safety

arXiv:2605.20808v1 Announce Type: new Abstract: Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs).

arXiv:2605.20408v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) effectively aligns Large Language Models (LLMs) with aggregate human preferences but often fails to ad

arXiv:2605.20478v1 Announce Type: new Abstract: LLM-curated tables can appear source-grounded while containing unsupported rows: the curator may recall entries from parametric memory and retroactively

arXiv:2512.23943v2 Announce Type: replace-cross Abstract: U.S. discrimination law can impose liability on firms that fail to adopt a less discriminatory alternative (LDA): a decision policy that achie

arXiv:2605.20929v1 Announce Type: new Abstract: We propose STEAM (Spatial, Temporal, and Emergent congestion Awareness for MAPF), a training-free test-time enhancement framework for learning-based dec

arXiv:2605.21261v1 Announce Type: new Abstract: Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility

arXiv:2506.21039v3 Announce Type: replace Abstract: Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are

Subword boundaries are the second meaningful effect. Adding end-of-subword markers as input embeddings produces a large gain throughout training (H3): end-boundaries leak future bytes (whitespace alwa

arXiv:2605.20373v1 Announce Type: cross Abstract: Building humanoid robots capable of generalizable whole-body loco-manipulation in the real world remains a fundamental challenge. Existing methods eit

arXiv:2605.20413v1 Announce Type: new Abstract: High-dimensional biological data often exhibit a severe mismatch between feature dimensionality and sample size, making reliable classification difficul

arXiv:2605.20619v1 Announce Type: new Abstract: Scalarization is widely used in multi-objective optimization owing to its simplicity and scalability. In many applications, the goal is to generate solu

arXiv:2605.21132v1 Announce Type: new Abstract: Understanding surgical workflow in real time is fundamental for intelligent surgical embodiment, where AI systems continuously perceive and respond as s

arXiv:2605.20908v1 Announce Type: new Abstract: Concept-based (CB) models provide interpretability and support test-time human intervention, while standard neural networks (NN) offer strong task perfo

arXiv:2605.20356v1 Announce Type: new Abstract: Full-duplex spoken dialogue models (SDMs) can listen and speak simultaneously, enabling interaction dynamics closer to human conversation than turn-base

arXiv:2506.08277v3 Announce Type: replace-cross Abstract: Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain

Since its earliest days back in office, the Trump administration has been going after researchers who study and try to counter hate speech, harassment, propaganda, and disinformation online. Now, some

arXiv:2605.20290v1 Announce Type: cross Abstract: Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Tech researchers are suing the Trump administration over the f

arXiv:2605.20281v1 Announce Type: cross Abstract: We develop a unified microeconomic and monetary theory of artificial intelligence inference costs and their pass-through to inflation, welfare, and op

arXiv:2605.20767v1 Announce Type: new Abstract: Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, becau

arXiv:2506.17631v4 Announce Type: replace Abstract: Time series forecasting aims to model temporal dependencies among variables for future state inference, holding significant importance and widesprea

arXiv:2605.20625v1 Announce Type: cross Abstract: Advanced Air Mobility (AAM) operations are expected to significantly increase aerial traffic in urban airspace, requiring autonomous traffic managemen

arXiv:2605.20994v1 Announce Type: new Abstract: Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a stand

arXiv:2605.20641v1 Announce Type: cross Abstract: Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While

arXiv:2603.24139v2 Announce Type: replace Abstract: Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and gene

The International Space Station has an ongoing air leak in its Russian PrK module that has been known since 2019 , and this leak has delayed the launch of Axiom Space's private astronaut mission . NAS

arXiv:2601.00990v2 Announce Type: replace-cross Abstract: Fetal ultrasound is the cornerstone of antenatal care, and accurate recognition of a small set of standard anatomical planes underpins biometr

arXiv:2605.21483v1 Announce Type: cross Abstract: Precise measurement of the kinematic Sunyaev-Zel'dovich (kSZ) effect - a probe of the large-scale distribution of baryonic matter, a key observable fo

arXiv:2603.19545v2 Announce Type: replace-cross Abstract: Many core problems in nonlinear systems analysis and control can be recast as solving partial differential equations (PDEs) such as Lyapunov a

arXiv:2602.18532v2 Announce Type: replace Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding fro

Reuters: Waymo suspends freeway rides and pauses its Atlanta operations, as it updates software to improve performance around construction zones and flooded roadways — Alphabet's (GOOGL.O) Waymo said

arXiv:2605.20795v1 Announce Type: new Abstract: Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-bas

arXiv:2604.01449v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems are increasingly integrated into healthcare and pharmacy workflows, supporting tasks such as medication r

When does circular financing stop? Similar to a Ponzi Scheme, when cash outflows become greater than inflows. In this last quarter, NVDA cash grew by only ~600, and now ~95% of its operating cash flow

arXiv:2603.28675v2 Announce Type: replace Abstract: Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant soc

arXiv:2504.12988v5 Announce Type: replace Abstract: Existing Learning-to-Defer (L2D) frameworks are limited to single-expert deferral, forcing each query to rely on only one expert and preventing the

Wonder what fraction of those liking this realized it was a joke 🤣 There's a lot of excitement about OpenAI's resolution of the unit distance conjecture. In this thread I will discuss the striking app

Gary Marcus argues that pursuing cheerleading and science as careers are mutually exclusive paths, suggesting fundamental incompatibility between these pursuits. The post likely critiques the idea of

Yowza! Similar in some ways to the Stanford paper recently on LLMs hallucinating responses to images they never saw. This was an amazing and incredibly damning experiment using Microsoft Copilot, by @

arXiv:2605.18933v1 Announce Type: new Abstract: Pre-norm Transformers with RMSNorm tolerate ternary {-1,0,+1} weight quantization with surprisingly small loss (Ma et al., 2024). We give a geometric ex

arXiv:2605.19166v1 Announce Type: cross Abstract: Reinforcement learning (RL)-based quadrotor control policies have achieved impressive performance in tasks such as fast navigation in cluttered enviro

arXiv:2605.19313v1 Announce Type: cross Abstract: In complex multivariate systems, interactions among variables are defined by dependency structures, often encoded as directed acyclic graphs (ext{DAGs

arXiv:2605.18798v1 Announce Type: new Abstract: We propose non-parametric estimators for the average run length (ARL) and average detection delay (ADD) in quickest changepoint detection (QCD) under fi

arXiv:2605.19202v1 Announce Type: cross Abstract: This paper addresses the problem of using a deep Reinforcement Learning (RL)-based low-level Quadrotor controller within an autonomous Quadrotor navig

In just a short time, we’ve seen AI transition from simple chat interfaces to autonomous agents capable of function calling, code execution, and persistent terminal use. But to orchestrate these capab

arXiv:2605.19503v1 Announce Type: cross Abstract: Reinforcement learning for legged locomotion has matured into a stack of multi-component reward functions and physics-engine benchmarks whose morpholo