CUEBES

Chance-Constrained Secrecy Optimization in Hybrid RIS-Empowered and UAV-Assisted Networks

arXiv:2601.22499v1 Announce Type: new Abstract: This paper considers a hybrid reconfigurable environment comprising a UAV-mounted reflecting RIS, an outdoor STAR-RIS enabling simultaneous transmission and reflection,...

Policy Biology

arXiv CS Feb 2

MIRRORTALK: Forging Personalized Avatars Via Disentangled Style and Hierarchical Motion Control

arXiv:2601.22501v1 Announce Type: new Abstract: Synthesizing personalized talking faces that uphold and highlight a speaker's unique style while maintaining lip-sync accuracy remains a significant challenge....

Software Chemistry

arXiv CS Feb 2

Constructing BERT Models: How Team Dynamics and Focus Shape AI Model Impact

arXiv:2601.22505v1 Announce Type: new Abstract: The rapid evolution of AI technologies, exemplified by BERT-family models, has transformed scientific research, yet little is known about their...

Software Technology

arXiv CS Feb 2

DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation

arXiv:2601.22507v1 Announce Type: new Abstract: Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality...

Technology Chemistry

arXiv CS Feb 2

CoVA: Text-Guided Composed Video Retrieval for Audio-Visual Content

arXiv:2601.22508v1 Announce Type: new Abstract: Composed Video Retrieval (CoVR) aims to retrieve a target video from a large gallery using a reference video and a...

Energy Policy

arXiv CS Feb 2

Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks

arXiv:2601.22509v1 Announce Type: new Abstract: Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set...

Neuroscience Software

arXiv CS Feb 2

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic

arXiv:2601.22510v1 Announce Type: new Abstract: Large language models (LLMs) often exhibit unexpected errors or unintended behavior, even at scale. While recent work reveals the discrepancy...

Psychology Policy

arXiv CS Feb 2

Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards

arXiv:2601.22511v1 Announce Type: new Abstract: Small LLMs often struggle to match the agentic capabilities of large, costly models. While reinforcement learning can help, progress has...

Environment Engineering

arXiv CS Feb 2

DRL-Enabled Trajectory Planing for UAV-Assisted VLC: Optimal Altitude and Reward Design

arXiv:2601.22512v1 Announce Type: new Abstract: Recently, the integration of unmanned aerial vehicle (UAV) and visible light communication (VLC) technologies has emerged as a promising solution...

Policy Technology

arXiv CS Feb 2

Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models

arXiv:2601.22513v1 Announce Type: new Abstract: Self-Rewarding Language Models (SRLMs) achieve notable success in iteratively improving alignment without external feedback. Yet, despite their striking empirical progress,...

Psychology Policy

arXiv CS Feb 2

DNA: Uncovering Universal Latent Forgery Knowledge

arXiv:2601.22515v1 Announce Type: new Abstract: As generative AI achieves hyper-realism, superficial artifact detection has become obsolete. While prevailing methods rely on resource-intensive fine-tuning of black-box...

Neuroscience Biology

arXiv CS Feb 2

SCOPE-PD: Explainable AI on Subjective and Clinical Objective Measurements of Parkinson's Disease for Precision Decision-Making

arXiv:2601.22516v1 Announce Type: new Abstract: Parkinson's disease (PD) is a chronic and complex neurodegenerative disorder influenced by genetic, clinical, and lifestyle factors. Predicting this disease...

Artificial Intelligence Health

arXiv CS Feb 2

RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing

arXiv:2601.22517v1 Announce Type: new Abstract: Achieving human-level competitive intelligence and physical agility in humanoid robots remains a major challenge, particularly in contact-rich and highly dynamic...

Robotics Software

arXiv CS Feb 2

Design Perspective on Materials Experience: A CiteSpace-Based Bibliometric and Visual Analysis of Interdisciplinary Research

arXiv:2601.22518v1 Announce Type: new Abstract: Based on a bibliometric analysis of literature from 2005 to 2024, this study reveals that material experience is undergoing a...

Technology Materials Science

arXiv CS Feb 2

One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry

arXiv:2601.22521v1 Announce Type: new Abstract: Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves...

Policy Psychology

arXiv CS Feb 2

Can 3D point cloud data improve automated body condition score prediction in dairy cattle?

arXiv:2601.22522v1 Announce Type: new Abstract: Body condition score (BCS) is a widely used indicator of body energy status and is closely associated with metabolic status,...

Health Software

arXiv CS Feb 2

Variational Bayesian Flow Network for Graph Generation

arXiv:2601.22524v1 Announce Type: new Abstract: Graph generation aims to sample discrete node and edge attributes while satisfying coupled structural constraints. Diffusion models for graphs often...

Engineering Software

arXiv CS Feb 2

Flexible FTN-OTFS for High-Mobility LEO Satellite-to-Ground Communication

arXiv:2601.22526v1 Announce Type: new Abstract: In this paper, a lightweight LEO satellite-assisted flexible faster-than-Nyquist (FTN)-orthogonal time frequency space (OTFS) (LEO-FFTN-OTFS) scheme is proposed to address...

Energy Space & Astronomy

arXiv CS Feb 2

$\rho$-$\texttt{EOS}$: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs

arXiv:2601.22527v1 Announce Type: new Abstract: Beyond parallel generation and global context modeling, current masked diffusion large language models (dLLMs) suffer from a fundamental limitation: they...

Software Psychology

arXiv CS Feb 2

Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution

arXiv:2601.22528v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to...

Environment Software

arXiv CS Feb 2

SHED Light on Segmentation for Dense Prediction

arXiv:2601.22529v1 Announce Type: new Abstract: Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes...

Robotics World News

arXiv CS Feb 2

Enhancing TableQA through Verifiable Reasoning Trace Reward

arXiv:2601.22530v1 Announce Type: new Abstract: A major challenge in training TableQA agents, compared to standard text- and image-based agents, is that answers cannot be inferred...

Environment Psychology

arXiv CS Feb 2

Learn from A Rationalist: Distilling Intermediate Interpretable Rationales

arXiv:2601.22531v1 Announce Type: new Abstract: Because of the pervasive use of deep neural networks (DNNs), especially in high-stakes domains, the interpretability of DNNs has received...

Neuroscience Engineering

arXiv CS Feb 2

Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective

arXiv:2601.22532v1 Announce Type: new Abstract: The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed,...

Psychology Policy