safety

Emergent Collaborative Deliberation in Multi-Model AI Systems: A BFT-Derived Protocol for Epistemic Synthesis

arXiv:2606.00005v1 Announce Type: new Abstract: We present the Consilium Protocol, a Byzantine Fault Tolerance-derived architecture for structured multi-model AI deliberation that treats inter-model d

Safety

EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion

DGX agent

arXiv:2505.13273v2 Announce Type: replace Abstract: Large text-to-image diffusion models rarely expose reliable signals of when a prompt is likely to produce a poorly aligned generation, especially wh

safetyarxiv-cs-ai

2 Jun 2026

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging

arXiv:2606.02339v1 Announce Type: cross Abstract: Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this

Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization

arXiv:2606.02129v1 Announce Type: new Abstract: Image customization learns target subjects from reference concept images and generates conditioned images per text prompts, mainly modifying styles or b

Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks

arXiv:2606.01602v1 Announce Type: cross Abstract: Pairwise dependence measures such as correlation and causality are fundamental to temporal data mining, yet there is still no principled and robust wa

Evaluating and Learning Robust Bandit Policies Under Uncertain Causal Mechanisms

arXiv:2508.02812v3 Announce Type: replace Abstract: Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowl

Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs

arXiv:2606.01072v1 Announce Type: cross Abstract: Imitation learning enables robots to learn how to execute tasks via observation. However, real-world environments like homes and offices are often sev

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification

arXiv:2606.01160v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used with formal interactive theorem provers such as Lean 4. Scaling these systems with reinforcement lear

Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings

arXiv:2606.02049v1 Announce Type: new Abstract: The increasing integration of renewable energy sources into power systems, particularly in buildings equipped with photovoltaic (PV) panels and energy s

Explainable deep reinforcement learning reveals energy-efficient control strategies for turbulent drag reduction

arXiv:2606.00949v1 Announce Type: cross Abstract: We propose a method combining Multi-Agent Deep Reinforcement Learning (MARL) and eXplainable Deep Learning (XDL) to reduce drag in wall-bounded turbul

Exploiting Similarities in A/B Testing with Off-Policy Estimation

arXiv:2506.10677v3 Announce Type: replace-cross Abstract: We study A/B testing, the standard protocol for measuring the performance gain of a new decision system relative to a baseline. Traditional A/

Failure of contextual invariance in large language models

arXiv:2603.23485v2 Announce Type: replace-cross Abstract: Standard evaluation practices assume that large language model (LLM) outputs are stable when prompts are embedded in contextually equivalent d

Fair Finetuning Mitigates Distribution Inference Attacks

arXiv:2606.01719v1 Announce Type: cross Abstract: Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat k

Fairness in two-player zero-sum games with bandit feedback

arXiv:2606.01159v1 Announce Type: new Abstract: We study two-player zero-sum games (TPZSGs) with bandit feedback under fairness constraints requiring every action to be played with probability at leas

FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting

arXiv:2606.01306v1 Announce Type: new Abstract: While Transformer-based architectures have established themselves as a dominant paradigm in Multivariate Time Series Forecasting (MTSF), their core self

Family Matters: A Systematic Study of Spatial vs. Frequency Masking for Continual Test-Time Adaptation

arXiv:2512.08048v3 Announce Type: replace Abstract: Recent continual test-time adaptation (CTTA) methods adopt masked image modeling to stabilize learning under distribution shift, yet each treats its

Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning

arXiv:2606.01207v1 Announce Type: new Abstract: The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understandi

FedCF: Fair Federated Conformal Prediction

arXiv:2509.22907v2 Announce Type: replace Abstract: Conformal Prediction (CP) is a widely used technique for quantifying uncertainty in machine learning models. In its standard form, CP offers probabi

FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models

arXiv:2511.16992v3 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessne

Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts

arXiv:2606.00967v1 Announce Type: new Abstract: Generative models for volumetric medical images have found many applications in medical imaging, ranging from data augmentation to serving as priors for

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning

arXiv:2510.09222v3 Announce Type: replace Abstract: Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for

Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback

arXiv:2606.02444v1 Announce Type: new Abstract: Recent evidence shows that people with eating disorders (EDs) are increasingly seeking guidance, advice, and emotional support from Large Language Model

Formally Solving Answer-Construction Problems in Lean

arXiv:2505.18492v5 Announce Type: replace Abstract: Mathematical competition problems fall into two broad types: theorem proving, which asks for a proof of a given statement, and answer construction,

Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference

arXiv:2603.12037v2 Announce Type: replace Abstract: Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an i

From Cues to Horizons: Dynamic Risk Horizon Profiling for Trajectory Prediction

arXiv:2606.00857v1 Announce Type: cross Abstract: Accurate and reliable vehicle trajectory prediction is essential for safe autonomous driving. Recent studies have incorporated safety risk into trajec

