Knowledge catalogue
Crusoe AI Talks returns to SF. Wed Oct. 7: Join @ollama's @jmorgan and @TrajectoryLabs' @MichaelElabd for a candid conversation with Crusoe's Erwan Menard on how the calculus is shifting as closed and
arXiv:2610.00859v1 Announce Type: new Abstract: World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video si
arXiv:2610.00680v1 Announce Type: cross Abstract: Curvature is often treated as an intrinsic property of a representation, although its empirical effect also depends on coordinate scale, learned logit
arXiv:2610.00961v1 Announce Type: new Abstract: As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a
arXiv:2610.01096v1 Announce Type: cross Abstract: A post-hoc out-of-distribution (OOD) detector reads the activations of a trained classifier and returns a score. It fits that score on in-distribution
arXiv:2610.01306v1 Announce Type: new Abstract: Professional work often starts with a brief request that leaves the professional to work out what is needed, which documents matter, and whether the req
arXiv:2610.01815v1 Announce Type: new Abstract: Although diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their ge
arXiv:2610.00208v1 Announce Type: cross Abstract: This paper studies decentralized safe path following for multiple quadrotors on intersecting paths, where safety requires both collision avoidance and
Decision models in llama.cpp are now available The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open
arXiv:2610.01513v1 Announce Type: new Abstract: Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited
arXiv:2610.02185v1 Announce Type: new Abstract: Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate represe
arXiv:2610.00302v1 Announce Type: cross Abstract: Crowdsourced imagery provides timely, fine-grained, street-level observations for disaster mapping, complementing conventional remote sensing imagery
arXiv:2610.01914v1 Announce Type: new Abstract: Decompositional scene reconstruction aims to reconstruct high-quality objects and background, yet existing methods still struggle with the level of qual
arXiv:2610.00363v1 Announce Type: cross Abstract: Ensuring safe and reliable operation of modern railway systems increasingly relies on data-driven monitoring and intelligent fault detection. Deep lea
arXiv:2506.11641v2 Announce Type: replace-cross Abstract: Deep autoencoders have become a fundamental tool in various machine learning applications, ranging from dimensionality reduction and reduced o
arXiv:2610.00368v1 Announce Type: cross Abstract: World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computatio
arXiv:2610.01256v1 Announce Type: new Abstract: Errors in LLM agent executions and their visible consequences can be separated by many steps, making decisive-error localization a matter of understandi
arXiv:2610.01361v1 Announce Type: cross Abstract: Multilayer networks allow the modeling of interactions between the same entities across different contexts, such as temporal observations, varying set
arXiv:2610.00499v1 Announce Type: new Abstract: As diffusion large language models (dLLMs) become more capable, they are moving from research settings to real-world extit{serving}, where request manag
arXiv:2610.00371v1 Announce Type: cross Abstract: Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creat
arXiv:2610.01207v1 Announce Type: new Abstract: When training large language models with reinforcement learning, terminal rewards provide little guidance about which steps matter. Common methods for a
arXiv:2610.01749v1 Announce Type: cross Abstract: Topological Data Analysis (TDA) offers novel methods for understanding temporal dynamics in complex systems, yet its application in information system
How quickly things change in the artificial intelligence era. Just a few months after everyone was scrambling to infuse AI into every enterprise operation — and frankly they still are, as agents have
arXiv:2610.01168v1 Announce Type: cross Abstract: Time Series Anomaly Detection has received increasing attention, driven by the growing availability of complex time series data. This surge has led to
arXiv:2610.01847v1 Announce Type: cross Abstract: Model specifications define how large language models (LLMs) should behave, guiding alignment training, inference-time behavior, and evaluation. Yet t
arXiv:2610.00360v1 Announce Type: cross Abstract: Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise th
arXiv:2610.02044v1 Announce Type: new Abstract: Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line o
arXiv:2610.00359v1 Announce Type: cross Abstract: Diffusion models with prompt and reference image-guided editing have seen rapid progress, yet they remain too coarse for pixel-level control. One prom
arXiv:2610.00582v1 Announce Type: new Abstract: Aesthetic image cropping aims to identify the optimal crop of an image in terms of aesthetics and composition. While supervision based on annotated data
arXiv:2610.01355v1 Announce Type: cross Abstract: We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete W
