Type: cross Abstract: Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used de
arXiv:2609.36560v1 Announce Type: cross Abstract: Object re-identification (ReID) faces a recurring challenge: different identities can share highly similar global appearances, while the cues that dis
arXiv:2609.36063v1 Announce Type: cross Abstract: Neural Combinatorial Optimization (NCO) has achieved strong empirical success, yet the internal mechanisms driving model decisions remain largely unex
arXiv:2609.34487v1 Announce Type: new Abstract: Radiology report generation (RRG) increasingly incorporates heterogeneous clinical evidence, such as multi-view radiographs and previous reports, whose
arXiv:2609.31717v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems
arXiv:2609.34942v1 Announce Type: new Abstract: The inference efficiency of Multimodal Large Language Models (MLLMs) is severely constrained by massive visual token sequences induced by high-resolutio
arXiv:2609.30751v1 Announce Type: new Abstract: Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best
arXiv:2609.30922v1 Announce Type: new Abstract: Building adaptable AI systems requires effective coordination of specialized capabilities across diverse tasks. Low-rank adaptation (LoRA) enables modul
arXiv:2609.30613v1 Announce Type: cross Abstract: Dermoscopy classifiers built on Vision Transformers process all image patches uniformly, although diagnostic evidence is concentrated in the lesion re
arXiv:2609.30096v1 Announce Type: cross Abstract: Video diffusion is computationally expensive, as it requires executing a large model across many denoising steps. Even with step-distillation, inferen
arXiv:2609.28860v1 Announce Type: new Abstract: Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided me
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop.
arXiv:2609.25853v1 Announce Type: new Abstract: Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be
arXiv:2609.20340v1 Announce Type: new Abstract: Ultrasound image analysis plays a crucial role in cancer screening and prenatal diagnosis, yet comprehensive assessment requires jointly addressing task
arXiv:2411.04319v1 Announce Type: cross Abstract: Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capable large la