Search: “safety”

Multimodal Dataset Normalization and Perceptual Validation for Music-Taste Correspondences

arXiv:2604.10632v1 Announce Type: cross Abstract: Collecting large, aligned cross-modal datasets for music-flavor research is difficult because perceptual experiments are costly and small by design. W

Safety

Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS

DGX agent

arXiv:2604.11142v1 Announce Type: new Abstract: Low-light conditions severely hinder 3D restoration and reconstruction by degrading image visibility, introducing color distortions, and contaminating g

safetyarxiv-cs-cv

14 Apr 2026

NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data

arXiv:2604.10401v1 Announce Type: new Abstract: Inferring nationality from personal names is a critical capability for equity and bias monitoring, personalization, and a valuable tool in biomedical an

Normative Common Ground Replication (NormCoRe): Replication-by-Translation for Studying Norms in Multi-Agent AI

arXiv:2603.11974v2 Announce Type: replace Abstract: In the late 2010s, the fashion trend NormCore framed sameness as a signal of belonging, illustrating how norms emerge through collective coordinatio

NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning

arXiv:2604.10452v1 Announce Type: new Abstract: Olfaction lies at the intersection of chemical structure, neural encoding, and linguistic perception, yet existing representation methods fail to fully

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

arXiv:2504.13818v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large langua

OmniUMI: Towards Physically Grounded Robot Learning via Human-Aligned Multimodal Interaction

arXiv:2604.10647v1 Announce Type: new Abstract: UMI-style interfaces enable scalable robot learning, but existing systems remain largely visuomotor, relying primarily on RGB observations and trajector

safetyarxiv-cs-ro

On the Effectiveness of Textual Prompting with Lightweight Fine-Tuning for SAM3 Remote Sensing Segmentation

arXiv:2512.15564v2 Announce Type: replace Abstract: Remote sensing (RS) image segmentation is constrained by the limited availability of annotated data and a gap between overhead imagery and natural i

Orthogonal machine learning for conditional odds and risk ratios

arXiv:2604.10412v1 Announce Type: cross Abstract: Conditional effects are commonly used measures for understanding how treatment effects vary across different groups, and are often used to target trea

PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery

arXiv:2604.11484v1 Announce Type: new Abstract: On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an o

Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images

arXiv:2604.10085v1 Announce Type: new Abstract: We propose a robust alignment technique for Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs), which are challenging to align due

PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decoding

arXiv:2412.11390v3 Announce Type: replace-cross Abstract: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the brain and external devices. Howeve

Perceptual Inductive Bias Is What You Need Before Contrastive Learning

arXiv:2506.01201v2 Announce Type: replace Abstract: David Marr's seminal theory of human perception stipulates that visual processing is a multi-stage process, prioritizing the derivation of boundary

PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency

arXiv:2603.25620v2 Announce Type: replace Abstract: Large language model (LLM)-based persona agents are rapidly being adopted as scalable proxies for human participants across diverse domains. Yet the

Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization

arXiv:2604.11510v1 Announce Type: cross Abstract: To encourage diverse exploration in reinforcement learning (RL) for large language models (LLMs) without compromising accuracy, we propose Policy Spli

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

arXiv:2509.21882v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other s

Predictions can be weapons of power. They only work if we believe them. -@carissaveliz @TEDTalks 2026

Carissa Véliz delivered a TED Talk in 2026 arguing that predictions function as instruments of power, shaping behavior and outcomes through the act of belief itself. Her thesis suggests that predictiv

safetygary-marcus--x

Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation

arXiv:2603.20725v2 Announce Type: replace Abstract: Text-to-image generation has advanced rapidly, yet it still struggles to capture the nuanced user preferences. Existing approaches typically rely on

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

arXiv:2604.10030v1 Announce Type: new Abstract: Video diffusion models have achieved remarkable progress in generating high-quality videos. However, these models struggle to represent the temporal suc

ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction

arXiv:2604.10633v1 Announce Type: new Abstract: LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases trainin

Proximal Supervised Fine-Tuning

arXiv:2508.17784v2 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new

QFS-Composer: Query-focused summarization pipeline for less resourced languages

arXiv:2604.10687v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance in text summarization, yet their effectiveness drops significantly across languages with res

Quantifying the Climate Risk of Generative AI: Region-Aware Carbon Accounting with G-TRACE and the AI Sustainability Pyramid

arXiv:2511.04776v2 Announce Type: replace-cross Abstract: Generative Artificial Intelligence (GenAI) represents a rapidly expanding digital infrastructure whose energy demand and associated CO2 emissi

RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation

arXiv:2604.10960v1 Announce Type: new Abstract: Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT

RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought

arXiv:2506.16796v4 Announce Type: replace Abstract: Real-World Image Super-Resolution is one of the most challenging task in image restoration. However, existing methods struggle with an accurate unde

Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation

arXiv:2604.09916v1 Announce Type: new Abstract: Simultaneous Speech Translation (SimulST) requires balancing high translation quality with low latency. Recent work introduced REINA, a method that trai

Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management

arXiv:2406.05358v3 Announce Type: replace Abstract: Intensity control is a class of continuous-time dynamic optimization problems with many important applications in Operations Research including queu

Relative Entropy Pathwise Policy Optimization

arXiv:2507.11019v4 Announce Type: replace Abstract: Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their h

Reliable Evaluation Protocol for Low-Precision Retrieval

arXiv:2508.03306v4 Announce Type: replace-cross Abstract: Lowering the numerical precision of model parameters and computations is widely adopted to improve the efficiency of retrieval systems. Howeve

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

arXiv:2603.14968v2 Announce Type: replace-cross Abstract: While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, req

Rethinking Token-Level Credit Assignment in RLVR: A Polarity-Entropy Analysis

arXiv:2604.11056v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has substantially improved the reasoning ability of Large Language Models (LLMs). However, its s

Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference

arXiv:2604.11496v1 Announce Type: cross Abstract: Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

arXiv:2505.24778v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically exp

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

arXiv:2604.10688v1 Announce Type: cross Abstract: On-policy reinforcement learning has become the dominant paradigm for reasoning alignment in large language models, yet its sparse, outcome-level rewa

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

arXiv:2604.07791v2 Announce Type: replace Abstract: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. Wit

See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment

arXiv:2604.09749v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding i

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance

arXiv:2510.07972v3 Announce Type: replace Abstract: Query-product relevance prediction is vital for AI-driven e-commerce, yet current LLM-based approaches face a dilemma: SFT and DPO struggle with lon

Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD

arXiv:2604.10373v1 Announce Type: cross Abstract: From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min-max optimization or, more generally, as

SIMPLER: H&E-Informed Representation Learning for Structured Illumination Microscopy

arXiv:2604.10334v1 Announce Type: new Abstract: Structured Illumination Microscopy (SIM) enables rapid, high-contrast optical sectioning of fresh tissue without staining or physical sectioning, making

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

arXiv:2604.10674v1 Announce Type: cross Abstract: Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited b

SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation

arXiv:2604.11466v1 Announce Type: cross Abstract: Large Language Model (LLM) agents offer a potentially-transformative path forward for generative social science but face a critical crisis of validity

Some opportunities you just can't turn down, like when @GaryMarcus wants to come talk about AI at BugBash. Fewer than 20 tickets left, come …

Gary Marcus, a prominent AI researcher and critic known for his skepticism of current deep learning approaches, was invited to speak at BugBash, an event hosted by Antithesis. The post, shared by Anti

safetygary-marcus--x

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

arXiv:2510.05057v2 Announce Type: replace-cross Abstract: A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and d

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

arXiv:2604.05549v2 Announce Type: replace Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team

Structural Consequences of Policy-Based Interventions on the Global Supply Chain Network

arXiv:2604.11479v1 Announce Type: new Abstract: As global political tensions rise and the anticipation of additional tariffs from the United States on international trade increases, the issues of econ

Structural Gating and Effect-aligned Lag-resolved Temporal Causal Discovery Framework with Application to Heat-Pollution Extremes

arXiv:2604.10371v1 Announce Type: new Abstract: This study proposes Structural Gating and Effect-aligned Discovery for Temporal Causal Discovery (SGED-TCD), a novel and general framework for lag-resol

Structured Causal Video Reasoning via Multi-Objective Alignment

arXiv:2604.04415v2 Announce Type: replace Abstract: Human understanding of video dynamics is typically grounded in a structured mental representation of entities, actions, and temporal relations, rath

SVD-Prune: Training-Free Token Pruning For Efficient Vision-Language Models

arXiv:2604.11530v1 Announce Type: cross Abstract: Vision-Language Models (VLM) have revolutionized multimodal learning by jointly processing visual and textual information. Yet, they face significant