Search: “safety”

From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning

arXiv:2603.10263v2 Announce Type: replace-cross Abstract: We introduce Distribution Contractive Reinforcement Learning (DICE-RL), a framework that uses reinforcement learning (RL) as a 'distribution c

From World Models to World Action Models: A Concise Tutorial for Robotics

DGX agent

arXiv:2607.00836v1 Announce Type: cross Abstract: World models are increasingly used in embodied intelligence and generative simulation, yet their scope remains ambiguous across communities. This tuto

safetyarxiv-cs-ai

2 Jul 2026

Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning

arXiv:2607.00452v1 Announce Type: cross Abstract: Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or va

GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception

arXiv:2607.00746v1 Announce Type: cross Abstract: The bird's-eye view (BEV) representation enables multi-sensor features to be fused within a unified space, serving as the primary approach for achievi

Google’s Continued Disruption of Malicious Residential Proxy Networks

Background Today, in coordination with the FBI, Lumen, and others, Google took action against the NetNut residential proxy network, also known as Popa. This action builds on our disruption of the IPID

safetygoogle-cloud-ai

Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination

arXiv:2607.00924v1 Announce Type: new Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. St

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

arXiv:2607.00152v1 Announce Type: cross Abstract: Three of the most popular methods for training language models to reason look like three different tricks. They are not. All three adjust a single num

How Environment and Urbanization Shape Bird Diversity in Sri Lanka

arXiv:2607.00582v1 Announce Type: cross Abstract: This study presents a comprehensive analysis of bird diversity across Sri Lanka by integrating spatial, temporal, and environmental data. Bird observa

HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

arXiv:2607.00428v1 Announce Type: new Abstract: CLIP (Contrastive Language-Image Pre-training) has become a de facto paradigm for image-text alignment, but it struggles with long-context descriptions

Identifying Latent Concepts and Structures for Generalized Category Discovery

arXiv:2607.00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, curren

in case you needed more evidence that tokenmaxxing was a stupid idea

in case you needed more evidence that tokenmaxxing was a stupid idea Meta burns 2.65B a year on AI tokens. at 300K for a Meta engineer, that's enough to pay ~9,000 engineers for a full year. now ask y

safetygary-marcus--x

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

arXiv:2506.12851v3 Announce Type: replace-cross Abstract: Humanoid robots are promising to acquire various skills by imitating human behaviors. However, existing algorithms are only capable of trackin

Learning Category-level Last-meter Navigation from RGB Demonstrations of a Single-instance

arXiv:2512.11173v4 Announce Type: replace Abstract: Achieving precise positioning of the mobile manipulator's base is essential for successful manipulation actions that follow. Most of the RGB-based n

safetyarxiv-cs-ro

Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

arXiv:2607.00392v1 Announce Type: cross Abstract: Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation fo

Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory

arXiv:2607.00017v1 Announce Type: cross Abstract: Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the righ

LIST3R: Long-sequence Instance-aware 3D Reconstruction

arXiv:2607.00375v1 Announce Type: new Abstract: We present LIST3R, an instance-aware framework for long-sequence 3D reconstruction inspired by the way humans organize spatial memory around stable and

Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment

arXiv:2607.00603v1 Announce Type: new Abstract: We give a descent-free, alignment-free measurement of singular structure on trained networks. At a single frozen checkpoint the read recovers the order

MedCAGD: Context-Aware Gated Decoder for Efficient Medical Image Segmentation

arXiv:2607.00409v1 Announce Type: new Abstract: Medical image segmentation relies on the ability of encoder-decoder architectures to translate rich feature representations into accurate pixel-level pr

Meta-Transfer Learning for mmWave Beam Alignment

arXiv:2607.00860v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) beam alignment plays a critical role in next-generation wireless systems, yet its efficient implementation remains challengin

Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning

arXiv:2607.00850v1 Announce Type: new Abstract: Most self-supervised learning (SSL) methods encourage invariance across augmentations, but strict flip invariance can suppress informative left--right c

MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment

arXiv:2607.00858v1 Announce Type: new Abstract: Contrastive pre-training has propelled video-text alignment, yet models often inherit the critical limitations of their image-text predecessors like CLI

Multi-scale Mixture of World Models for Embodied Agents in Evolving Environments

arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in a

Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning

arXiv:2505.19614v2 Announce Type: replace-cross Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities. Most current approache

