Order-based Rehearsal Learning
arXiv:2605.04955v1 Announce Type: new Abstract: When a machine learning (ML) model forecasts an undesired event, one often seeks a decision to avoid it, known as the avoiding undesired future (AUF) pr
Knowledge catalogue
arXiv:2605.04955v1 Announce Type: new Abstract: When a machine learning (ML) model forecasts an undesired event, one often seeks a decision to avoid it, known as the avoiding undesired future (AUF) pr
arXiv:2605.05084v1 Announce Type: new Abstract: Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this b
arXiv:2605.04738v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption
Our new voice models are now available in the Realtime API: 🎙️ GPT-Realtime-2: Build production-ready voice agents that can think harder, take action, handle interruptions, and keep conversations flow
Over 450 remote villages across the island nation of Timor-Leste in Southeast Asia now have high-speed internet access thanks to SpaceX’s @Starlink, helping expand digital government services, educati
arXiv:2506.07548v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most meth
In this post, you will learn how to implement reinforcement learning with verifiable rewards (RLVR) to introduce verification and transparency into reward signals to improve training performance. This
arXiv:2602.12095v3 Announce Type: replace Abstract: The automation of warehouse operations is crucial for improving productivity and reducing human exposure to hazardous environments. One operation fr
arXiv:2605.03143v1 Announce Type: cross Abstract: Recent advances in large language models have led to the rise of software systems (i.e. agents) that execute with increasing autonomy on behalf of use
arXiv:2605.04838v1 Announce Type: cross Abstract: The standard constraint-based paradigm for causal discovery with incomplete data -- impute first, test second -- is frequently miscalibrated: any cons
arXiv:2605.04665v1 Announce Type: new Abstract: When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that th
Pareidolia, but for text. Apophenia, but for latent spaces. Its no wonder that our relationship to LLMs is so confusing. It's hard enough to resist apophenia in normal life, in such high dimensional l
Parloa, an AI company, has developed service agents powered by OpenAI's technology that are designed to provide natural, conversational customer interactions. These agents aim to improve customer expe
people are really starting to use voice to interact with AI, especially when they have a lot of context to dump. GPT-Realtime-2 comes to the API today; it is a pretty big step forward. (we are working
arXiv:2509.24943v2 Announce Type: replace Abstract: Long videos, characterized by temporal complexity and sparse task-relevant information, pose significant reasoning challenges for AI systems. Althou
Personal Computer is built for the Mac ecosystem, so you can manage it from anywhere. Start tasks from your iPhone with local files on your Mac. Add a Mac mini for full continuity and always-on agents
Personal Computer is now available to all users in a new Perplexity Mac app. Personal Computer is an advanced version of Perplexity Computer. It operates on any Mac, running tasks across your local fi
arXiv:2601.00020v3 Announce Type: replace-cross Abstract: Electroencephalography (EEG)-based brain-computer interfaces (BCIs) are strongly affected by non-stationary neural signals that vary across se
arXiv:2605.04344v1 Announce Type: cross Abstract: We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction base
arXiv:2603.22844v4 Announce Type: replace Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-b
arXiv:2605.05163v1 Announce Type: new Abstract: Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on
arXiv:2605.04675v1 Announce Type: new Abstract: Visible-thermal (RGB-T) object detection is a crucial technology for applications such as autonomous driving, where multimodal fusion enhances performan
arXiv:2605.04003v1 Announce Type: cross Abstract: High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledg
arXiv:2605.04247v1 Announce Type: new Abstract: The Linear Mixing Model (LMM) dominates spectral unmixing for its simplicity, but fails under multiple scattering; existing nonlinear models compensate
arXiv:2605.05120v1 Announce Type: new Abstract: An interpretable and scalable framework for decoding driving behaviors from multimodal physiological signals is proposed in this study. We utilize multi
Cursor, an AI code editor, introduced a feature allowing users to pin frequently-used skills or commands as quick-action pills for faster access within the interface. This enhancement improves workflo
arXiv:2605.05049v1 Announce Type: cross Abstract: Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE mo
arXiv:2511.16567v3 Announce Type: replace Abstract: In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordi
arXiv:2506.00886v3 Announce Type: replace Abstract: As large language models evolve into tool-augmented agents, a central question remains unresolved: when is external tool use actually justified? Exi
