Search: “safety”

Distributed Optimization with Streaming Data: A Temporal Weighting Perspective

arXiv:2608.09565v1 Announce Type: cross Abstract: Optimization theory is a widely used tool for intelligent decision-making. While classical optimization deals with fixed, time-invariant objective fun

Distribution-Free Conformal Prediction for Steel Fatigue Strength: Marginal Validity Is Not Enough

DGX agent

arXiv:2608.07589v1 Announce Type: cross Abstract: Predicting fatigue failure in steel components experimentally is costly because it requires testing across multiple compositions and processing condit

safetyarxiv-cs-lg

11 Aug 2026

DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology

arXiv:2608.08148v1 Announce Type: cross Abstract: Attention mechanisms have been widely utilized in modern deep learning, and many existing multi-omics models inherit their conventional use to allow u

DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models

arXiv:2608.09233v1 Announce Type: cross Abstract: Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-trai

DSLE: A Learning Environment for Dark Souls Boss Encounters

arXiv:2608.09902v1 Announce Type: new Abstract: We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered as game

EFFEKT: Efficient Federated Knowledge Transfer to Foundation Models

arXiv:2608.08138v1 Announce Type: new Abstract: Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training. Nevertheless, increa

Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition

arXiv:2608.09762v1 Announce Type: new Abstract: Real-world online reinforcement learning (RL) provides a promising approach for training robotic manipulation policies directly in the physical world, a

EHR-MPC: Inference-Time Control for Sepsis Treatment with Generative Patient Digital Twins

arXiv:2607.08793v4 Announce Type: replace-cross Abstract: Sepsis is a leading cause of mortality, yet optimal treatment policies remain contested. Existing reinforcement learning (RL) approaches learn

Model Releases

ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models

model-releasesarxiv-cs-ai

arXiv:2608.09548v1 Announce Type: cross Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that or

Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning

arXiv:2608.09876v1 Announce Type: cross Abstract: Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must strictly conform to real-world ex

Ethical Framework for Responsible Foundational Models in Medical Imaging

arXiv:2406.11868v2 Announce Type: replace-cross Abstract: The emergence of foundational models represents a paradigm shift in medical imaging, offering extraordinary capabilities in disease detection,

Evaluation of Motivational Interviewing Counsellors with Task-Aware Multi-Stage LLM-Based Simulated Clients

arXiv:2608.07499v1 Announce Type: cross Abstract: The development and benchmarking of Large Language Model (LLM)-based Motivational Interviewing (MI) counsellors now often rely on LLM-based simulated

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

arXiv:2603.26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space,

F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting

arXiv:2608.09082v1 Announce Type: new Abstract: Spatiotemporal prediction on graph-structured data is central to traffic forecasting and environmental monitoring, yet decentralized and heterogeneous d

FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving

arXiv:2608.09591v1 Announce Type: cross Abstract: Vision-language models (VLMs) have advanced scene understanding and enabled explicit reasoning in end-to-end autonomous driving. However, existing met

Fairness in Link Prediction Beyond Demographic Parity: A Reproducibility Study

arXiv:2608.09899v1 Announce Type: new Abstract: In fair ranked link prediction, demographic parity (Delta_DP) is a common fairness metric. Yet, Mattos et al. (2025) argue that it fails to detect expos

Financial Numerical Prediction and Allocation as Token Generation

arXiv:2608.09880v1 Announce Type: new Abstract: Financial prediction typically relies on task-specific regression, ranking, or policy heads, separating the language model from the numerical object ult

Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains

arXiv:2608.08114v1 Announce Type: cross Abstract: In this work, viscous fluid flow governed by the Stokes equations in highly perforated domains is studied using physics-informed neural networks (PINN

flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R

arXiv:2511.00079v2 Announce Type: replace Abstract: flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpo

Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR Perspective

arXiv:2608.08445v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely regarded as a novel paradigm born from the limitations of large language models (LLMs)--a mechanism to gr

From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation

arXiv:2506.00633v3 Announce Type: replace-cross Abstract: Generating semantically controllable 3D CT volumes from radiology reports requires more than a rich text encoder, it requires vision-language

From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition

arXiv:2308.04553v4 Announce Type: replace Abstract: Visual recognition models are prone to learning spurious correlations induced by a biased training set where certain conditions B (eg, Indoors) are

From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering

arXiv:2604.01476v2 Announce Type: replace-cross Abstract: Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intende

From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation

arXiv:2608.09564v1 Announce Type: cross Abstract: UAV vision-language navigation (UAV-VLN) focuses on enabling an aerial agent to follow natural-language instructions in open 3D environments from egoc

From @sequoia's own your intelligence event. We're starting to see a new category of company emerge, the Full-Stack AI company, where innova…