arXiv:2610.01435v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong predictive performance through in-context learning, yet repeatedly conditioning on labeled data makes in
arXiv:2610.00997v1 Announce Type: cross Abstract: Knowledge distillation aims to transfer the factual knowledge of large language models to smaller models for efficient deployment. Yet a teacher may r
arXiv:2602.03006v3 Announce Type: replace Abstract: Deploying Large Language Models (LLMs) for discriminative workloads is often limited by inference latency, compute, and API costs at scale. Active d
arXiv:2610.02043v1 Announce Type: cross Abstract: Schrodinger bridge (SB) learns stochastic transport between prescribed initial and target distributions. When the initial distribution shifts at test
arXiv:2610.00781v1 Announce Type: new Abstract: Teleoperated demonstrations are a primary source of data for robot manipulation, and teleoperated interventions are a primary mechanism for correcting p
arXiv:2610.01661v1 Announce Type: new Abstract: Despite remarkable progress, video generation models often produce highly similar outputs when repeatedly sampled from the same prompt, limiting their u
arXiv:2610.00982v1 Announce Type: cross Abstract: Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the actio
arXiv:2610.02188v1 Announce Type: cross Abstract: Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it m
arXiv:2610.00415v1 Announce Type: new Abstract: Machine-learning surrogates accelerate physical simulation, but lower prediction error need not coincide with lower error in physically relevant flow st
arXiv:2610.01670v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly used as automated judges for instruction-based image editing and as reward signals for model t
arXiv:2603.18480v2 Announce Type: replace-cross Abstract: Inferring human engagement from gameplay video is important for game design and player-experience research, yet it remains unclear whether vis
arXiv:2610.01955v1 Announce Type: new Abstract: Outcome-based reinforcement learning can train language models to forecast real-world events, but prior forecasting work either freezes research context
arXiv:2610.00542v1 Announce Type: new Abstract: Continual imitation learning evaluates whether a robot can learn new knowledge without forgetting previously learned skills. However, retaining task per
arXiv:2610.01133v1 Announce Type: cross Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield
arXiv:2610.00030v1 Announce Type: new Abstract: Object detection models often experience performance degradation when deployed under distribution shifts, caused by for example changes in weather type,
arXiv:2610.00861v1 Announce Type: cross Abstract: Adversarial optimization under a shared ell_1 budget requires deciding not only how much perturbation to use, but also where that limited budget shoul
arXiv:2610.00097v1 Announce Type: new Abstract: Recent diffusion and autoregressive models have substantially improved text-to-video generation, yet producing coherent long-form story videos with cons
arXiv:2610.01439v1 Announce Type: new Abstract: Parallel drafting reduces the drafting overhead of speculative decoding for large language models (LLMs), but its gains remain limited by the accepted p
arXiv:2610.00317v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control. While chunk-
arXiv:2610.00040v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation mod
arXiv:2610.02161v1 Announce Type: cross Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) have recently driven rapid progress in general-purpose robots, yet most progres
arXiv:2610.00316v1 Announce Type: cross Abstract: Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored. We
arXiv:2606.19483v2 Announce Type: replace Abstract: Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object reco
arXiv:2610.01286v1 Announce Type: new Abstract: Recent depth foundation models like Depth Anything 3 (DA3) achieve remarkable multi-view depth estimation but assume static 3D scenes, limiting their ap
arXiv:2601.22153v2 Announce Type: replace-cross Abstract: Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models. Although recent VLAs generalize well in static
arXiv:2512.03068v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) systems increasingly shape consequential decisions, creating value but also potential harms for individuals, soci
arXiv:2610.00412v1 Announce Type: new Abstract: KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reco
arXiv:2610.00801v1 Announce Type: new Abstract: A robot may lose sight of an object it must later retrieve, need to recall what a person demonstrated earlier, or track which steps of a task it has alr
arXiv:2610.02175v1 Announce Type: new Abstract: Protein function annotation needs to know which predictions to distrust, not only what a model predicts. We ask whether tissue-specific interaction stru
arXiv:2602.15396v2 Announce Type: replace Abstract: Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces ind