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

arXiv:2606.00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robot

From Graph Retrieval to Schema Realization: Counterfactual Validation for Text-to-SPARQL over Heterogeneous Knowledge Graphs

arXiv:2508.01815v2 Announce Type: replace-cross Abstract: Text-to-SPARQL maps natural-language questions to executable SPARQL queries over RDF knowledge graphs. While standard evaluations often fix th

From Noise to Control: Parameterized Diffusion Policies

arXiv:2606.00336v1 Announce Type: new Abstract: We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embed

From 'Weak' Signals to Strong Models: Preference Delta Aggregation with LoRA Merging

arXiv:2606.00357v1 Announce Type: new Abstract: Training strong large language models (LLMs) requires high-quality supervision, which is often scarce. Recent work shows that paired preference data fro

FROST-STA: Frozen Dense Features for the Ego4D Short-Term Object Interaction Anticipation

arXiv:2606.00694v1 Announce Type: new Abstract: Short-term anticipation in egocentric video requires more than recognizing the current scene: a system must infer which object the camera wearer will co

GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks

arXiv:2506.16114v3 Announce Type: replace-cross Abstract: Generative recommendations (GR), which usually include item tokenizers and generative Large Language Models (LLMs), have demonstrated remarkab

Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion

arXiv:2606.00637v1 Announce Type: new Abstract: Although reinforcement learning has significantly advanced humanoid locomotion, perceptive policies still struggle on sparse-foothold terrain and constr

safetyarxiv-cs-ro

GovAI-Pipe: A Layered AI Governance Pipeline for Citizen-Facing AI in Turkey's e-Government Gateway

arXiv:2606.01417v1 Announce Type: new Abstract: Turkey's e-Government Gateway (e-Devlet) serves over 68 million registered users with more than 9,200 government services, and is increasingly integrati

Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation

arXiv:2510.18439v3 Announce Type: replace Abstract: Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision-language models and is particularly

safetyarxiv-cs-cl

Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift

arXiv:2512.15647v3 Announce Type: replace Abstract: Soft labels from teacher models are a de facto practice for knowledge transfer and large-scale dataset distillation (e.g., SRe2L, LPLD). However, wh

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses

arXiv:2606.02373v1 Announce Type: new Abstract: Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which

HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems

arXiv:2606.01779v1 Announce Type: new Abstract: LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent

safetyarxiv-cs-cl

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces

arXiv:2606.01117v1 Announce Type: cross Abstract: Extreme multi-label classification (XMC) involves learning models over large output spaces with millions of labels, making the output layer a memory-c

Hierarchical Object Representation for Spatial Robot Perception: Points, Meshes, and Superquadrics

arXiv:2606.01545v1 Announce Type: new Abstract: Hierarchical 3D Scene Graphs (3DSG) have emerged as an actionable and scalable representation for long-term autonomy incorporating metric, semantic, and

safetyarxiv-cs-ro

Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation

arXiv:2606.01565v1 Announce Type: cross Abstract: Vision-Language Navigation in Continuous Environments (VLN-CE) poses a formidable challenge for autonomous agents, requiring seamless integration of n

HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution

arXiv:2606.01157v1 Announce Type: new Abstract: Vector-quantized (VQ) generative models have shown promising results in real-world image super-resolution (Real-ISR). However, existing methods typicall

HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression

arXiv:2606.01934v1 Announce Type: cross Abstract: Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial infere

safetyarxiv-cs-cl

HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads

arXiv:2606.00252v1 Announce Type: cross Abstract: Manipulating suspended payloads with humanoid robots is challenging because the robot can only influence an underactuated, oscillatory load through wh

HOLA: Holistic Multi-Modal Alignment for Open-Set 3D Recognition

arXiv:2606.01334v1 Announce Type: new Abstract: Open-set 3D recognition requires models that generalize to rare or unseen categories. Recent approaches address this by distilling language-vision knowl

Hot-Start Chinese Language Modeling:Visual Glyphs Accelerate Sample-Efficient Learning

arXiv:2601.09566v4 Announce Type: replace-cross Abstract: In this work, we study whether rendering Chinese characters as visual glyph images, rather than discrete token IDs as mainstream LLMs do, prov

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning

arXiv:2606.02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the mode

How Much Progress Has There Been in NVIDIA Datacenter GPUs?

arXiv:2601.20115v3 Announce Type: replace-cross Abstract: As the role of modern Graphics Processing Units (GPUs) becomes increasingly essential for several computing tasks, analyzing their past and cu

Hybrid TD3: Overestimation Bias Analysis and Stable Policy Optimization for Hybrid Action Space

arXiv:2603.01302v2 Announce Type: replace Abstract: Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task d

safetyarxiv-cs-ro