From @sequoia's own your intelligence event. We're starting to see a new category of company emerge, the Full-Stack AI company, where innovation happens at both the product and intelligence layer. Tha

safetysonya-huang--x

From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems

arXiv:2608.07627v1 Announce Type: new Abstract: Hospitals are racing to embed AI, while coping with the surge in adaptation of the technology in other industries, into the triage management, documenta

Generalized Convexity and Smoothness via Conjugate Duality: Optimization Theory for Deep Neural Networks

arXiv:2608.09523v1 Announce Type: new Abstract: Deep neural network (DNN) training with stochastic gradient descent (SGD) and its variants achieves strong empirical performance, yet classical optimiza

Generalizing deep reinforcement learning across cable-driven parallel robot configurations with actuator-level policies

arXiv:2608.07546v1 Announce Type: cross Abstract: Cable-driven parallel robots (CDPRs) present diverse configurations and complex control challenges, which can be addressed by deep reinforcement learn

GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering

arXiv:2608.07881v1 Announce Type: new Abstract: Clustering mixed tabular data requires a unified metric space to bridge the inherent heterogeneity between continuous numerical measurements and discret

Hierarchical Topology-Aware Planning and Control of Underwater Vehicle-Manipulator Systems in Confined Environments

arXiv:2608.08871v1 Announce Type: new Abstract: This paper addresses autonomous intervention with an underwater vehicle--manipulator system (UVMS) in confined, cluttered, and partially known environme

High-Capacity Generalized Hopfield Networks

arXiv:2608.08226v1 Announce Type: cross Abstract: Generalized Hopfield networks are introduced where memories and neurons are continuous variables that lie on a Riemannian manifold. We explicitly focu

HonestFace: Towards Honest Face Restoration with One-Step Diffusion Model

arXiv:2505.18469v2 Announce Type: replace Abstract: Face restoration has achieved significant advancements through the years of development. However, maintaining high fidelity and authenticity while a

Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue

arXiv:2608.08210v1 Announce Type: new Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an extbf{illu

Impact of Dataset Composition on Embedded Real-Time UAV Wildfire Detection Using Compact YOLO Models

arXiv:2608.07554v1 Announce Type: new Abstract: The development of vision-based wildfire detection systems for unmanned aerial vehicles is constrained by the limited availability of diverse real-world

Improving Generalization Robustness of Multimodal RLVR

arXiv:2608.08802v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasi

In-Loop Model Adaptation with Coupled Latent-Noise Guidance for High-Fidelity Subject-Driven Text-to-Image Generation

arXiv:2608.09244v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved remarkable success in generating high-quality images from a given text prompt. Subject-driven generation ai

Integrating RCTs, RWD, AI/ML and Statistics: Next-Generation Evidence Synthesis

arXiv:2511.19735v2 Announce Type: replace-cross Abstract: Randomized controlled trials (RCTs)have been the cornerstone of clinical evidence; however, their cost, duration, and restrictive eligibility

Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation

arXiv:2608.09420v1 Announce Type: new Abstract: User simulators are widely used as scalable environments for training and evaluating interactive assistants. Generating the next user turn is inherently

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders

arXiv:2604.03919v2 Announce Type: replace-cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations. Standard SAEs decompose video into interpretable

Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated Dialogue

arXiv:2608.08915v1 Announce Type: new Abstract: Situated language use is multimodal and embodied. For example, gestures can carry information that is absent or underspecified in the speech signal, yet

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family

arXiv:2604.05971v2 Announce Type: replace-cross Abstract: Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While

JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

arXiv:2608.09381v1 Announce Type: new Abstract: Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployme

JustLLMGRPO: Radiographic Control for Chest X-Ray Generation

arXiv:2608.08046v1 Announce Type: new Abstract: Text-conditioned chest X-ray generation aims to synthesize realistic radiographs that faithfully depict specified findings. Existing work has primarily

KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs

arXiv:2608.07954v1 Announce Type: new Abstract: Large language models can answer knowledge-intensive questions more reliably when they are grounded with knowledge graphs, but systems such as Think-on-

Knowing When to Ask: Resolving Uncertainty in Human-Robot Joint Planning via Explicit Dialogue and Implicit Intent Cues

arXiv:2603.07822v2 Announce Type: replace Abstract: Effective human-robot collaboration in open-world environments requires joint planning under uncertainty about the task, the environment, and the hu

Knowledge-Distilled End-to-End Reinforcement Learning for Smooth 6-DOF Thrust Control and Rapid Adaptation to Ocean Currents in Remotely Operated Vehicles

arXiv:2608.08598v1 Announce Type: new Abstract: With the continuous improvement of computational capabilities, end-to-end reinforcement learning has been rapidly developed for remotely operated vehicl

LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation

arXiv:2608.08805v1 Announce Type: new Abstract: Domain Generalization Semantic Segmentation (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains where data is

Learning aligned EEG representations with subject-specific encoders

arXiv:2606.16462v2 Announce Type: replace-cross Abstract: Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We st