safety

ACTUAL BREAKING NEWS that sounds like an @TheOnion Headline: Florida man/Adjudicated rapist/convicted felon/one-time close personal friend w…

ACTUAL BREAKING NEWS that sounds like an @TheOnion Headline: Florida man/Adjudicated rapist/convicted felon/one-time close personal friend with Jeffrey Epstein who has six corporate bankruptcies in hi

safetygary-marcus--x

Safety

Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization

DGX agent

arXiv:2604.09462v1 Announce Type: new Abstract: Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces high

safetyarxiv-cs-ro

13 Apr 2026

Advantage-Guided Diffusion for Model-Based Reinforcement Learning

arXiv:2604.09035v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this

Adversarial Concept Distillation for One-Step Diffusion Personalization

arXiv:2510.20512v2 Announce Type: replace Abstract: Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

arXiv:2502.08691v2 Announce Type: replace-cross Abstract: Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significa

AI chatbots misdiagnose in over 80% of early medical cases, study finds https://ft.trib.al/cRifiz2

A study has found that AI chatbots incorrectly diagnose patients in more than 80% of early medical cases, raising significant concerns about the reliability of AI tools in clinical settings. The resea

safetygary-marcus--x

Alienated Europe Alienated the religious right Alienated Rogan, Carlson and many more Declared a war that even he can’t justify Messed up th…

Alienated Europe Alienated the religious right Alienated Rogan, Carlson and many more Declared a war that even he can’t justify Messed up the Middle East Drove up the price of oil Drove up inflation U

safetygary-marcus--x

An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations

arXiv:2602.13939v3 Announce Type: replace-cross Abstract: Business environments characterized by intermittent demand, high variability, and multi-step planning horizons require forecasting policies th

Anthropic says its $20M donation to Public First Action can't be 'used to influence federal elections' and is to educate the public on AI policy (Veronica Irwin/Transformer)

Veronica Irwin / Transformer: Anthropic says its $20M donation to Public First Action can't be “used to influence federal elections” and is to educate the public on AI policy — The company's money isn

safetytechmeme

Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification

arXiv:2604.09288v1 Announce Type: new Abstract: Trusted multi-view classification typically relies on a view-wise evidential fusion process: each view independently produces class evidence and uncerta

Artifacts as Memory Beyond the Agent Boundary

arXiv:2604.08756v1 Announce Type: new Abstract: The situated view of cognition holds that intelligent behavior depends not only on internal memory, but on an agent's active use of environmental resour

As AI agents accelerate coding, what is the future of software engineering? Some trends are clear, such as the Product Management Bottleneck…

As AI agents accelerate coding, what is the future of software engineering? Some trends are clear, such as the Product Management Bottleneck, referring to the idea that we are more constrained by deci

safetyandrew-ng--x

ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer

arXiv:2604.08355v2 Announce Type: replace Abstract: Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered.

ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering

arXiv:2604.08999v1 Announce Type: cross Abstract: Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering, hindered by challenges such as

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

arXiv:2511.18960v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations in

Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias

arXiv:2405.16772v2 Announce Type: replace-cross Abstract: Social recommendation models weave social interactions into their design to provide uniquely personalized recommendation results for users. Ho

Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine

arXiv:2603.06665v2 Announce Type: replace-cross Abstract: Large vision-language models (VLMs) often benefit from chain-of-thought (CoT) prompting in general domains, yet its efficacy in medical vision

Beyond Segmentation: Structurally Informed Facade Parsing from Imperfect Images

arXiv:2604.09260v1 Announce Type: new Abstract: Standard object detectors typically treat architectural elements independently, often resulting in facade parsings that lack the structural coherence re

BIAS: A Biologically Inspired Algorithm for Video Saliency Detection

arXiv:2604.08858v1 Announce Type: new Abstract: We present BIAS, a fast, biologically inspired model for dynamic visual saliency detection in continuous video streams. Building on the Itti--Koch frame

Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Training

arXiv:2604.08357v2 Announce Type: replace Abstract: Conditional Diffusion Models are powerful surrogates for emulating complex spatiotemporal dynamics, yet they often fail to match the accuracy of det

BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis

arXiv:2604.07361v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have been widely used in diverse brain network analysis tasks based on preprocessed functional magnetic resonance imagi

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning

arXiv:2604.08926v1 Announce Type: new Abstract: Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dil

Cards Against LLMs: Benchmarking Humor Alignment in Large Language Models

arXiv:2604.08757v1 Announce Type: cross Abstract: Humor is one of the most culturally embedded and socially significant dimensions of human communication, yet it remains largely unexplored as a dimens

CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention

arXiv:2603.18561v2 Announce Type: replace Abstract: Planning-oriented end-to-end driving models show great promise, yet they fundamentally learn statistical correlations instead of true causal relatio

Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search

arXiv:2509.25835v4 Announce Type: replace Abstract: Test-time scaling improves large language models (LLMs) on long-horizon reasoning tasks by allocating more compute at inference. LLM inference via t

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

arXiv:2505.18600v3 Announce Type: replace-cross Abstract: Modern single-image super-resolution (SISR) models deliver photo-realistic results at the scale factors on which they are trained, but collaps

ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning

arXiv:2507.04736v2 Announce Type: replace Abstract: Large Language Models have emerged as powerful tools for automating Register-Transfer Level (RTL) code generation, yet they face critical limitation

ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering

arXiv:2508.06656v2 Announce Type: replace Abstract: In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attri

Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary

arXiv:2511.22963v2 Announce Type: replace-cross Abstract: Enabling humanoid robots to follow free-form language commands is critical for seamless human-robot interaction, collaborative task execution,

Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents

arXiv:2604.09308v1 Announce Type: new Abstract: Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any s

Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

arXiv:2604.08643v1 Announce Type: new Abstract: User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the s

Dejavu: Towards Experience Feedback Learning for Embodied Intelligence

arXiv:2510.10181v3 Announce Type: replace-cross Abstract: Embodied agents face a fundamental limitation: once deployed in real-world environments, they cannot easily acquire new knowledge to improve t

Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success

arXiv:2601.22285v4 Announce Type: replace Abstract: Model merging combines knowledge from separately fine-tuned models, yet success factors remain poorly understood. While recent work treats mergeabil

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

arXiv:2604.08846v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prom

Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies

arXiv:2604.09189v1 Announce Type: cross Abstract: LLMs internalize safety policies through RLHF, yet these policies are never formally specified and remain difficult to inspect. Existing benchmarks ev

Dynamic Class-Aware Active Learning for Unbiased Satellite Image Segmentation

arXiv:2604.08965v1 Announce Type: new Abstract: Semantic segmentation of satellite imagery plays a vital role in land cover mapping and environmental monitoring. However, annotating large-scale, high-

E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning

arXiv:2604.09455v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face signific

ECHO: Efficient Chest X-ray Report Generation with One-step Block Diffusion

arXiv:2604.09450v1 Announce Type: cross Abstract: Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists' workload. However, conventional autoregressive visio

Efficient RL Training for LLMs with Experience Replay

arXiv:2604.08706v1 Announce Type: new Abstract: While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL,

EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure

arXiv:2604.09405v1 Announce Type: new Abstract: As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted char

EmoCtrl: Controllable Emotional Image Content Generation

arXiv:2512.22437v2 Announce Type: replace Abstract: An image conveys meaning through both its visual content and emotional tone, jointly shaping human perception. We introduce Controllable Emotional I

Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations

arXiv:2506.09067v2 Announce Type: replace-cross Abstract: Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports)

@ESYudkowsky My horrendous nightmare of a political lifecycle, ladies and gentlemen and others.

Connor Leahy shared a post on X (formerly Twitter) quoting or referencing Eliezer Yudkowsky's account (@ESYudkowsky), describing what he characterizes as a 'horrendous nightmare of a political lifecyc

safetyconnor-leahy--x

EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue

arXiv:2604.09265v1 Announce Type: new Abstract: Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or

safetyarxiv-cs-cl

EvoLen: Evolution-Guided Tokenization for DNA Language Model

arXiv:2604.08698v1 Announce Type: new Abstract: Tokens serve as the basic units of representation in DNA language models (DNALMs), yet their design remains underexplored. Unlike natural language, DNA

Evolutionary Optimization Trumps Adam Optimization on Embedding Space Exploration

arXiv:2511.03913v2 Announce Type: replace-cross Abstract: Deep diffusion models have revolutionized image generation by producing high-quality outputs. However, achieving specific objectives with thes

Exploring Teachers' Perspectives on Using Conversational AI Agents for Group Collaboration

arXiv:2602.07142v2 Announce Type: replace-cross Abstract: Collaboration is a cornerstone of 21st-century learning, yet teachers continue to face challenges in supporting productive peer interaction. E

Extrapolating Volition with Recursive Information Markets

arXiv:2604.08606v1 Announce Type: cross Abstract: One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the 'buyer's ins