safety

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

arXiv:2505.12843v2 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) relies on reward models to align large language models with human preferences. However, RLHF often

Safety

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

DGX agent

arXiv:2606.25473v1 Announce Type: new Abstract: Autoregressive video diffusion with causal diffusion transformers has emerged as a major paradigm for real-time streaming video generation and action-co

safetyarxiv-cs-cv

25 Jun 2026

Causality-Based Parametric Control Barrier Function for Safe Multi-Vehicle Interaction

arXiv:2606.25134v1 Announce Type: new Abstract: Safe control has been widely studied in various safety-critical applications, for instance, autonomous driving. In order to ensure the autonomous vehicl

Chad Jones, economist who'll be joining Anthropic: 'In other words, with log utility it is optimal to take a 1 in 3 chance of ending human e…

Chad Jones, economist who'll be joining Anthropic: 'In other words, with log utility it is optimal to take a 1 in 3 chance of ending human existence in exchange for a 2/3 chance of dramatically raisin

safetyconnor-leahy--x

Chart of increasing revenue, pre the decline of token-maxxing, not looking at the immense costs/lack of profitability, not considering threa…

Chart of increasing revenue, pre the decline of token-maxxing, not looking at the immense costs/lack of profitability, not considering threats from open-source models, price-war dynamics etc. @noahopi

Commerge: Communication-Efficient, Robust, and Fast LiDAR Map Merging Framework for Multi-Robot Coordination in Resource-Constrained Scenarios

arXiv:2606.25386v1 Announce Type: new Abstract: By maintaining global consistency across robot teams, multi-robot LiDAR map merging enables faster exploration and efficient area coverage. However, map

Communicability-Inspired Positional Encoding (CIPE)

arXiv:2606.25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings shou

Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers

arXiv:2606.25371v1 Announce Type: cross Abstract: Runtime assurance (RTA) protects a safety-critical system by switching from an advanced controller to a verified safe controller when a monitored cond

safetyarxiv-cs-ai

Consistent Zero-Shot Imitation with Contrastive Goal Inference

arXiv:2510.17059v2 Announce Type: replace Abstract: Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction o

Constituency Structure over Eojeol in Korean Treebanks

arXiv:2512.22487v2 Announce Type: replace Abstract: The design of Korean constituency treebanks raises a central representational question concerning the choice of terminal units. Although Korean word

Contrastive Conditional-Unconditional Alignment for Long-tailed Diffusion Model

arXiv:2507.09052v3 Announce Type: replace Abstract: Training data for class-conditional image synthesis often exhibit a long-tailed distribution with limited amount of images for tail classes. Such an

Crazy how many times people have told me over the last five years that a solution to hallucinations was right around the corner — and yet he…

Crazy how many times people have told me over the last five years that a solution to hallucinations was right around the corner — and yet here we still are. This study tests how often LLMs invent answ

Cross-View Variance Correlation in Path-Traced Stereo:A Hidden Shortcut in Synthetic Training Data

arXiv:2606.25483v1 Announce Type: new Abstract: Path-traced synthetic stereo data underlie a large fraction of modern disparity-estimation training pipelines. We report a previously unrecognised prope

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

arXiv:2606.16497v2 Announce Type: replace-cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective. We present da

Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning

arXiv:2606.25360v1 Announce Type: new Abstract: While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoni

Deep Reinforcement Learning-Enhanced Event-Triggered Data-Driven Predictive Control for a 3D Cable-Driven Soft Robotic Arm

arXiv:2606.26048v1 Announce Type: new Abstract: Soft robots are challenging to control due to their nonlinear and time-varying dynamics. Data-enabled predictive control (DeePC) offers a model-free alt

DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning

arXiv:2606.25939v1 Announce Type: new Abstract: Demonstration augmentation is proposed for cost-efficient data acquisition, but existing methods are fundamentally limited in deformable manipulation du

Digital Twin-Driven Adaptive Sim-to-Real Alignment via Reinforcement Learning for Vibration-Based Bearing Health Monitoring Under Data Scarcity

arXiv:2606.24954v1 Announce Type: cross Abstract: Vibration-based health monitoring of rotating machinery requires reliable fault diagnosis under operational data constraints, yet condition assessment

DRM: Diffusion-based Reward Model With Step-wise Guidance

arXiv:2605.25661v2 Announce Type: replace Abstract: Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward model

Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation

arXiv:2606.25254v1 Announce Type: cross Abstract: Maternal-fetal US is the primary imaging modality for monitoring fetal development, yet accurate automated segmentation remains challenging due to the

DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects

arXiv:2606.25295v1 Announce Type: new Abstract: Mobile manipulation is a fundamental robotics task and has advanced rapidly in recent years, enabling robots to navigate, reach, and interact with objec

Efficient Adaptive Data Acquisition via Pretrained Belief Representations

arXiv:2606.25197v1 Announce Type: new Abstract: Learning effective policies for adaptive data acquisition remains challenging: posterior-based methods rely on surrogate models and posterior approximat

Evaluation Protocols and Validation for Cameras in Indoor Healthcare Monitoring

arXiv:2606.25284v1 Announce Type: new Abstract: Camera-based monitoring systems are increasingly adopted in healthcare settings for the continuous assessment of patient movement and activities. Howeve

Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situations

arXiv:2606.25629v1 Announce Type: new Abstract: Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the un

Exclusive: Chainguard extends Repository scanning and policies to Java, Python and containers

Secure software supply chain solution provider Chainguard Inc. today expanded its Chainguard Repository product with malware scanning, policy enforcement and visibility features that now cover Java pa

safetysiliconangle

ext{DT}^2: Decision-Targeted Digital Twins

arXiv:2606.25923v1 Announce Type: new Abstract: A digital twin (DT) is a virtual model of a real-world system that can assist decision-making by simulating scenarios induced by different policies. How

FAST-LIVGO: A Degeneracy-Robust LiDAR-Inertial-Visual-GNSS Fusion Odometry

arXiv:2606.19190v2 Announce Type: replace Abstract: Robust state estimation and mapping in long-term, large-scale, and highly dynamic environments remains a key challenge in robotics. Existing LiDAR-I

Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories

arXiv:2606.25344v1 Announce Type: new Abstract: 4D generation aims to animate 3D objects with realistic motion, holding great promise for applications. Existing methods typically decouple 3D asset gen

FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation

arXiv:2606.26006v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are often constrained by the imitation ceiling imposed by sub-optimal data. While Reinforcement Learning (RL) fine-t

ForceBand: Learning Forceful Manipulation with sEMG

arXiv:2606.26093v1 Announce Type: new Abstract: Human demonstrations are a scalable data source for learning robot manipulation policies. However, common sources of human demonstration data, such as m

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential

arXiv:2502.18959v4 Announce Type: replace Abstract: The architecture of a neural network and the choice of its activation function are both fundamental to its performance. Equally important is ensurin

Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

arXiv:2505.19532v2 Announce Type: replace Abstract: The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume th

From Forecasting Leaderboards to Deployment Decisions: A Fail-Closed Certification Protocol

arXiv:2606.24996v1 Announce Type: new Abstract: Forecasting leaderboards rank models by predictive quality, but their winners are often read as deployment-ready top-1 advice. That reading can fail whe

From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control

arXiv:2502.02205v4 Announce Type: replace Abstract: The application of deep learning for partial differential equation (PDE)-constrained control is gaining increasing attention. However, existing meth

Fully Differentiable Neural Forced Alignment via Soft Dynamic Programming

arXiv:2606.25460v1 Announce Type: cross Abstract: Recent advances in sequence modeling have significantly improved ASR systems, bringing them close to human-level recognition accuracy and enhancing ro

G2DP: Diffusion Planning with Spatio-Temporal Grid Guidance

arXiv:2606.26017v1 Announce Type: new Abstract: In autonomous driving, diffusion-based planners have emerged as a promising paradigm for robust motion planning in dense and interactive traffic, as the

GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning

arXiv:2606.25073v1 Announce Type: new Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch fo

Generalised Medical Phrase Grounding

arXiv:2512.01085v3 Announce Type: replace-cross Abstract: Medical phrase grounding (MPG) maps textual descriptions of radiological findings to corresponding image regions. These grounded reports are e

Generative AI for Safe and Photorealistic Drone Light Shows

arXiv:2606.25458v1 Announce Type: new Abstract: Drone light shows are redefining aerial entertainment, yet their widespread adoption is bottlenecked by labor-intensive, manual animation. While generat

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

arXiv:2606.25347v1 Announce Type: cross Abstract: Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditio

Grifters and many other salesman are like LLMs. They say things that aren’t always true with absolutely certainty.

Grifters and many other salesman are like LLMs. They say things that aren’t always true with absolutely certainty. Bitcoin has won. Global consensus is that $BTC is digital capital. The four-year cycl

Grok may not be the AGI that Elon promised, but it appears that the man has found his use case.

Grok may not be the AGI that Elon promised, but it appears that the man has found his use case. xAI is betting big on AI video and image generation — but the biggest driver of Grok Imagine may not be

GUI agent: Guided Exploration of User-Sensitive Screens

arXiv:2606.25705v1 Announce Type: new Abstract: LLM agents are increasingly being used to automate tasks for users within an open GUI environment. They inevitably encounter screens containing user-sen

safetyarxiv-cs-ai

Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty

arXiv:2606.25198v1 Announce Type: new Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-base

safetyarxiv-cs-ai

Homogeneity Bias in Open-Weight LLMs Is Robust to Decoding Hyperparameters

arXiv:2501.02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominan

Imagine if i had a business that gave you 20 bills for 10 bills. As word spread, my customer base would grow. My revenue (how many $10 bil…

Imagine if i had a business that gave you 20 bills for 10 bills. As word spread, my customer base would grow. My revenue (how many $10 bills I collected) would grow. And I would continue to lose money

In the end, will Elon be best known for his efforts to mainstream electric cars, for his rockets, …. or for his efforts to mainstream AI-gen…

In the end, will Elon be best known for his efforts to mainstream electric cars, for his rockets, …. or for his efforts to mainstream AI-generated porn? xAI is betting big on AI video and image genera

It is amazing to me how little the X-verse cares about the rise of authoritarianism in the United States. Is that because most of the “peopl…

It is amazing to me how little the X-verse cares about the rise of authoritarianism in the United States. Is that because most of the “people” here are actually Russian bots? 🤔 More Soviet-style decep