Kepler: Auditable World Models for ARC-AGI-3
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source h
Knowledge catalogue
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source h
arXiv:2610.01317v1 Announce Type: new Abstract: Evaluating candidate architectures in neural architecture search (NAS) faces an inherent trade-off: on the one hand, reliable performance labels are lim
arXiv:2610.01320v1 Announce Type: new Abstract: Generative modeling has shown strong promise for multivariate time mseries (MTS) forecasting, especially scale to high-dimensional settings. Diffusion-b
arXiv:2610.01780v1 Announce Type: new Abstract: A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the
arXiv:2508.08882v5 Announce Type: replace Abstract: Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-int
arXiv:2610.00970v1 Announce Type: cross Abstract: Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has follo
arXiv:2610.01140v1 Announce Type: new Abstract: Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a tra
arXiv:2610.00031v1 Announce Type: new Abstract: Street-view imagery is increasingly used to infer urban attributes, but predictive accuracy alone does not reveal how much a photograph contributes beyo
arXiv:2610.00003v1 Announce Type: cross Abstract: Vision models pretrained for frame-level appearance often struggle to infer hidden physical properties from motion. We study center-of-mass (CoM) loca
arXiv:2610.00654v1 Announce Type: new Abstract: Personalization has long relied on customer data to infer what an individual is likely to value. We call this customer evidence: the customer's historic
arXiv:2603.01623v2 Announce Type: replace Abstract: Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference spee
arXiv:2609.39183v1 Announce Type: new Abstract: This paper studies extbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target
arXiv:2609.38962v1 Announce Type: new Abstract: Recent work on hallucination detection in large language models has shown that, for a fixed pre-trained model and reasoning task, it is possible to esti
AI agent infrastructure is evolving to support systems that move continuously among inference, feedback and training. Cognition AI Inc.’s Devin now assists throughout the software development lifecycl
arXiv:2609.40269v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static ob
arXiv:2606.13603v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individua
The Nvidia Deploy repository provides open‑source C++ samples that pair ONNX Runtime with the TensorRT RTX execution provider to accelerate local inference on Windows and Linux. It separates model exp
arXiv:2609.38356v1 Announce Type: new Abstract: Dynamical Systems Reconstruction (DSR) aims to infer models from observed time series that reproduce a system's qualitative long-term behavior. Continua
arXiv:2609.39390v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previ
arXiv:2609.38932v1 Announce Type: new Abstract: Surface electromyography (sEMG) provides a wearable, camera-free signal for continuous hand-motion inference. Mapping muscle activity to joint kinematic
arXiv:2609.39624v1 Announce Type: new Abstract: Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic ra
Hi everyone — I'm behind Autonomous Workday, and I'm sharing an English-language architecture walkthrough about building an event-driven workflow around local inference. The proposed flow separates fi
arXiv:2609.39128v1 Announce Type: new Abstract: Global video geo-localization aims to infer the geographic location of a video worldwide, evaluating performance across four geographic hierarchies: cit
arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, b
arXiv:2609.40170v1 Announce Type: new Abstract: MANETs enable flexible infrastructure-less wireless connectivity in dynamic and resource-constrained environments. As modern MANETs exploit multiple fre
arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SL
arXiv:2609.38289v1 Announce Type: cross Abstract: In personalized AI applications, such as conversational assistants and recommender systems, users interact not with models in isolation but with broad
arXiv:2609.40131v1 Announce Type: cross Abstract: Rank-constrained tensor neural networks reduce the parameterization of high-order inputs, but they do not explicitly constrain class geometry in the l
arXiv:2609.38672v1 Announce Type: cross Abstract: Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning i
arXiv:2609.39365v1 Announce Type: cross Abstract: Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are fle
arXiv:2609.39056v1 Announce Type: new Abstract: World-action models (WAMs) jointly generate future world states and actions through iterative denoising, using shared weights to process heterogeneous s
arXiv:2609.39034v1 Announce Type: cross Abstract: Designing expressive sequence layers with efficient inference remains a central challenge in modern machine learning. Standard softmax attention achie
arXiv:2609.39661v1 Announce Type: new Abstract: Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value ca
arXiv:2609.39343v1 Announce Type: new Abstract: Diffusion caching accelerates generation by replacing transformer computation with cached or predicted features at selected denoising steps. We introduc
arXiv:2609.39972v1 Announce Type: new Abstract: Speculative decoding accelerates language model inference by verifying multiple draft tokens in a single target-model pass. Recent parallel drafters hav
arXiv:2609.38420v1 Announce Type: cross Abstract: We introduce Type-6 logic, a variant of dynamic epistemic logic augmented with two operators (uncertainty and recurrence), designed to model the infer
arXiv:2609.39496v1 Announce Type: cross Abstract: Typed decision models such as Jev offer an efficient alternative to generative LLMs in decision-making workflows by selecting directly from predefined
arXiv:2609.38067v1 Announce Type: new Abstract: Scientific foundation models are commonly evaluated after heterogeneous physical problems have already been translated into a compatible gridded, tokeni
arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferring
arXiv:2609.36726v1 Announce Type: new Abstract: Can a scientific agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled benchma
arXiv:2609.37837v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly eli
Cognition is the first customer running @NVIDIA Vera Rubin, powered by @CoreWeave! Hopper in 2022. Blackwell in 2024. Now Vera Rubin: On SWE-2 inference, the new chips deliver about 4.8x more token th
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s
arXiv:2609.36099v1 Announce Type: new Abstract: Multi-step matching models, including flow and diffusion models, produce high-quality outputs but incur substantial inference costs and may reproduce un
arXiv:2609.37446v1 Announce Type: new Abstract: Supervised causal discovery learns to infer causal structure for a new dataset from training datasets paired with structural labels. These training pair
Generative recommender systems model recommendation as high‑cardinality event streams, turning user actions, context, and candidate items into tokens for sequence modeling over user behavior. NVIDIA’s
🪽DFlash draft models are available for Ornith-1.5 9B, 35B-A3B, and 397B. DFlash and Ornith 1.5 make a dynamic duo: DFlash performs as the draft model, accelerating inference by drafting multiple token
arXiv:2609.36472v1 Announce Type: new Abstract: Sequential Model-Based Optimization (SMBO) traditionally relies on Bayesian or ensembling surrogates for uncertainty quantification. While historically
arXiv:2609.37532v1 Announce Type: cross Abstract: Growing large language model applications demand efficient inference. At high concurrency, block-diffusion speculative decoding suffers from verificat
arXiv:2609.37551v1 Announce Type: cross Abstract: Emerging optical-network applications increasingly use received data for inference and control rather than exact source reproduction, creating an oppo
arXiv:2609.36202v1 Announce Type: new Abstract: Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time. Ho
arXiv:2609.37582v1 Announce Type: cross Abstract: Federated knowledge must remain usable by recipients with different modalities, private architectures, and tasks. We present FedSocket, which makes re
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation fr
I've been closely following the rise of the Strata inference engine and as someone with 28GB VRAM and 32GB RAM I'm itching to buy 32GB more RAM just to use Flash Next. But of course before I make such
arXiv:2609.36012v1 Announce Type: new Abstract: General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL)
arXiv:2609.38173v1 Announce Type: new Abstract: We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its
arXiv:2609.38166v1 Announce Type: cross Abstract: Recent LLMs increasingly adopt hybrid designs that replace standard attention with linear attention, such as Gated DeltaNet (GDN) and Kimi Delta Atten
arXiv:2609.37029v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The mo
arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the comput