Saturday, 14 November 2026
This dated roundup collects the most interesting AI and technology developments found for Saturday, 14 November 2026.
industry-media
Gradio’s NeurIPS challenge asks AI agents to show their work
Gradio’s paper-reproduction challenge runs November 20–December 5, with a five-paper limit and registration closing November 19.
Read more‘Stand with Jensen’ letter is ‘amateur hour,’ @lulumeservey says
@lulumeservey says the letter’s signature pages include names such as Xi Jinping and Jeffrey Epstein.
Read moreMuse announces Poppy 1.0, an open standard for personal agents to work with businesses
Muse says a poppy.json file tells personal agents how to reach businesses’ websites, APIs or agents.
Read moreresearch-feed
Solving Witness Triangle Puzzles Faster with an Automatically Learned Predicate
arXiv:2308.02666v2 Announce Type: replace Abstract: The Witness is a game with combinatorial puzzles that are challenging for both human players and AI solvers. Search-based AI solvers can require large amounts of time to solve such puzzles. We accelerate search by automatically learning a predicate that predicts whether a partial path to a Witness puzzle is completable to a solution path. We demonstrate that our learned predicate is human-explainable, which makes it amenable to proofs, and we prove a key property that allows us to use it for pruning successor states in search. Doing so accelerates search by about six times while maintaining search completeness. Conversely, given a fixed tim
Read moreApproximate and Weighted Data Reconstruction Attack in Federated Learning
arXiv:2308.06822v4 Announce Type: replace-cross Abstract: Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data. Although FL is considered privacy-preserved by design, recent data reconstruction attacks demonstrate that an attacker can recover clients' training data based on the parameters shared in FL. However, most existing methods fail to attack the most widely used horizontal Federated Averaging (FedAvg) scenario, where clients share model parameters after multiple local training steps. To tackle this issue, we propose an interpolation-based approximation method, whic
Read moreDataCook: Exploring Anti-Adversarial Fingerprints for Healthcare Data Usage Control
arXiv:2403.17755v2 Announce Type: replace Abstract: Purpose: Healthcare AI increasingly relies on high-quality datasets, yet medical data are scarce, costly to curate, and tightly regulated in terms of data access. More critically, once medical data are leaked or accessed without authorization, data owners have limited means to prevent such data from being used to train and deploy downstream models. To address this gap, we propose DataCook, a deployment-stage usage-control framework based on anti-adversarial fingerprints. Materials and Methods: Specifically, DataCook transforms raw samples through a private cooking procedure that embeds anti-adversarial fingerprints. Models trained on the co
Read moreMoralBench: Moral Evaluation of LLMs
arXiv:2406.04428v3 Announce Type: replace-cross Abstract: In the rapidly evolving field of artificial intelligence, large language models (LLMs) have emerged as powerful tools for a myriad of applications, from natural language processing to decision-making support systems. However, as these models become increasingly integrated into societal frameworks, the imperative to ensure they operate within ethical and moral boundaries has never been more critical. This paper introduces a novel benchmark designed to measure and compare the moral reasoning capabilities of LLMs. We present the first comprehensive dataset specifically curated to probe the moral dimensions of LLM outputs, addressing a wi
Read moreA hybrid FEM-PINN method for time-dependent partial differential equations
arXiv:2409.02810v2 Announce Type: replace-cross Abstract: In this work, we present a hybrid numerical method for solving evolution partial differential equations (PDEs) by merging the time finite element method with deep neural networks. In contrast to the conventional deep learning-based formulation where the neural network is defined on a spatiotemporal domain, our methodology utilizes finite element basis functions in the time direction where the space-dependent coefficients are defined as the output of a neural network. We then apply the Galerkin or collocation projection in the time direction to obtain a system of PDEs for the space-dependent coefficients which is approximated in the fr
Read moreFACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition
