Knowledge catalogue
arXiv:2607.01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without dow
arXiv:2607.01727v1 Announce Type: new Abstract: Synthetic data can be scaled along two routes: Source Expansion (SE), which enlarges the source by adding seed materials or generators, and Fixed-Source
arXiv:2607.00578v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide interpretability by routing predictions through a layer of human-understandable concepts. However, defining an
arXiv:2602.05711v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures are evolving towards finer granularity to improve parameter efficiency. However, existing MoE designs f
arXiv:2607.00780v1 Announce Type: new Abstract: Most adaptive-inference techniques for foundation models change what the model does - early exit, MoE routing, KV-cache compression, dynamic attention s
arXiv:2511.07175v2 Announce Type: replace Abstract: Efficient routing of mobile robot fleets requires roadmaps with high redundancy, short path lengths, and sufficient node and edge clearance for conf
arXiv:2606.31082v1 Announce Type: new Abstract: AI-generated image (AIGI) detection is undergoing a critical transition from laboratory benchmarks to open-world adversarial defense. The prevalent para
Anthropic's agentic coding tool Claude Code has worked with Google Cloud for a while now. An individual developer could easily point CLAUDE_CODE_USE_VERTEX=1 at a Google Cloud (GCP) project, grant the
Ethan Mollick predicts that multi-agent organizational structures will deliver better cost-to-performance ratios compared to simple task-based routing systems for AI applications. This suggests that m
arXiv:2606.30027v1 Announce Type: new Abstract: Color Fundus Photography (CFP) offers a low-cost and non-invasive route for ischemic heart disease (IHD) screening, but current studies are limited by s
arXiv:2606.30566v1 Announce Type: cross Abstract: We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through ob
arXiv:2603.05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters
Sakana Fugu Technical Report Instead of training one larger model, Sakana AI trains an orchestrator that reads each query and dynamically routes or composes GPT-5.5, Gemini-3.1-Pro, Claude Opus 4.8 an
When does combining LLMs help? Great analysis on combining language models, measured across 67 models from 21 providers. Any policy that routes, votes, cascades, or runs a mixture of agents and then r
arXiv:2606.26852v1 Announce Type: new Abstract: Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing. Wh
arXiv:2606.27144v1 Announce Type: new Abstract: Reliable action generation for multi-stage robotic manipulation remains challenging for Vision-Language-Action (VLA) models. While existing flow-matchin
arXiv:2606.27355v1 Announce Type: new Abstract: We study whether pre-deployment evaluation rollouts can be reused to supervise policy selection. Robot teams routinely smoke test candidate vision-langu
SITUATION EXPLAINED: 70% of frontier model queries could run locally for free. @ClementDelangue, co-founder and CEO of @huggingface: 'There was an interesting study from Stanford published last year s
arXiv:2606.26400v1 Announce Type: new Abstract: Agentic systems are changing how complex operational tasks are coordinated, introducing a new paradigm for connecting heterogeneous data sources and aut
BREAKING: Kazakhstan Railways is bringing Starlink internet to 900 train carriages this summer. • By July, around 900 train carriages will be equipped with Starlink internet. • The service will cover
arXiv:2606.25432v1 Announce Type: cross Abstract: Inference efficiency is typically pursued by shrinking the model: distillation, pruning, quantization, and sparse routing each lower per-token cost wh
arXiv:2606.24983v1 Announce Type: cross Abstract: Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulation
arXiv:2606.25344v1 Announce Type: new Abstract: 4D generation aims to animate 3D objects with realistic motion, holding great promise for applications. Existing methods typically decouple 3D asset gen
arXiv:2606.25665v1 Announce Type: new Abstract: Domain generalization (DG) aims to learn a model from one or more source domains that generalizes to an unseen target domain without accessing target da
Sometimes you just need a dose of fresh inspiration but your agent doesn't get the vibe. The creative-ideation skill analyzes your prompt and routes it through one of 22 creative methodologies from ar
What is actually limiting model routers for coding tasks? Most routers treat picking a model as a static, one-off classification. This paper identifies the real bottleneck as information deficit. Simp
arXiv:2606.20651v1 Announce Type: cross Abstract: Autonomous drone swarms in space-constrained environments such as warehouses, inspection corridors, and urban delivery routes must share limited airsp
arXiv:2603.19822v2 Announce Type: replace Abstract: Existing UAV vision-language navigation (VLN) benchmarks have enabled language-guided flight, but they largely focus on long, step-wise route descri
arXiv:2606.22597v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable d
Identity and access management company Okta Inc. today said more than 25 software makers have signed on to its Cross App Access framework, which routes the connections artificial intelligence agents m
arXiv:2606.21917v1 Announce Type: cross Abstract: Detecting hallucination risk before generation enables abstention, retrieval augmentation, and routing decisions without incurring the cost of decodin
arXiv:2606.23536v1 Announce Type: new Abstract: We propose a method for estimating time-varying traffic flow patterns from sparse aggregated vehicle counts. The method partitions the study area into s
arXiv:2606.22589v1 Announce Type: new Abstract: Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific ex
arXiv:2606.21868v1 Announce Type: new Abstract: Modern Mixture-of-Experts (MoE) models place most of their parameters in expert layers, yet only a small fraction of those experts are used for any toke
The Top AI Papers of the Week (June 14 - June 21): - PreAct - SpatialClaw - Back on Track - OpenClaw-Skill - From Trainee to Trainer - Compositional Skill Routing - Can LLM Agents Infer World Models?
