Search: “safety”

Towards Color-Faithful Low-Light Image Enhancement via Adaptive Color Debiasing and Saturation Rectification

arXiv:2608.10512v1 Announce Type: new Abstract: Low-light imaging often introduces color bias caused by the low signal-to-noise ratio and the image formation process. Although recent low-light image e

Safety

TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration

DGX agent

arXiv:2608.10286v1 Announce Type: new Abstract: We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting

safetyarxiv-cs-cv

12 Aug 2026

UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment

arXiv:2608.10316v1 Announce Type: new Abstract: Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shor

Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning

arXiv:2608.11013v1 Announce Type: new Abstract: Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, lead

What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers

arXiv:2603.16840v2 Announce Type: replace Abstract: Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However

What We Know about Responsible AI Practices in Industry: A Half Decade of Empirical Research

arXiv:2608.10431v1 Announce Type: cross Abstract: Responsible AI (RAI) has become a central concern for technology companies, regulators, and the public. How industry practitioners interpret, implemen

When should you start post-training your own models? @FireworksAI_HQ CEO @lqiao’s answer: after product-market fit. Not because it's hard...…

When should you start post-training your own models? @FireworksAI_HQ CEO @lqiao’s answer: after product-market fit. Not because it's hard... but because only after PMF is the data coming off your prod

safetysonya-huang--x

A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning

arXiv:2608.08743v1 Announce Type: cross Abstract: Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time. However, when deployed in high-sta

A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual Data

arXiv:2608.08663v1 Announce Type: cross Abstract: Humans converge on shared names for novel, hard-to-describe objects through repeated interaction, a process psycholinguists call lexical entrainment.

A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable Calibration

arXiv:2608.08689v1 Announce Type: new Abstract: The state evolution of a complex system arises jointly from object laws, relational propagation, domain conservation, and unmodeled error. Forcing all s

Action- and Language-Conditioned Video Assessment for Embodied Control

arXiv:2608.08273v1 Announce Type: cross Abstract: Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete tr

Adaptive Supervised Anchoring for On-Policy Self-Distillation

arXiv:2608.07935v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its ef

Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception

arXiv:2608.08648v1 Announce Type: new Abstract: Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial s

Model Releases

Anchor-Based AI Approach for Pre-Crash Object Detection Utilizing Micro-Doppler Signatures in Automotive Radar

model-releasesarxiv-cs-ro

arXiv:2608.08701v1 Announce Type: new Abstract: Advanced automated driving presents significant potential to improve modern automotive safety systems, but it depends highly on the reliable activation

ArchAgent v2: A Case Study with the Data Prefetching Championship

arXiv:2608.09874v1 Announce Type: new Abstract: Agentic artificial intelligence has shown great promise in automating algorithm design, but scaling similar techniques to computer microarchitecture dis

Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory

arXiv:2406.14373v3 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science

Auditing Instruction-Trajectory Mismatches in Multimodal Robot Demonstrations

arXiv:2608.07895v1 Announce Type: cross Abstract: Robot demonstration datasets used to train vision-language-action policies can contain a subtle but harmful failure mode: trajectories that are behavi

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

arXiv:2510.04465v3 Announce Type: replace-cross Abstract: LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns tha

Beyond Aggregate Calibration: Decomposing Income-Conditional Recall Disparities in Automated Credit Default Prediction

arXiv:2608.08202v1 Announce Type: new Abstract: Data-centric curation pipelines frequently rely on model confidence scores to flag and filter noisy or mislabeled training instances. Evaluating this fi

Beyond Binary: Continuous State Optimization with Graph-Structured Objectives

arXiv:2608.09366v1 Announce Type: new Abstract: Large-scale learning systems often face the challenge of balancing multiple, potentially competing objectives, such as fairness, accuracy, and latency.

Beyond cognacy

arXiv:2507.03005v3 Announce Type: replace Abstract: Computational phylogenetics has become an established tool in historical linguistics, with many language families now analyzed using likelihood-base

safetyarxiv-cs-cl

Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training

arXiv:2608.09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform tas

CDGC-Net: 3D Medical Image Segmentation with Cooperative Dual-Scale Self-Attention and Grouped Channel Modeling

arXiv:2608.08575v1 Announce Type: cross Abstract: Accurate 3D medical image segmentation requires the integration of long-range anatomical context with fine boundary detail. Existing methods often mod

CIFA: Contextual-Intersectional Fairness Auditing for Hidden Subgroup Discovery in Face Analysis

arXiv:2608.09669v1 Announce Type: new Abstract: Fairness evaluation in computer vision commonly relies on aggregate accuracy and demographic subgroup analysis. However, visual models are also sensitiv

CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data

arXiv:2608.08064v1 Announce Type: new Abstract: Learning fine-grained spatial patterns from coarse-resolution data is challenging, especially in causal settings where high-resolution effects must be i

