Search: “papers”

Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods

arXiv:2604.20243v1 Announce Type: new Abstract: Color constancy is a fundamental ability of many biological visual systems and a crucial step in computer imaging systems. Bio-inspired modeling offers

CHASM: Unveiling Covert Advertisements on Chinese Social Media

DGX agent

arXiv:2604.20511v1 Announce Type: cross Abstract: Current benchmarks for evaluating large language models (LLMs) in social media moderation completely overlook a serious threat: covert advertisements,

applicationsarxiv-cs-ai

23 Apr 2026

CHORUS: An Agentic Framework for Generating Realistic Deliberation Data

arXiv:2604.20651v1 Announce Type: new Abstract: Understanding the intricate dynamics of online discourse depends on large-scale deliberation data, a resource that remains scarce across interactive web

agentsarxiv-cs-ai

CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment

arXiv:2510.18471v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between the

Tutorials

Combo-Gait: Unified Transformer Framework for Multi-Modal Gait Recognition and Attribute Analysis

arXiv:2510.10417v2 Announce Type: replace-cross Abstract: Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environm

tutorialsarxiv-cs-ai

ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

model-releasesarxiv-cs-cv

arXiv:2604.20358v1 Announce Type: new Abstract: The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on exp

Applications

Continuous Semantic Caching for Low-Cost LLM Serving

arXiv:2604.20021v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries h

applicationsarxiv-cs-cl

Cover meets Robbins while Betting on Bounded Data: ln n Regret and Almost Sure lnln n Regret

arXiv:2604.20172v1 Announce Type: new Abstract: Consider betting against a sequence of data in [0,1], where one is allowed to make any bet that is fair if the data have a conditional mean m_0 in (0,1)

CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction

arXiv:2505.04897v2 Announce Type: replace-cross Abstract: Interactive imitation learning makes an agent's control policy robust by stepwise supervisions from an expert. The recent algorithms mostly em

safetyarxiv-cs-lg

Development and Preliminary Evaluation of a Domain-Specific Large Language Model for Tuberculosis Care in South Africa

model-releasesarxiv-cs-cl

arXiv:2604.19776v1 Announce Type: new Abstract: Tuberculosis (TB) is one of the world's deadliest infectious diseases, and in South Africa, it contributes a significant burden to the country's health

Distributional Value Estimation Without Target Networks for Robust Quality-Diversity

arXiv:2604.20381v1 Announce Type: new Abstract: Quality-Diversity (QD) algorithms excel at discovering diverse repertoires of skills, but are hindered by poor sample efficiency and often require tens

Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models

arXiv:2604.01965v2 Announce Type: replace-cross Abstract: Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary syst

Efficiently Closing Loops in LiDAR-Based SLAM Using Point Cloud Density Maps

arXiv:2501.07399v2 Announce Type: replace Abstract: Consistent maps are key for most autonomous mobile robots, and they often use SLAM approaches to build such maps. Loop closures via place recognitio

safetyarxiv-cs-ro

Applications

Energy-Based Open-Set Active Learning for Object Classification

arXiv:2604.20083v1 Announce Type: cross Abstract: Active learning (AL) has emerged as a crucial methodology for minimizing labeling costs in deep learning by selecting the most valuable samples from a

applicationsarxiv-cs-cv

Enhancing Speaker Verification with Whispered Speech via Post-Processing

arXiv:2604.20229v1 Announce Type: cross Abstract: Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated spee

Epistemic Constitutionalism Or: how to avoid coherence bias

arXiv:2601.14295v3 Announce Type: replace Abstract: Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their

EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Strategies

arXiv:2509.03335v3 Announce Type: replace Abstract: In traffic engineering, fixed-time traffic signal control remains widely used for its low cost, stability, and interpretability. However, its design

agentsarxiv-cs-lg

Fairness Testing of Large Language Models in Role-Playing

arXiv:2411.00585v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have become foundational in modern language-driven software applications, profoundly influencing daily life. A cr

FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

arXiv:2604.20825v1 Announce Type: cross Abstract: Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed client

Fextsuperscript{2}LP-AP: Fast & Flexible Label Propagation with Adaptive Propagation Kernel

model-releasesarxiv-cs-lg

arXiv:2604.20736v1 Announce Type: new Abstract: Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by

Finding Duplicates in 1.1M BDD Steps: cukereuse, a Paraphrase-Robust Static Detector for Cucumber and Gherkin

model-releasesarxiv-cs-cl

arXiv:2604.20462v1 Announce Type: cross Abstract: Behaviour-Driven Development (BDD) suites accumulate step-text duplication whose maintenance cost is established in prior work. Existing detection tec

