Search: “safety”

Hamiltonian-Inspired Attention Mechanism for Scalable RF Transmitter Fingerprinting

arXiv:2605.30364v1 Announce Type: cross Abstract: Radio-frequency (RF) fingerprinting identifies wire-less transmitters using hardware-induced imperfections present in baseband I/Q signals. However, d

HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model

DGX agent

arXiv:2605.31234v1 Announce Type: new Abstract: Learning generalizable vision-language-action (VLA) models from large-scale human videos is promising but challenging due to cross-embodiment discrepanc

safetyarxiv-cs-ro

1 Jun 2026

Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response

arXiv:2605.30680v1 Announce Type: new Abstract: Healthcare mechanisms are inseparable from the strategic provider response they induce: existing healthcare AI benchmarks hold this response fixed and s

HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents

arXiv:2602.16165v2 Announce Type: replace-cross Abstract: Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and del

HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning

arXiv:2605.31068v1 Announce Type: new Abstract: We introduce HQ-JEPA, a hybrid quantum-classical joint-embedding predictive architecture for cross-modal remote sensing representation learning. The pro

Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models

arXiv:2508.08204v2 Announce Type: replace-cross Abstract: There has been much recent interest in evaluating large language models for uncertainty calibration to facilitate model control and modulate u

Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty

arXiv:2605.30675v1 Announce Type: cross Abstract: Uncertainty Quantification is a large and growing subfield of large language model behavioral analysis. Primarily to recognize and combat hallucinatio

Human Psychometric Questionnaires Mischaracterize LLM Behavior

arXiv:2509.10078v4 Announce Type: replace-cross Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for characterizing and predicting LLM behavior in everyday us

I would say that it is absurd to say that “AI belongs to the people”, when so many companies have worked so hard to develop it, but it is al…

I would say that it is absurd to say that “AI belongs to the people”, when so many companies have worked so hard to develop it, but it is also absurd that Generative AI has basically been built on the

IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning

arXiv:2602.19049v2 Announce Type: replace Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We

If “Insanity is doing the same thing over and over again and expecting different results”, what the heck is Generative AI?

Gary Marcus critiques generative AI by applying the 'insanity' aphorism to highlight repetitive patterns in how these systems operate—suggesting they may be fundamentally limited by repeating the same

ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment

arXiv:2605.30965v1 Announce Type: cross Abstract: Recent advancements in text-guided audio generation have yielded promising results in diverse domains, including sound effects, speech, and music. How

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment

arXiv:2603.19862v2 Announce Type: replace Abstract: Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individ

Kiss your pensions goodbye, folks May 20 - SpaceX's (SPCX) S-1 filing Ludicrous targeted valuation: 1.8T despite 4.28B loss over last year…

Kiss your pensions goodbye, folks May 20 - SpaceX's (SPCX) S-1 filing Ludicrous targeted valuation: 1.8T despite 4.28B loss over last year June 11 - offering price set June 12 - first day of trading /

LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation

arXiv:2605.30651v1 Announce Type: cross Abstract: We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a stu

Learning Controlled Separation of Small Objects Between Two Fingers with a Tactile Skin

arXiv:2605.31486v1 Announce Type: new Abstract: We introduce and solve the novel task of controlled separation of small objects with two fingers of a multi-purpose robotic hand: after grasping into a

Learning Generalizable Robot Policy with Human Demonstration Video as a Prompt

arXiv:2505.20795v2 Announce Type: replace Abstract: Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task,

Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation

arXiv:2605.31343v1 Announce Type: new Abstract: Legged manipulators integrate exceptional terrain adaptability along with mobile manipulation capabilities, which make them highly promising for deploym

Lightweight CNN-Based Anomaly Detection for High Voltage Converter Modulators in the Spallation Neutron Source

arXiv:2605.31259v1 Announce Type: new Abstract: Unscheduled trips of high-power pulsed converters are a leading source of downtime at large accelerator facilities. At the Spallation Neutron Source (SN

LVSA: Training-Free Sparse Attention for Long Video Diffusion

arXiv:2605.31057v1 Announce Type: new Abstract: Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and bey

Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation

arXiv:2605.30365v1 Announce Type: cross Abstract: Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging

arXiv:2605.30904v1 Announce Type: new Abstract: Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconst

Multi-Agent Teams Hold Experts Back

arXiv:2602.01011v4 Announce Type: replace-cross Abstract: Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-spe

Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models

arXiv:2605.30717v1 Announce Type: new Abstract: Language models (LMs) can produce gendered language and stereotypes even when given neutral prompts. Most prior work on gender bias in LMs primarily exa

Neurosymbolic rising!

