safety

Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation

arXiv:2508.04691v2 Announce Type: replace-cross Abstract: As humans move toward collaborating with coordinated robot teams, understanding how these teams coordinate and fail is essential for building

Safety

Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment

DGX agent

arXiv:2604.07306v1 Announce Type: cross Abstract: Existing dynamic data pruning methods often fail under noisy-label settings, as they typically rely on per-sample loss as the ranking criterion. This

safetyarxiv-cs-lg

10 Apr 2026

Beyond Pessimism: Offline Learning in KL-regularized Games

arXiv:2604.06738v1 Announce Type: cross Abstract: We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized under a KL constraint to a fixed reference policy.

Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation

arXiv:2604.06820v1 Announce Type: new Abstract: Large language models (LLMs) can generate persuasive narratives at scale, raising concerns about their potential use in disinformation campaigns. Assess

Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?

arXiv:2604.08111v1 Announce Type: cross Abstract: Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness impl

Boycott OpenAI. They literally want the right to kill you.

I'm unable to fetch the content of that X (Twitter) URL directly, as I don't have the ability to browse or retrieve content from social media posts or URLs. Additionally, my web search did not retu...

Brain3D: EEG-to-3D Decoding of Visual Representations via Multimodal Reasoning

arXiv:2604.08068v1 Announce Type: new Abstract: Decoding visual information from electroencephalography (EEG) has recently achieved promising results, primarily focusing on reconstructing two-dimensio

CAFP: A Post-Processing Framework for Group Fairness via Counterfactual Model Averaging

arXiv:2604.07009v1 Announce Type: new Abstract: Ensuring fairness in machine learning predictions is a critical challenge, especially when models are deployed in sensitive domains such as credit scori

Candles are more regulated than AI. And candle manufacturers aren’t AFAIK lobbying for absolute freedom from liability if they fuck up. Open…

Candles are more regulated than AI. And candle manufacturers aren’t AFAIK lobbying for absolute freedom from liability if they fuck up. OpenAI is truly appalling. @GaryMarcus @ESYudkowsky Seriously fu

CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection

arXiv:2604.07457v1 Announce Type: new Abstract: While decoupled control schemes for legged mobile manipulators have shown robustness, learning holistic whole-body control policies for tracking global

CNN-based Surface Temperature Forecasts with Ensemble Numerical Weather Prediction

arXiv:2507.18937v3 Announce Type: replace-cross Abstract: Due to limited computational resources, medium-range temperature forecasts typically rely on low-resolution numerical weather prediction (NWP)

Contextualising (Im)plausible Events Triggers Figurative Language

arXiv:2604.07885v1 Announce Type: new Abstract: This work explores the connection between (non-)literalness and plausibility at the example of subject-verb-object events in English. We design a system

Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge

arXiv:2510.18196v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge.

CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research

arXiv:2604.07132v1 Announce Type: cross Abstract: Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethi

Data Leakage in Automotive Perception: Practitioners' Insights

arXiv:2604.06899v1 Announce Type: cross Abstract: Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliab

Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs

arXiv:2604.07518v1 Announce Type: new Abstract: Vision-Language Models often struggle with complex visual reasoning due to the visual information loss in textual CoT. Existing methods either add the c

Deep Learning-Powered Visual SLAM Aimed at Assisting Visually Impaired Navigation

arXiv:2510.20549v2 Announce Type: replace Abstract: Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting r

Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

arXiv:2604.08527v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models under their own induced distribution while leveraging supervision from stronger teachers. We identify

Designing Safe and Accountable GenAI as a Learning Companion with Women Banned from Formal Education

arXiv:2604.07253v1 Announce Type: cross Abstract: In gender-restrictive and surveilled contexts, where access to formal education may be restricted for women, pursuing education involves safety and pr

Discrete Flow Matching Policy Optimization

arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

arXiv:2604.06210v2 Announce Type: cross Abstract: As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks fac

Does anyone without a lot of money at stake seriously disagree?

I was unable to retrieve the specific tweet at the provided URL. The tweet ID `2042429820500656544` does not appear in any indexed search results, and X (formerly Twitter) requires JavaScript/login...