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

arXiv:2603.09046v2 Announce Type: replace-cross Abstract: Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs

agentsarxiv-cs-lg

FLOSS: Federated Learning with Opt-Out and Straggler Support

arXiv:2507.23115v2 Announce Type: replace-cross Abstract: Previous work on data privacy in federated learning systems focuses on privacy-preserving operations for data from users who have agreed to sh

Tutorials

Foundational Design Principles and Patterns for Building Robust and Adaptive GenAI-Native Systems

arXiv:2508.15411v3 Announce Type: replace-cross Abstract: Generative AI (GenAI) has emerged as a transformative technology, demonstrating remarkable capabilities across diverse application domains. Ho

tutorialsarxiv-cs-cl

From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents

arXiv:2604.19775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.

agentsarxiv-cs-ai

From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLP

arXiv:2510.12817v3 Announce Type: replace-cross Abstract: Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the diversity of human perspectives rather than mere

From Scene to Object: Text-Guided Dual-Gaze Prediction

arXiv:2604.20191v1 Announce Type: cross Abstract: Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaz

FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory

arXiv:2604.20300v1 Announce Type: new Abstract: For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--

Generalization and Membership Inference Attack a Practical Perspective

arXiv:2604.19936v1 Announce Type: cross Abstract: With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previ

GeoRect4D: Geometry-Compatible Generative Rectification for Dynamic Sparse-View 3D Reconstruction

arXiv:2604.20784v1 Announce Type: new Abstract: Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

arXiv:2604.19790v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed under diverse numerical precision configurations, including standard floating-point formats (e.g.

High-Level Multi-Robot Trajectory Planning And Spurious Behavior Detection

arXiv:2510.17261v2 Announce Type: replace-cross Abstract: The reliable execution of high-level missions in multi-robot systems with heterogeneous agents, requires robust methods for detecting spurious

How Will My Business Process Unfold? Predicting Case Suffixes With Start and End Timestamps

arXiv:2509.14536v3 Announce Type: replace Abstract: Predictive process monitoring supports operational decision-making by forecasting future states of ongoing business cases. A key task is case suffix

HumanScore: Benchmarking Human Motions in Generated Videos

arXiv:2604.20157v1 Announce Type: new Abstract: Recent advances in model architectures, compute, and data scale have driven rapid progress in video generation, producing increasingly realistic content

Improving End-to-End Training of Retrieval-Augmented Generation Models via Joint Stochastic Approximation

arXiv:2508.18168v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) has become a widely recognized paradigm to combine parametric memory with non-parametric memories. An RAG model

researcharxiv-cs-cl

Applications

Improving Large-Scale Recommender Systems with Auxiliary Learning

arXiv:2510.02215v3 Announce Type: replace Abstract: Training large-scale recommendation models under a single global objective implicitly assumes homogeneity across user populations. However, real-wor

applicationsarxiv-cs-lg

Intersectional Fairness in Large Language Models

model-releasesarxiv-cs-cl

arXiv:2604.20677v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across i

Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity

arXiv:2402.06266v2 Announce Type: replace Abstract: Multi-objective reinforcement learning (MORL) algorithms extend conventional reinforcement learning (RL) to the more general case of problems with m

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

arXiv:2505.07527v5 Announce Type: replace Abstract: The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Pol

safetyarxiv-cs-lg

KoALa-Bench: Evaluating Large Audio Language Models on Korean Speech Understanding and Faithfulness

arXiv:2604.19782v1 Announce Type: cross Abstract: Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain

LayerTracer: A Joint Task-Particle and Vulnerable-Layer Analysis framework for Arbitrary Large Language Model Architectures

arXiv:2604.20556v1 Announce Type: cross Abstract: Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. How

Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems

arXiv:2604.20745v1 Announce Type: cross Abstract: Federated continual learning (FCL) allows distributed autonomous fleets to adapt collaboratively to evolving terrain types across extended mission lif

agentsarxiv-cs-cv

Lucky High Dynamic Range Smartphone Imaging

arXiv:2604.19976v1 Announce Type: new Abstract: While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite dec

Machine learning moment closure models for the radiative transfer equation IV: enforcing symmetrizable hyperbolicity in two dimensions

arXiv:2604.20143v1 Announce Type: cross Abstract: This is our fourth work in the series on machine learning (ML) moment closure models for the radiative transfer equation (RTE). In the first three pap

MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation

arXiv:2604.20286v1 Announce Type: cross Abstract: Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, the

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning

arXiv:2604.20074v1 Announce Type: new Abstract: A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm succe

Measuring Creativity in the Age of Generative AI: Distinguishing Human and AI-Generated Creative Performance in Hiring and Talent Systems

arXiv:2604.19799v1 Announce Type: cross Abstract: Generative AI is rapidly transforming how organizations create value and evaluate talent. While large language models enhance baseline output quality,

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

model-releasesarxiv-cs-lg

arXiv:2412.14590v2 Announce Type: replace Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions sti