Neurosymbolic rising! I've wanted to work on deep neurosymbolic integration for a while: if you make an 800k transformer reason *like* a logical solver, you get 100% on sudoku-extreme w. 15m of train

OmniMem: Scalable and Adaptive Memory Retrieval for Long Video Generation

arXiv:2605.30519v1 Announce Type: new Abstract: Autoregressive (AR) video generation extends videos by producing latent chunks sequentially, but scaling to long videos requires repeated access to a gr

On the Illusion of Gender Bias in Face Recognition: Explaining the Fairness Issue Through Non-demographic Attributes

arXiv:2501.12020v2 Announce Type: replace Abstract: Face recognition systems (FRS) exhibit significant accuracy differences based on the user's gender. Since such a gender gap reduces the trustworthin

On the 'Induction Bias' in Sequence Models

arXiv:2602.18333v2 Announce Type: replace-cross Abstract: Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform

On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders

arXiv:2605.31518v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many learned features never activate, a problem called

Optimizing Rank for High-Fidelity Implicit Neural Representations

arXiv:2512.14366v2 Announce Type: replace Abstract: Implicit Neural Representations (INRs) based on vanilla Multi-Layer Perceptrons (MLPs) are widely believed to be incapable of representing high-freq

Organizational Adaptation to Generative AI in Cybersecurity

arXiv:2506.12060v2 Announce Type: replace-cross Abstract: Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influ

PAC-Bayesian Reinforcement Learning Trains Generalizable Policies

arXiv:2510.10544v3 Announce Type: replace-cross Abstract: We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, t

Parallel Tempering Initial Sampling in Inference-Time Reward Alignment

arXiv:2605.30991v1 Announce Type: cross Abstract: Inference-time reward alignment steers pretrained diffusion and flow-based generative models to satisfy user-specified rewards without retraining. Rec

PASTA: A Scalable Framework for Multi-Policy AI Compliance Evaluation

arXiv:2601.11702v3 Announce Type: replace-cross Abstract: AI compliance is becoming increasingly critical as AI systems grow more powerful and pervasive. Yet the rapid expansion of AI policies creates

*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation

arXiv:2602.15778v2 Announce Type: replace Abstract: Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are com

Population-Free Pareto Tracking for Sample-Efficient Multi-Policy MORL

arXiv:2508.02217v2 Announce Type: replace Abstract: Multi-objective reinforcement learning (MORL) is a fundamental framework for real-world decision-making problems involving multiple conflicting crit

PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention

arXiv:2511.17185v2 Announce Type: replace Abstract: We propose PostCam, a streamlined framework for novel-view video generation that achieves superior detail preservation and precise camera trajectory

Prediction: Nobody knows when this will all collapse, but 2026 will be remembered in hindsight as the year in which retail investors and ind…

Prediction: Nobody knows when this will all collapse, but 2026 will be remembered in hindsight as the year in which retail investors and index funds were left holding the bag. It's funny how people th

Preference-Aware Rubric Learning for Personalized Evaluation

arXiv:2605.31545v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve from general-purpose assistants to user-centric agents, personalization has become central to aligning model beha

PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges

arXiv:2605.30803v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric a

Primitive Subspaces Mediate Few-Shot Transfer in VLAs

arXiv:2605.30695v1 Announce Type: new Abstract: Deploying vision-language-action (VLA) policies in industrial environments requires the ability to teach new tasks at low cost, a property current VLAs

Rationalize: Shared Semantic Reasoning for Human-AI Alignment

arXiv:2605.30632v1 Announce Type: cross Abstract: We introduce Rationalize, a role-pair framework for shared semantic reasoning between humans and AI models in data-driven sensemaking. Building on ide

RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning

arXiv:2605.30957v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundament

Reading Between the Citations: A Typed Claim Network for Scientific Literature

arXiv:2605.30966v1 Announce Type: cross Abstract: Knowledge graphs over corpora of inter-referencing documents - scholarly papers, legal opinions, policy briefs - encode the topology of reference but

REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

arXiv:2603.17145v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known a

Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses

arXiv:2504.11972v3 Announce Type: replace Abstract: Extractive QA tasks are commonly evaluated using Exact Match (EM) and F1-score, but these metrics often fail to reflect true model performance. Rece

Reinforced sequential Monte Carlo for amortised sampling

arXiv:2510.11711v2 Announce Type: replace Abstract: This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions. We

Representation Collapse in Sequential Post-Training of Large Language Models

arXiv:2605.30524v1 Announce Type: new Abstract: Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies wh