Knowledge catalogue
arXiv:2609.38743v1 Announce Type: new Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retriev
arXiv:2609.38823v1 Announce Type: new Abstract: Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly becaus
arXiv:2609.38472v1 Announce Type: cross Abstract: Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstration
arXiv:2609.13268v1 Announce Type: new Abstract: Annual reports, diligence packs, and infographic dashboards bury numbers in page images: axes, cell grids, and footnotes that OCR pipelines flatten and
arXiv:2609.14825v1 Announce Type: cross Abstract: Large language models (LLMs) are often deemed unsafe for clinical question answering because of their tendency to hallucinate. Retrieval augmentation,
arXiv:2609.13682v1 Announce Type: cross Abstract: We introduce LayerRoute, a parameter-efficient method for adaptive transformer layer-skipping that combines per-layer hard-gated routing (trained via
arXiv:2609.01689v1 Announce Type: new Abstract: We revisit median-of-means estimation from a deterministic optimization viewpoint and develop a family of block-Lp estimators for robust learning with h
arXiv:2511.08590v2 Announce Type: replace Abstract: Large Language Model (LLM) routing has demonstrated strong capability in balancing response quality with computational cost. As users exhibit divers
arXiv:2503.01236v3 Announce Type: replace-cross Abstract: This paper addresses fixed-graph terrain-aware path refinement, in which a global planner is restricted to a predefined route space and may re
arXiv:2608.13790v1 Announce Type: cross Abstract: Macro placement significantly affects a chip's post-route performance, power, and area (PPA). Most placement methods optimize half-perimeter wirelengt
arXiv:2608.14252v1 Announce Type: new Abstract: Recent work suggests that some large language model representations have content or reference. Grounding can secure either without supplying live routes
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:2608.12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt t
arXiv:2608.12146v1 Announce Type: cross Abstract: Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense at
arXiv:2608.09355v1 Announce Type: new Abstract: RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in
arXiv:2510.19366v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) scales model capacity through sparse activation, and is becoming an important architecture for large language models (LLMs)
arXiv:2608.06867v1 Announce Type: new Abstract: No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment.
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long
server + ui: fix stream routes for model names containing a slash (#26137) server + ui: refactor resumable stream routes to query string conv_id The conversation id can embed a model name containing s
arXiv:2604.24608v1 Announce Type: cross Abstract: Large Language Models (LLMs) have recently been explored as fine-grained zero-shot re-rankers by leveraging attention signals to estimate document rel
arXiv:2510.08814v2 Announce Type: replace-cross Abstract: We present a proof architecture for (P neq NP) based on an upper--lower clash in polytime-capped conditional description length. We construct
arXiv:2610.15039v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models combine specialized experts through an input-dependent routing mechanism, and their sparse variants underpin many modern
arXiv:2610.09372v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) layers replace the feed-forward block of a Transformer with E expert networks, and each token is routed to k of these experts.
arXiv:2610.02584v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models combine learned routing with selection from a large expert pool. We isolate the contribution of dynamic expert co
arXiv:2610.02910v1 Announce Type: new Abstract: Suppressing a small set of routed experts can weaken the safety behavior of a sparse Mixture-of-Experts (MoE) language model without retraining. Which e
arXiv:2610.02762v1 Announce Type: new Abstract: Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We analyze six commercial r
arXiv:2610.02349v1 Announce Type: cross Abstract: Inter-agent communication is central to Large Language Model Multi-Agent Systems (LLM-MAS), but it introduces an underexplored vulnerability: Agent-in
arXiv:2610.02491v1 Announce Type: new Abstract: Large language models spend the same amount of computation on every token they generate, regardless of how difficult each token is to produce. Methods s
Introducing FireRouter with Opus. Our first router model. Routine tasks go to top open models, Claude Opus handles the rest. Cache and task-aware routing. Proven 98.1% of Opus accuracy with 57% lower
arXiv:2609.11859v1 Announce Type: new Abstract: How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through
arXiv:2605.22866v1 Announce Type: new Abstract: Compound AI systems route tasks through hierarchies of specialised components. Attribution is dominated by Shapley-based methods (SHAP), which decompose
arXiv:2605.12476v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse ont
Vercel’s unified API for hundreds of models — one endpoint, auth, failover, spend controls; pairs with the AI SDK and powers this wiki’s Ask models.
arXiv:2610.13370v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become the standard architecture for frontier LLMs. The multiple parallel experts in each transformer block theoret
arXiv:2610.07207v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability proble
Enterprises and individual developers frequently run multiple AI inference models. The right architecture can simplify how the models are called while also providing centralized governance. In this po
cuda : route sm70 to the Turing MMVQ nwarps table (#29753) cuda : route sm70 to the Turing MMVQ nwarps table Volta (sm_70) has no MMVQ parameter table of its own and falls through to GENERIC, which la
I have been building a somewhat unusual local inference machine around two Huawei Atlas 300I Duo cards. They are relatively inexpensive, passive, dual-accelerator PCIe cards with 96 GB of device memor
arXiv:2609.13058v1 Announce Type: new Abstract: Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have
arXiv:2601.16905v3 Announce Type: replace Abstract: Machine unlearning in Mixture-of-Experts (MoE) large language models presents a critical yet under-explored challenge. Current unlearning methods ap
arXiv:2608.25231v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-
arXiv:2602.02685v3 Announce Type: replace Abstract: Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree i
arXiv:2602.19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fi
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:2607.05915v1 Announce Type: new Abstract: PCB routing is the task of connecting the nets of a board with copper traces under strict design rules, yet learning-based methods still lag behind rule
arXiv:2605.29708v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) LLMs rely on sparse, router-driven expert activation, yet how safety alignment interacts with routed expert specialization rema
arXiv:2605.16349v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures achieve scalable capacity through sparse routing, yet the geometric structure of expert specialization remains po
arXiv:2605.17598v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior across underrepresented languages remains poorly unde
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:2609.20822v1 Announce Type: cross Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built
arXiv:2609.06593v1 Announce Type: cross Abstract: Choosing when to translate multilingual documents is a central routing problem in text classification: translation can improve predictions for some la
arXiv:2608.23794v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) scales language models by routing each input through a small set of independently parameterized experts. We show that copying
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: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