AI News

RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning (arxiv.org)

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models (arxiv.org)

T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains (arxiv.org)

Assessment of Personality Dimensions Across Situations in Dyadic Role-Play Scenarios (arxiv.org)

LLM-Aided Joint Secrecy Precoding and Trajectory for RSMA-Based Heterogeneous UAV Networks (arxiv.org)

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design (arxiv.org)

ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark (arxiv.org)

Attacks on Machine-Text Detectors Retain Stylistic Fingerprints (arxiv.org)

CleanPatrick: A Benchmark for Image Data Cleaning (arxiv.org)

Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines (arxiv.org)

NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices (arxiv.org)

Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music (arxiv.org)

Visual-TCAV: Concept-based Attribution and Saliency Maps for Post-hoc Explainability in Image Classification (arxiv.org)

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World (arxiv.org)

Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations (arxiv.org)

Designed by Journalists, but Is It for Readers? Rethinking AI Disclosures and Transparency in News (arxiv.org)

Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language Models (arxiv.org)

Building Change Detection in Earthquake: A Multi-Scale Interaction Network and A Change Detection Dataset (arxiv.org)

Content-Induced Spatial-Spectral Aggregation Network for Change Detection in Remote Sensing Images (arxiv.org)

Baseline-Free Policy Optimization for Neural Combinatorial Optimization (arxiv.org)

The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge (arxiv.org)

LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks (arxiv.org)

Towards Robust Arabic Speech Emotion Recognition with Deep Learning (arxiv.org)

Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory (arxiv.org)

Business World Model (arxiv.org)

Overcoming Rank Collapse in Feedback Alignment (arxiv.org)

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning (arxiv.org)

Efficiently Learning Drifting Halfspaces with Massart Noise (arxiv.org)

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning (arxiv.org)

Unifying Local Communications and Local Updates for LLM Pretraining (arxiv.org)

Exploring the Design Space of Reward Backpropagation for Flow Matching (arxiv.org)

DAH-Net: A Dual-Attention Hybrid Network for Interpretable and Robust EEG-Based Emotion Recognition (arxiv.org)

Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors (arxiv.org)

MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning (arxiv.org)

Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs (arxiv.org)

Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective (arxiv.org)

MMD Guidance: Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance (arxiv.org)

SCOPE: Sequential Causal Optimization of Process Interventions (arxiv.org)

Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes (arxiv.org)

When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models (arxiv.org)

Generative Archetype-Grounded Item Representations for Sequential Recommendation (arxiv.org)

Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions (arxiv.org)

Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals (arxiv.org)

Density Field State Space Models: 1-Bit Distillation, Efficient Inference, and Knowledge Organization in Mamba-2 (arxiv.org)

A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS (arxiv.org)

Task Robustness via Re-Labelling Vision-Action Robot Data (arxiv.org)

What Do Deepfake Speech Detectors Actually Hear? (arxiv.org)

Ethical and Technical Limits of Deepfake Speech Datasets (arxiv.org)

Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks (arxiv.org)

RAT: Reference-Augmented Training for ASV Anti-Spoofing (arxiv.org)