Coarse-to-Fine Registration of Jawbone CT and Intraoral Scan Data Using GeDi and ICP with Pseudo-IOS Ground Truth

arXiv:2608.07564v1 Announce Type: cross Abstract: In digital dentistry and oral surgery, the registration of jawbone CT and intraoral scanner (IOS) data is essential for integrating internal bone stru

Concept-Guided Spatial Regularization for World Models in Atari Pong

arXiv:2607.15142v2 Announce Type: replace Abstract: World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, leaving their standalone reliability understu

Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

arXiv:2608.09688v1 Announce Type: cross Abstract: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head class

Contextual Value Alignment via Multilayer Combinatorial Fusion

arXiv:2608.07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF

Control-Oriented Scenario Tree Construction through Reinforcement Learning

arXiv:2608.09335v1 Announce Type: new Abstract: Multistage stochastic model predictive control (MPC) handles uncertainty by optimizing over a scenario tree, a finite branching approximation of future

Coordinated incentives in AI-generated misinformation governance

arXiv:2608.07070v1 Announce Type: cross Abstract: With the rapid diffusion of AI-generated content, AI-driven misinformation is becoming increasingly pervasive and difficult to govern, undermining inf

CoRCi: Cross-Reconstruction of Coherent Interests Modeling in Cross-Domain Sequential Recommendation

arXiv:2608.09580v1 Announce Type: new Abstract: Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user interests across related domains. A key chall

Correlation flow governs learning at criticality

arXiv:2608.08350v1 Announce Type: new Abstract: The initialisation of deep neural networks determines whether information and gradients can propagate across depth, yet a unified theory connecting thes

CPDA: Class-Conditional Path Distribution Alignment for Unsupervised Time-Series Domain Adaptation

arXiv:2608.09193v1 Announce Type: cross Abstract: Unsupervised time-series domain adaptation (DA) addresses the challenge of transferring a classifier from a labeled source domain to an unlabeled targ

Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids

arXiv:2603.28385v2 Announce Type: replace-cross Abstract: Maritime surveillance missions, such as search and rescue and environmental monitoring, rely on the efficient allocation of sensing assets ove

Crowd-Sourced Geographies of Income: Using Google Maps Points of Interest as High-Frequency Proxies for Sub-Municipal Income Estimation in Sao Paulo, Brazil

arXiv:2608.07871v1 Announce Type: cross Abstract: Accurate, up-to-date income data at the sub-municipal scale is essential for social policy in middle-income countries, yet in Brazil it depends on a c

CUPA-T2: Covariance-Aware Uncertainty Propagation and Alignment for T2 Mapping in Accelerated MRI

arXiv:2608.08693v1 Announce Type: new Abstract: Quantitative T2* maps have strong potential for biomarker discovery but are limited by long scan times, rendering them impractical in clinical settings.

DA-NBV: A Direction-Aware Next-Best-View Planner for Efficient 3D Reconstruction of Ships at Sea

arXiv:2608.08025v1 Announce Type: cross Abstract: Accurate 3D reconstruction of ships at sea is important for maritime supervision, damage assessment, and autonomous maritime operations. Although 3D r

Local Ai

Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE

arXiv:2608.08032v1 Announce Type: new Abstract: Safety alignment in multilingual models is uneven: a model that reliably refuses a harmful request in English will often comply with the same request in

local-aiarxiv-cs-ai

Demystifying Prediction Powered Inference

arXiv:2601.20819v2 Announce Type: replace-cross Abstract: Machine learning predictions are increasingly used to supplement incomplete or costly-to-measure outcomes in fields such as biomedical researc

Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation

arXiv:2604.01742v2 Announce Type: replace Abstract: Crowd instance segmentation is a crucial task with a wide range of applications, including surveillance and transportation. Currently, point labels

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models

arXiv:2608.08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the i

Designing for Ethical AI: HCI Feature Considerations to Improve Fairness and User Experience in AutoML use for Human Resources

arXiv:2608.07477v1 Announce Type: cross Abstract: This thesis examines the fairness of Automated Machine Learning (AutoML) tools in human resource hiring systems through the combined lenses of regulat

Determinization in Structure Theories: A Unified Framework via Closure, Comparability, and Joint Admissibility

arXiv:2608.07476v1 Announce Type: new Abstract: We develop a formal framework for constructing canonical interpretations from plural structure theories. A structure theory is a triple T = ({Sigma}, A,

DiSCo: Diffusion Sequence Copilots for Shared Autonomy

arXiv:2603.22787v2 Announce Type: replace-cross Abstract: Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requir

safetyarxiv-cs-ro

Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models

arXiv:2601.03115v2 Announce Type: replace Abstract: Emotion is a central dimension of spoken communication, yet, we still lack a mechanistic account of how modern large audio-language models (LALMs) e

safetyarxiv-cs-cl

Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation

arXiv:2608.09826v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which acc

Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

arXiv:2608.08815v1 Announce Type: new Abstract: Traffic sign recognition (TSR) models based on deep neural networks achieve strong clean-data performance but remain vulnerable to physically realizable