arXiv:2606.11258v1 Announce Type: new Abstract: Gradient-based inversion of reaction-diffusion systems is typically approached via surrogate models or physics-informed neural networks (PINNs), while t
arXiv:2606.12217v1 Announce Type: cross Abstract: World Action Models (WAMs) offer a promising route for robot manipulation by using video generation models to model future scene evolution before prod
arXiv:2606.10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems. The standard training algorithm, REINFORCE with a ro
arXiv:2606.10703v1 Announce Type: cross Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of target
arXiv:2606.10369v1 Announce Type: new Abstract: As large language models (LLMs) continue to scale, it becomes increasingly challenging to grow model capacity under fixed computation budgets. We propos
arXiv:2606.10794v1 Announce Type: new Abstract: As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model
arXiv:2606.09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the
arXiv:2601.02424v2 Announce Type: replace-cross Abstract: The synthesis of nanocrystals has been highly dependent on trial-and-error, due to the complex correlation between synthesis parameters and ph
arXiv:2606.08327v1 Announce Type: cross Abstract: Standard transformers apply self-attention uniformly at every layer and token, regardless of whether the input requires dynamic cross-token interactio
arXiv:2606.09605v1 Announce Type: new Abstract: Foundation models offer a promising route to compress multi-modal physiological signals into compact representations of human health, with broad applica
arXiv:2606.07550v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-er
arXiv:2606.07404v1 Announce Type: new Abstract: This paper reports on training a hundred-billion-parameter sparse mixture of experts on a single eight-GPU node, end to end. LightningLM 0.1V is a recur
arXiv:2601.21162v2 Announce Type: replace-cross Abstract: Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing
arXiv:2606.06311v1 Announce Type: new Abstract: Accurate vessel trajectory prediction is essential for safe and efficient maritime operations, enabling collision avoidance and supporting route optimiz
arXiv:2606.05633v1 Announce Type: new Abstract: Retrieval-augmented QA pipelines often route retrieved passages through an LLM rewriter before a smaller reader, lifting F1 by tens of points on multi-h
arXiv:2606.05654v1 Announce Type: cross Abstract: Hate moderation is often evaluated as classification on clean English inputs, but deployed systems must route content to actions such as ALLOW, FLAG,
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialize
arXiv:2510.15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke. We hyp
arXiv:2606.04160v1 Announce Type: new Abstract: Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse to respond to harmful or disallowed r
arXiv:2606.05145v1 Announce Type: cross Abstract: When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, a
arXiv:2606.02939v1 Announce Type: new Abstract: Interpretable brain-computer interface classifiers that generalize across subjects without calibration remain an open challenge. We test whether prototy
arXiv:2606.03780v1 Announce Type: new Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to l
arXiv:2606.03968v1 Announce Type: cross Abstract: Rubric-based RL is a promising route for extending reinforcement learning beyond verifiable rewards, yet existing methods optimize rubrics while treat
At Google Cloud Next, we announced the preview of graph algorithms with Spanner Graph, bringing Google Research’s state-of-the-art graph mining capabilities natively to your database. These graph inte
arXiv:2606.00988v1 Announce Type: new Abstract: Symbolic regression (SR) offers a route to scientific discovery by converting observations into interpretable governing equations. However, despite its