Download the Tesla Robotaxi app

Download the Tesla Robotaxi app NEWS: Tesla has updated their Robotaxi app. What's new: • New tips section, which displays how many seats are available in the car, tells you that the vehicle lights wi

safetyelon-musk--x

Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Control

arXiv:2604.03540v2 Announce Type: replace Abstract: Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require

EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation

arXiv:2602.13669v4 Announce Type: replace Abstract: Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder re

EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World

arXiv:2604.07607v1 Announce Type: cross Abstract: Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human da

EMMa: End-Effector Stability-Oriented Mobile Manipulation for Tracked Rescue Robots

arXiv:2604.08292v1 Announce Type: new Abstract: The autonomous operation of tracked mobile manipulators in rescue missions requires not only ensuring the reachability and safety of robot motion but al

Epic corruption, endless propaganda, security force crackdowns and false flag operations, election interference by a hostile foreign dictato…

Epic corruption, endless propaganda, security force crackdowns and false flag operations, election interference by a hostile foreign dictatorship… That’s Orbán’s Hungary today and, unless America wake

Equivariant Multi-agent Reinforcement Learning for Multimodal Vehicle-to-Infrastructure Systems

arXiv:2604.06914v1 Announce Type: new Abstract: In this paper, we study a vehicle-to-infrastructure (V2I) system where distributed base stations (BSs) acting as road-side units (RSUs) collect multimod

Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles

arXiv:2604.07378v1 Announce Type: new Abstract: Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biase

Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making

arXiv:2604.07392v1 Announce Type: cross Abstract: Autonomous agents operating in dynamic and safety-critical environments require decision-making frameworks that are both computationally efficient and

Event-Level Detection of Surgical Instrument Handovers in Videos with Interpretable Vision Models

arXiv:2604.07577v1 Announce Type: new Abstract: Reliable monitoring of surgical instrument exchanges is essential for maintaining procedural efficiency and patient safety in the operating room. Automa

Everything you need to know about “Open”AI’s claims to be working on AI “for the benefit of humanity”.

The specific X/Twitter post referenced (status ID 2042632799950352702) is not publicly accessible through search results, as X requires JavaScript and login to view individual posts. However, based...

Explainable AI to Improve Machine Learning Reliability for Industrial Cyber-Physical Systems

arXiv:2601.16074v2 Announce Type: replace Abstract: Industrial Cyber-Physical Systems (CPS) are sensitive infrastructure from both safety and economics perspectives, making their reliability criticall

Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization

arXiv:2604.08476v1 Announce Type: new Abstract: Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchma

Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control

arXiv:2603.04038v2 Announce Type: replace Abstract: Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered b

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

arXiv:2604.06916v1 Announce Type: cross Abstract: Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human prefere

From experimentation to engagement: on the paradox of participatory AI and power in contexts of forced displacement and humanitarian crises

arXiv:2604.06219v1 Announce Type: cross Abstract: Across the Global North, calls for participatory artificial intelligence (AI) to improve the responsible, safe, and ethical use of AI have increased,

From Ground Truth to Measurement: A Statistical Framework for Human Labeling

arXiv:2604.07591v1 Announce Type: cross Abstract: Supervised machine learning assumes that labeled data provide accurate measurements of the concepts models are meant to learn. Yet in practice, human

Front-End Ethics for Sensor-Fused Health Conversational Agents: An Ethical Design Space for Biometrics

arXiv:2604.06203v1 Announce Type: cross Abstract: The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of 'Sensor-Fused LLM agents' for personal

FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

arXiv:2604.06779v1 Announce Type: new Abstract: We introduce Fleming-Viot Diffusion (FVD), an inference-time alignment method that resolves the diversity collapse commonly observed in Sequential Monte

Garry @Kasparov63 retired from competitive chess over twenty years ago, and most or all of his tournament games are presumably publicly avai…

Garry @Kasparov63 retired from competitive chess over twenty years ago, and most or all of his tournament games are presumably publicly available - and yet I bet he still could crush any LLM that didn

Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models

arXiv:2604.06767v1 Announce Type: new Abstract: Language models operate on discrete tokens but compute in continuous vector spaces, inducing a Voronoi tessellation over the representation manifold. We

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA

arXiv:2510.23868v4 Announce Type: replace Abstract: This paper proposes extit{Group-relative Implicit Fine-Tuning (GIFT)}, a reinforcement learning framework for aligning large language models (LLMs

Governed Capability Evolution for Embodied Agents: Safe Upgrade, Compatibility Checking, and Runtime Rollback for Embodied Capability Modules

arXiv:2604.08059v1 Announce Type: new Abstract: Embodied agents are increasingly expected to improve over time by updating their executable capabilities rather than rewriting the agent itself. Prior w

Governing frontier general-purpose AI in the public sector: adaptive risk management and policy capacity under uncertainty through 2030

arXiv:2604.06215v1 Announce Type: cross Abstract: The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical

Grasp as You Dream: Imitating Functional Grasping from Generated Human Demonstrations

arXiv:2604.07517v1 Announce Type: new Abstract: Building generalist robots capable of performing functional grasping in everyday, open-world environments remains a significant challenge due to the vas

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs

arXiv:2604.07655v1 Announce Type: cross Abstract: Hard-gated safety checkers often over-refuse and misalign with a vendor's model spec; prevailing taxonomies also neglect robustness and honesty, yield