CUEBES

Restoring Exploration after Post-Training: Latent Exploration Decoding for Large Reasoning Models

arXiv:2602.01698v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we...

Software Mathematics

arXiv CS Feb 3

Mitigating loss of control in advanced AI systems through instrumental goal trajectories

arXiv:2602.01699v1 Announce Type: new Abstract: Researchers at artificial intelligence labs and universities are concerned that highly capable artificial intelligence (AI) systems may erode human control...

Artificial Intelligence Economics

arXiv CS Feb 3

Tilt-Ropter: A Novel Hybrid Aerial and Terrestrial Vehicle with Tilt Rotors and Passive Wheels

arXiv:2602.01700v1 Announce Type: new Abstract: In this work, we present Tilt-Ropter, a novel hybrid aerial-terrestrial vehicle (HATV) that combines tilt rotors with passive wheels to...

Energy Environment

arXiv CS Feb 3

Meta Engine: A Unified Semantic Query Engine on Heterogeneous LLM-Based Query Systems

arXiv:2602.01701v1 Announce Type: new Abstract: With the increasingly use of multi-modal data, semantic query has become more and more demanded in data management systems, which...

Software Environment

arXiv CS Feb 3

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

arXiv:2602.01703v1 Announce Type: new Abstract: While Large Language Models (LLMs) have achieved remarkable capabilities, they unintentionally memorize sensitive data, posing critical privacy and security risks....

Software Cybersecurity

arXiv CS Feb 3

Beyond Mode Elicitation: Diversity-Preserving Reinforcement Learning via Latent Diffusion Reasoner

arXiv:2602.01705v1 Announce Type: new Abstract: Recent reinforcement learning (RL) methods improve LLM reasoning by optimizing discrete Chain-of-Thought (CoT) generation; however, exploration in token space often...

Policy Biology

arXiv CS Feb 3

Curvature Preserving Fractal Interpolation Functions: A Hybrid Geometric Approach

arXiv:2602.01707v1 Announce Type: new Abstract: Fractal interpolation functions (FIFs) generated using iterated function systems (IFS) provide a powerful framework for modeling self-similar and irregular data,...

Software Energy

arXiv CS Feb 3

Game of Thought: Robust Information Seeking with Large Language Models Using Game Theory

arXiv:2602.01708v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world scenarios where they may lack sufficient information to complete a given...

Software Technology

arXiv CS Feb 3

ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation

arXiv:2602.01709v1 Announce Type: new Abstract: Current test-time scaling (TTS) techniques enhance large language model (LLM) performance by allocating additional computation at inference time, yet they...

Biology Technology

arXiv CS Feb 3

Physics Informed Generative AI Enabling Labour Free Segmentation For Microscopy Analysis

arXiv:2602.01710v1 Announce Type: new Abstract: Semantic segmentation of microscopy images is a critical task for high-throughput materials characterisation, yet its automation is severely constrained by...

Biology Robotics

arXiv CS Feb 3

Optimizing Prompts for Large Language Models: A Causal Approach

arXiv:2602.01711v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly embedded in enterprise workflows, yet their performance remains highly sensitive to prompt design. Automatic...

Embedded Systems Artificial Intelligence

arXiv CS Feb 3

Mapping a Decade of Avian Influenza Research (2014-2023): A Scientometric Analysis from Web of Science

arXiv:2602.01712v1 Announce Type: new Abstract: This scientometric study analyzes Avian Influenza research from 2014 to 2023 using bibliographic data from the Web of Science database....

World News Software

arXiv CS Feb 3

MedAraBench: Large-Scale Arabic Medical Question Answering Dataset and Benchmark

arXiv:2602.01714v1 Announce Type: new Abstract: Arabic remains one of the most underrepresented languages in natural language processing research, particularly in medical applications, due to the...

Software Artificial Intelligence

arXiv CS Feb 3

Mechanistic Indicators of Steering Effectiveness in Large Language Models

arXiv:2602.01716v1 Announce Type: new Abstract: Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its...

Biology Psychology

arXiv CS Feb 3

BBPE16: UTF-16-based byte-level byte-pair encoding for improved multilingual speech recognition

arXiv:2602.01717v1 Announce Type: new Abstract: Multilingual automatic speech recognition (ASR) requires tokenization that efficiently covers many writing systems. Byte-level BPE (BBPE) using UTF-8 is widely...

Psychology Software

arXiv CS Feb 3

Revisiting Generalization Measures Beyond IID: An Empirical Study under Distributional Shift

arXiv:2602.01718v1 Announce Type: new Abstract: Generalization remains a central yet unresolved challenge in deep learning, particularly the ability to predict a model's performance beyond its...

Psychology Policy

arXiv CS Feb 3

COMI: Coarse-to-fine Context Compression via Marginal Information Gain

arXiv:2602.01719v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered...

Software Policy

arXiv CS Feb 3

Phoenix: A Modular and Versatile Framework for C/C++ Pointer Analysis

arXiv:2602.01720v1 Announce Type: new Abstract: We present Phoenix, a modular pointer analysis framework for C/C++ that unifies multiple state-of-the-art alias analysis algorithms behind a single,...

Environment Policy

arXiv CS Feb 3

Scalable Pseudospectral Analysis via Low-Rank Approximations of Dynamical Systems

arXiv:2602.01721v1 Announce Type: new Abstract: Pseudospectral analysis is fundamental for quantifying the sensitivity and transient behavior of nonnormal matrices, yet its computational cost scales cubically...

Psychology Software

arXiv CS Feb 3

FastPhysGS: Accelerating Physics-based Dynamic 3DGS Simulation via Interior Completion and Adaptive Optimization

arXiv:2602.01723v1 Announce Type: new Abstract: Extending 3D Gaussian Splatting (3DGS) to 4D physical simulation remains challenging. Based on the Material Point Method (MPM), existing methods...

Software Physics

arXiv CS Feb 3

DenVisCoM: Dense Vision Correspondence Mamba for Efficient and Real-time Optical Flow and Stereo Estimation

arXiv:2602.01724v1 Announce Type: new Abstract: In this work, we propose a novel Mamba block DenVisCoM, as well as a novel hybrid architecture specifically tailored for...

Psychology Software

arXiv CS Feb 3

SafePred: A Predictive Guardrail for Computer-Using Agents via World Models

arXiv:2602.01725v1 Announce Type: new Abstract: With the widespread deployment of Computer-using Agents (CUAs) in complex real-world environments, prevalent long-term risks often lead to severe and...

Environment Psychology

arXiv CS Feb 3

Cross-Domain Fake News Detection on Unseen Domains via LLM-Based Domain-Aware User Modeling

arXiv:2602.01726v1 Announce Type: new Abstract: Cross-domain fake news detection (CD-FND) transfers knowledge from a source domain to a target domain and is crucial for real-world...

Psychology World News

arXiv CS Feb 3

Voting-based Pitch Estimation with Temporal and Frequential Alignment and Correlation Aware Selection

arXiv:2602.01727v1 Announce Type: new Abstract: The voting method, an ensemble approach for fundamental frequency estimation, is empirically known for its robustness but lacks thorough investigation....

Technology Environment