AI News Archive: August 19, 2026 — Part 19
Sourced from 500+ daily AI sources, scored by relevance.
- Multi-Agent Off-Policy Deep Reinforcement Learning for Smart Campus Coverage
Deep reinforcement learning (DRL) has recently gained a great attention due to its real-time adaptation and effectiveness in complex optimization problems. This paper investigates the optimal deployment of millimeter-wave (mmWave) base stations (BSs) in a realistic, non-convex campus topology. The o...
- Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference
Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose che...
- Lost in Aggregation: How Benchmarks Overlook Irreplaceable Model Strengths
Tabular machine learning benchmarks typically summarize performance by averaging scores, ranks, or pairwise wins across datasets. Such aggregates are useful for selecting robust default models, but they can obscure a different question: which models are necessary to attain peak performance on partic...
- Converting Expert Deliberation into Financial Signals Through A Context-Aware NLP Pipeline
We introduce the CDSP (context-conditional deliberation signal pipeline), converting an investment committee's meeting transcripts into structured predictive features. CDSP segments the meeting transcripts into topical chunks, assigns asset-class context labels using a large language model (LLM), ma...
- Quantum Tensor Network Learning with DMRG
Tensor Networks are a relatively new machine learning approach. The architectures proposed initially are inspired by approaches from quantum many-body physics simulations. One common layout is the matrix product state (MPS) also known as a tensor train optimized with gradient descent techniques. We ...
- GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models
Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework tha...
- A Unifying Relational Perspective on Expressive Lottery Tickets
Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is poorly understood. The Strong Expressive Lottery Ticket Hypothesis (SELTH) posits the existence of sparse GNNs that preserve Weisfeiler-Leman (WL) ...
- LabDex: A Hierarchical Benchmark for Dexterous Manipulation in Laboratories
Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instruments and execute long-horizon, state-dependent experimental procedures. Yet existing benchmarks do not jointly capture de...
- Many Optimizers But Only One Training Path: Repeated Resampling for Adaptive Optimizer Selection
An optimizer is usually chosen before training a deep neural network and then kept fixed. Treating optimizer choice as a hyperparameter could boost performance, but it requires several complete training runs and discards all but the winner. Repeated Optimizer Resampling (ROR) instead searches during...
- Forgetting, plasticity, and co-observation: a third facet of continual learning
Efficient continual learning remains a fundamental challenge for deep neural networks. While catastrophic forgetting and loss of plasticity are widely considered the primary obstacles to overcome, we show that these two issues cannot fully explain the performance gap between naive sequential trainin...
- GraphK: Variable-Size Graph Generation with Efficient Edge Construction
Graph generation models have advanced significantly with deep learning, yet they remain limited in scalability, flexibility, and ability to model underlying structures. We present GraphK, a novel encoder-sampler-decoder framework for graph generation that overcomes these challenges through structura...
- Lévy Attention: Single-Pass Predictive Uncertainty for Continuous-Time Attention
Deep models for irregularly-sampled time series answer queries at arbitrary continuous timestamps, yet report nothing about how far each answer should be trusted. We show the attention layer itself can close that gap: with the right stochastic formulation, the pass that makes each prediction also re...
- Geometric Iterative Retrieval for Neural Audio Codec Resynthesis
Neural audio codecs based on Residual Vector Quantization (RVQ) have become the dominant discrete representation for token-based general audio generation, yet resynthesizing high-quality audio from coarse codec tokens remains an open problem and bounds the fidelity of every system that generates the...
- SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval
Accurate visual decoding can reveal how the brain represents visual information and recover perceived content from neural signals such as electroencephalography (EEG), with potential for neural communication. However, current EEG-to-image retrieval methods perform far below their within-subject coun...
- Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval
Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulu...
- Does Mapping Non-Maximal Probabilities to GMM Components Matter for S-JEPA Encoder Representations?
S-JEPA uses soft Gaussian mixture model (GMM) posteriors instead of hard cluster labels to preserve uncertainty. It remains unclear whether the probability values alone are sufficient, or whether it also matters which GMM components receive the non-maximal probabilities. We test this with two matche...
- Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification
The empirical success of diffusion models in generative modelling has motivated theoretical work, including quantitative error bounds and qualitative analyses that characterise the different phases of denoising. We bring these two areas together by studying the adaptivity of diffusion models to the ...
- Fuzzy Accuracy Compensates for Label Subjectivity in Classification of Skin Tone Using Wearable Photoplethysmography Signals
We consider the problem of classification of skin tone using photoplethysmography (PPG) signals with labels of the ordinal six-class Fitzpatrick skin tones. A typical accuracy for this task is a poor 40-55 %. However, the labels are subjectively determined by comparing the skin with a colour chart, ...
- Graph-Based Approaches to Learning Epileptogenic Zone Localization Using Stereo-EEG Recordings
The epileptogenic zone (EZ) is the brain region that generates seizures in an individual, and is the target of epilepsy surgery. Localizing the EZ from stereo-EEG (sEEG) recordings supports surgical planning, but manual interpretation is time-consuming and focuses on seizure recordings. Graphical le...
- Sharper Regret Bounds for Time-Varying Gaussian Process Bandits with Constant Exploration
We study Bayesian optimization in a time-varying environment where the unknown reward function evolves according to a Gaussian process drift model. Existing GP-UCB analyses in this setting typically require the exploration parameter to grow with the horizon to maintain uniform confidence bounds. Usi...
- Multi-stage neural operator learning with application for convolutions
Convolution integrals widely exist in applications, and to enable fast and accurate computations, this paper introduces two general multi-stage neural operator learning frameworks. The first, Deep Collocation Neural Operator (DCNO), is a supervised approach that iteratively refines the operator appr...
- A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs
Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each device. By installing a single meter that measures a building's total electricity consumption, NILM algorithms can determine the ac...
- To Go Far, Go Together: Diverse Preferences Induce a Curriculum for Reward Optimization
Learning a reward model from human feedback and optimizing a policy against it is one approach to aligning AI systems with individual users. From a fairness perspective, existing work improves such alignment by developing data-efficient and accurate reward models that capture minority preferences de...
- Vois 2.0
The ElevenLabs alternative with unlimited generation
- PartialBiGrasp: Inferring Hidden Local Geometry for Bimanual Grasping from Partial Views
Dual-arm robotic grasping is essential for manipulating large, heavy, and geometrically complex objects that cannot be reliably handled using a single manipulator. These large objects often contain only sparse graspable regions determined by local geometric properties such as thickness, edge structu...
- RoboEdit: Turning Human Manipulation Videos into Scalable Robot Experience
Collecting robot hand-object interaction data is costly and embodiment-specific, yet abundant human-object videos remain unusable for robot training. We present RoboEdit, a human-to-robot video editing suite that transforms human manipulation videos into action-consistent, physically plausible robot...
- Dream2Reward: Transition-Alignment Reward Models from Positive Demonstrations for Robotic Manipulation
Learning robotic policies requires dense rewards that remain informative when behavior departs from successful demonstrations. Progress-based rewards estimate how far an observation has advanced along a nominal successful trajectory, but may remain high after an incorrect transition. We introduce Dr...
- Engineering Psychological Safety in Autonomous Vehicles: A Systems-Theoretic Framework for Psychological Safety in Autonomous Vehicles and its Validation in Real-World Scenarios
Despite rapid technological advances, the societal acceptability of autonomous vehicles (AVs) remains limited by psychological barriers that extend beyond traditional concerns of physical safety. While factors such as trust and perceived safety are known to influence user acceptance, there is a lack...
- SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation
Physical interaction quality is central to deformable-object manipulation, yet most benchmarks evaluate task success alone. A policy may complete the task while allowing slip or causing excessive compression. A primary bottleneck is the absence of visuo-tactile datasets that pair policy-visible cont...
- Orienteering Problem with Uncertain Time-Varying Rewards: Framework and Benchmark for Everyday Service Robotics
We present the orienteering problem with uncertain time-varying rewards (OP-UTVR), a novel variant of the orienteering problem (OP). While most existing OP formulations assume rewards to be known in advance, practical applications involve uncertain and time-varying rewards, as with shifting customer...