arXiv:2503.18998v2 Announce Type: replace-cross Abstract: Cross-subject EEG emotion recognition is challenged by significant inter-subject variability and intricately entangled intra-subject variability. Existing works have primarily addressed these challenges through domain adaptation or generalization strategies. However, they typically require extensive target subject data or demonstrate limited generalization performance to unseen subjects. Recent few-shot learning paradigms attempt to address these limitations but often encounter catastrophic overfitting during subject-specific adaptation with limited samples. This article introduces the few-shot adapter with a cross-view fusion method
Read moreShannon observables: A scalable approach to information decomposition
arXiv:2504.15779v2 Announce Type: replace-cross Abstract: Distributed systems, such as biological and artificial neural networks, process information via complex interactions engaging multiple subsystems, resulting in high-order structure of the information within the system with distinct properties across scales. Investigating how these systems process information remains challenging due to difficulties in defining appropriate multivariate metrics and ensuring their scalability to large systems. To address these challenges, we introduce a novel framework based on what we call "Shannon observables": quantities that capture essential properties of high-order information processing, yet can be
Read moreSilent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming
arXiv:2505.01584v5 Announce Type: replace-cross Abstract: Adaptive video streaming optimizes Quality of Experience (QoE) metrics by selecting appropriate bitrates according to varying network bandwidth and user demands. In practice, however, real-world network bandwidth often exhibits heterogeneity relative to training environments. Current methods predominantly tackle this problem through learning-based approaches designed to improve generalization performance. Our systematic investigation reveals a critical limitation: neural networks suffer from plasticity loss, significantly impeding their ability to adapt to heterogeneous network conditions. Through theoretical analysis of neural propag
Read moreOPA-Pack: Object-Property-Aware Robotic Bin Packing
arXiv:2505.13339v2 Announce Type: replace-cross Abstract: Robotic bin packing is a fundamental manipulation problem with broad applications in e-commerce and warehouse automation. However, existing methods primarily focus on object geometry to optimize packing compactness without explicitly modeling object properties such as fragility, edibility, and chemical compatibility that humans typically consider during packing. This paper presents OPA-Pack (Object-Property-Aware Packing), a framework that incorporates object-property information into robotic bin-packing planning. The framework includes an object property recognition scheme based on retrieval-augmented generation and chain-of-thought
Read moreSpecification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks
arXiv:2506.15253v3 Announce Type: replace-cross Abstract: As large language model (LLM) agents are increasingly deployed in long-horizon unattended scenarios, security evaluation of them before deployment becomes increasingly essential and challenging. Existing evaluation methods mainly follow the paradigms of LLM-as-a-Judge or Agent-as-a-Judge. However, such judges are themselves often vulnerable to hallucination and can even be affected by perturbations. Furthermore, because capturing full environment states at every step is often prohibitively expensive in open-ended environments, existing evaluations typically rely on textual logs and the final environment state. As a result, they may mi
Read moreLilith: Developmental Modular LLMs with Chemical Signaling
arXiv:2507.04575v2 Announce Type: replace-cross Abstract: Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical signaling may be a productive step toward understanding the emergence of consciousness. We propose LILITH, a novel architecture that combines developmental training of modular language models with brain-inspired token-based communication protocols, mirroring chemical signaling in the brain. Our approach models distinct brain regions as specialized LLM modules including thinking, memory, sensory, and regulatory components t
Read moreLet's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
arXiv:2507.11662v4 Announce Type: replace Abstract: Verifiers--functions assigning rewards to agent behavior--have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria (e.g., computer use) remains a challenge: while humans can recognize desired outcomes, translating this intuition into scalable rules is nontrivial. Multimodal LLMs (MLLMs) offer a promising solution, given their world knowledge, human-preference alignment, and reasoning skills. We evaluate MLLM verifiers across web navigation, computer use, and robotics, spanning 13 models, 28 judge designs, diverse agent trajectories, and distinct downstream applications. We
Read more