arXiv:2605.05017v1 Announce Type: cross Abstract: Embodied AI (EAI) systems are rapidly transitioning from simulations into real-world domestic and other sensitive environments. However, recent EAI so
arXiv:2605.04127v1 Announce Type: cross Abstract: Model collapse, the degradation in performance that arises when generative models are trained on the outputs of prior models, is an increasing concern
arXiv:2502.12370v3 Announce Type: replace Abstract: Recent advancements in transformer-based models have greatly improved time series analysis, providing robust solutions for tasks such as forecasting
arXiv:2605.04542v1 Announce Type: new Abstract: Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, dist
AI will help build the energy it needs. That’s the case U.S. Energy Secretary Chris Wright and NVIDIA Vice President of Hyperscale and High-Performance Computing Ian Buck made Thursday morning at the
arXiv:2605.04564v1 Announce Type: new Abstract: The representativeness of synthetic pre-crash scenarios is crucial for assessing the safety impact of Driving Automation Systems through virtual simulat
arXiv:2605.04215v1 Announce Type: new Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead t
arXiv:2605.04510v1 Announce Type: cross Abstract: Intense wildfire seasons require critical prioritization decisions to allocate scarce suppression resources over a dispersed geographical area. This p
arXiv:2605.05040v1 Announce Type: new Abstract: On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a st
arXiv:2601.06839v2 Announce Type: replace Abstract: We present PRISM, a novel color-guided stratified sampling method for RGB-LiDAR point clouds. Our approach is motivated by the observation that uniq
arXiv:2504.10808v3 Announce Type: replace Abstract: Detecting empathy from video interactions has emerging applications, yet raw videos that could be used for training AI models are rarely available d
arXiv:2605.04286v1 Announce Type: new Abstract: Climate classification plays a vital role in agricultural planning, hydrological studies, and climate science. One of the most widely used systems for c
arXiv:2605.04352v1 Announce Type: new Abstract: We introduce a benchmark suite for evaluating structural mathematical reasoning in language models, built on subgroup-construction problems in SL(3, Z)
arXiv:2601.09195v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional S
arXiv:2605.03546v1 Announce Type: cross Abstract: Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain,
arXiv:2605.03101v1 Announce Type: new Abstract: Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scient
arXiv:2601.14180v3 Announce Type: replace Abstract: Self-supervised learning has been increasingly investigated for low-dose computed tomography (LDCT) image denoising, as it alleviates the dependence
arXiv:2510.25224v3 Announce Type: replace Abstract: While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that c
arXiv:2605.05027v1 Announce Type: new Abstract: Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from s
arXiv:2605.05081v1 Announce Type: new Abstract: We consider the stabilization of Vlasov--Poisson plasma dynamics, a central control problem in nuclear fusion. Our focus is the gap between what an idea
arXiv:2508.00091v3 Announce Type: replace-cross Abstract: The problem of recovering the configuration of points from their partial pairwise distances, referred to as the Euclidean Distance Matrix Comp
arXiv:2605.05093v1 Announce Type: cross Abstract: Regularization is often used in high-dimensional regression settings to generate a sparse model, which can save tremendous computing resources and ide
arXiv:2605.05159v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fin
This article argues for democratizing public health data analytics by making intelligence and insights accessible to non-technical public health professionals without requiring specialized data scienc
arXiv:2505.18466v2 Announce Type: replace Abstract: Evaluations of Large Language Models (LLMs) often overlook intersectional and culturally specific biases, particularly in underrepresented multiling
arXiv:2605.03884v1 Announce Type: new Abstract: Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-pr
arXiv:2605.04844v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an advanced technique for real-time novel view synthesis by representing scene geometry and appearance using
arXiv:2605.04497v1 Announce Type: new Abstract: Shapley values are a standard tool for explaining predictions of tree ensembles, with Path-Dependent SHAP being the most widely used variant. Despite su
arXiv:2604.03976v2 Announce Type: replace Abstract: Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI syste
arXiv:2605.04847v1 Announce Type: new Abstract: Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings
This discussion examines the practical performance gains of quantization techniques when deployed in production environments, particularly addressing whether theoretical speedups translate to real-wor