NeuroCogMap Reveals Cognitive Organization of Large Language Models

arXiv:2607.00397v1 Announce Type: cross Abstract: Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and rela

NEW paper from NVIDIA. They discuss robot programming that compounds experience instead of throwing it away. Traditional robot programming f…

NEW paper from NVIDIA. They discuss robot programming that compounds experience instead of throwing it away. Traditional robot programming forces you to orchestrate perception, contact dynamics, diver

safetydair-ai--x

OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping

arXiv:2607.00881v1 Announce Type: new Abstract: Spatial intelligence remains a persistent challenge for Multimodal Large Language Models (MLLMs), as it requires coherent spatial scene representations

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning

arXiv:2510.24636v3 Announce Type: replace Abstract: Reward models (RMs) have become essential for aligning large language models (LLMs), serving as scalable proxies for human evaluation in both traini

safetyarxiv-cs-cl

PAPA: Online Personalized Active Preference Alignment

arXiv:2607.00486v1 Announce Type: cross Abstract: Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized re

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

arXiv:2607.00407v1 Announce Type: new Abstract: Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design

Predicting LLM Reasoning Performance with Small Proxy Model

arXiv:2509.21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before

Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation

arXiv:2607.00499v1 Announce Type: new Abstract: Automated pathology report generation from Whole Slide Images (WSIs) has attracted increasing attention in digital pathology. However, existing methods

PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition

arXiv:2607.00358v1 Announce Type: new Abstract: Electroencephalogram (EEG) captures endogenous brain activity with high temporal fidelity and holds substantial promise for precise emotion decoding. Ho

Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework

arXiv:2607.00010v1 Announce Type: cross Abstract: Conversational recommender systems (CRSs) are a core component of next-generation intelligent recommender systems because they enable users to activel

Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation

arXiv:2606.13971v2 Announce Type: replace Abstract: While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current pra

QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling

arXiv:2607.01179v1 Announce Type: cross Abstract: Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities.

safetyarxiv-cs-cl

Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval

arXiv:2607.00448v1 Announce Type: cross Abstract: The two-tower model has been widely used for large-scale recommendation systems, particularly in the retrieval stage. Industry standards for training

Revisiting Autoregressive Models for Generative Image Classification

arXiv:2603.19122v2 Announce Type: replace Abstract: Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other

Robots Ask the Way: Communication-Enabled Social Navigation

arXiv:2607.01044v1 Announce Type: new Abstract: Assistive autonomous robots operating in multi-agent environments require efficient strategies to locate specific individuals among multiple residents.

safetyarxiv-cs-ro

RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation

arXiv:2607.01060v1 Announce Type: new Abstract: Video world models are emerging as a scalable alternative for evaluating generalist robot policies, bypassing the physical constraints and engineering b

safetyarxiv-cs-ro

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

arXiv:2604.03118v2 Announce Type: replace Abstract: Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging

Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs

arXiv:2510.04140v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Mo

Selective Test-Time Debiasing for CLIP via Reward Gating

arXiv:2607.00423v1 Announce Type: new Abstract: Vision language models (VLMs) demonstrate strong zero-shot performance, but often perpetuate social stereotypes in person-centric queries, yielding skew

safetyarxiv-cs-cl

Self-Evolving Agents with Anytime-Valid Certificates

arXiv:2607.00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produce

Semi-Bandit Learning for Monotone Stochastic Optimization

arXiv:2312.15427v3 Announce Type: replace Abstract: Stochastic optimization is a widely used approach for optimization under uncertainty, where uncertain input parameters are modeled by random variabl

Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search

arXiv:2607.01144v1 Announce Type: cross Abstract: While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the

Should we be spending literally trillions on a speculative bet when we can’t even solidly document clear positive impact? Great analysis of …

Should we be spending literally trillions on a speculative bet when we can’t even solidly document clear positive impact? Great analysis of what we don’t yet know below, by @bencasselman drawing on a

safetygary-marcus--x

SleepLM: Natural-Language Intelligence for Human Sleep

arXiv:2602.23605v2 Announce Type: replace Abstract: We present SleepLM, a family of sleep-language foundation models that enable human sleep alignment, interpretation, and interaction with natural lan

Spatio-Temporal Gaussian Process for Building Terrain-Incorporating Wind Power Curves

arXiv:2607.00051v1 Announce Type: cross Abstract: Accurate modeling of wind turbine power curves is crucial for optimal wind farm operation. Nearly all existing power curve models focus on temporal va