- Progressive Experience Fusion for Multi-Task World Model Control in Endovascular Navigation
Autonomous endovascular navigation could support the delivery of mechanical thrombectomy to underserved areas, but controllers must navigate long, multi-stage paths across varying vascular anatomies. This study investigates Progressive Experience Fusion (PEF) to train a multi-task TD-MPC2 controller...
- Evaluation of Monocular SLAM Systems on High-Altitude Nadir UAV Footage
Aerial nadir video combines weak geometric constraints with severe perceptual aliasing, making it a difficult regime for monocular SLAM. We benchmark five monocular SLAM systems on local UAV flights, synthetic city-scale imagery, and long-range aerial sequences. To isolate visual performance, we pro...
- Payload Swing Estimation and Damping Without Payload Parameters for Multirotor UAVs
Cable-suspended payload transport by multirotor UAVs is flexible but generates periodic swing disturbance that degrades tracking and risks instability. Existing anti-swing methods require additional sensors or precise identification of cable length and payload mass, limiting field deployment. We pro...
- The Role of Grid Cells in Reducing Spatial Aliasing in Hippocampal Place Representations
Spatial aliasing occurs when two or more distinct locations produce highly similar place-cell representations, primarily due to environmental symmetry or repetitive structures. This issue is most pronounced when place representations are constructed solely from boundary vector cell (BVC) inputs, bec...
- Real-Time Control-Constrained DDP for Underactuated Balancing of Legged Robots
This paper presents a real-time control-constrained Differential Dynamic Programming (DDP) framework for underactuated legged robots. To address the limitation of classical DDP in handling control constraints, we propose an Accelerated Projected Gradient (APG)-based control-constrained DDP (ABC-DDP)...
- An Experimental Study of Downwash Effects on a Continuum Manipulator Integrated with a Multirotor UAV
Continuum arm aerial manipulation systems leverage soft-manipulator compliance and dexterity for tasks in confined or hazardous environments, but propeller downwash can degrade performance, particularly near walls and the ground. This effect remains uncharacterized for continuum manipulators. This l...
- Designing Social Robots for Social-Cognition Training with Autistic Adults
Social robots have been widely explored as tools for autism intervention, yet this literature has focused predominantly on children and has rarely involved autistic adults as active contributors to design. This creates a mismatch between existing systems and the social-cognitive challenges autistic ...
- DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model
Existing visual navigation models often aim to develop foundation models that can generalize robot navigation across diverse platforms. However, many of these models are prone to collisions when deployed in complex indoor environments, particularly in structured layouts and narrow passages. To addre...
- The Embodiment Gap in Robot Foundation Models
Robot foundation models (RFMs), including vision-language-action (VLA) policies, are often discussed through a scaling view: more data, larger models, and broader benchmarks should improve generalization. In robotics, however, a model can generalize while work still remains before it can run on a ro...
- Function-On-Function Regression Through Separable Neural Operators
This paper investigates the estimation of the regression operator in function-on-function regression models. While traditional research has predominantly focused on linear models or their immediate nonlinear extensions, we propose a neural operator approach to accommodate general regression operator...
- Scalable Amortized Variational Inference for Non-Poisson Buy-'Til-You-Die Models
Despite the wide variety of existing Buy-`Til-You-Die (BTYD) models, nearly all rely upon the convenient assumption of transactions following a Poisson process. As modern customer bases grow larger and more diverse, a major gap in the marketing literature is BTYD models that can account for heteroge...
- Astute
Automate your B2B brand going viral, with new media creators
- Clipto MCP
Let agents source clips from terabytes of your local video
- Origin by Cursor
The Git forge built for the age of coding agents
- Claude Watermark Remover
Find and remove every trace AI leaves in your text
- Hosted Agents in Cluing
Collaborative agents who build, learn and publish in 1 place
- Expert Chase 2.0
Where human life runs with AI
- Paper Critters
Kid friendly paper toys, free to decorate and COPPA safe.
- Fairphone Gen 6+
A modular phone built to last through 2033
- OmniVibe
Marketplace for agent creators & users