CUEBES

Gradient-Enhanced Partitioned Gaussian Processes for Real-Time Quadrotor Dynamics Modeling

arXiv:2602.12487v1 Announce Type: new Abstract: We present a quadrotor dynamics Gaussian Process (GP) with gradient information that achieves real-time inference via state-space partitioning and approximation,...

Hardware Software

arXiv CS Feb 16

Insertion Network for Image Sequence Correspondence

arXiv:2602.12489v1 Announce Type: new Abstract: We propose a novel method for establishing correspondence between two sequences of 2D images. One particular application of this technique...

Software Technology

arXiv CS Feb 16

Proving periodic solutions and branches in the 2D Swift Hohenberg PDE with hexagonal and triangular symmetry

arXiv:2602.12491v1 Announce Type: new Abstract: In this article, we enforce space group symmetries in Fourier series to rigorously prove the existence of smooth, periodic solutions...

Software Mathematics

arXiv CS Feb 16

Composable Model-Free RL for Navigation with Input-Affine Systems

arXiv:2602.12492v1 Announce Type: new Abstract: As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating...

Robotics Policy

arXiv CS Feb 16

Layer-Specific Fine-Tuning for Improved Negation Handling in Medical Vision-Language Models

arXiv:2602.12498v1 Announce Type: new Abstract: Negation is a fundamental linguistic operation in clinical reporting, yet vision-language models (VLMs) frequently fail to distinguish affirmative from negated...

Software Medicine & Health

arXiv CS Feb 16

A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models

arXiv:2602.12499v1 Announce Type: new Abstract: The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for...

Politics Policy

arXiv CS Feb 16

Favia: Forensic Agent for Vulnerability-fix Identification and Analysis

arXiv:2602.12500v1 Announce Type: new Abstract: Identifying vulnerability-fixing commits corresponding to disclosed CVEs is essential for secure software maintenance but remains challenging at scale, as large...

Software Technology

arXiv CS Feb 16

Building Large-Scale Drone Defenses from Small-Team Strategies

arXiv:2602.12502v1 Announce Type: new Abstract: Defending against large adversarial drone swarms requires coordination methods that scale effectively beyond conventional multi-agent optimisation. In this paper, we...

Software Robotics

arXiv CS Feb 16

On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

arXiv:2602.12506v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its...

Technology Mathematics

arXiv CS Feb 16

Monocular Reconstruction of Neural Tactile Fields

arXiv:2602.12508v1 Announce Type: new Abstract: Robots operating in the real world must plan through environments that deform, yield, and reconfigure under contact, requiring interaction-aware 3D...

Robotics Neuroscience

arXiv CS Feb 16

Visual RAG Toolkit: Scaling Multi-Vector Visual Retrieval with Training-Free Pooling and Multi-Stage Search

arXiv:2602.12510v1 Announce Type: new Abstract: Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of...

Hardware Technology

arXiv CS Feb 16

Matching of SAR and optical images based on transformation to shared modality

arXiv:2602.12515v1 Announce Type: new Abstract: Significant differences in optical images and Synthetic Aperture Radar (SAR) images are caused by fundamental differences in the physical principles...

Software Biology

arXiv CS Feb 16

Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games

arXiv:2602.12517v1 Announce Type: new Abstract: The intersection of Mean Field Games (MFGs) and Reinforcement Learning (RL) has fostered a growing family of algorithms designed to...

Software Environment

arXiv CS Feb 16

Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings

arXiv:2602.12520v1 Announce Type: new Abstract: Learning to coordinate many agents in partially observable and highly dynamic environments requires both informative representations and data-efficient training. To...

Environment Software

arXiv CS Feb 16

Photonic Rails in ML Datacenters with Opus

arXiv:2602.12521v1 Announce Type: new Abstract: Rail-optimized network fabrics have become the de facto datacenter scale-out fabric for large-scale ML training. However, the use of high-radix...

Engineering Software

arXiv CS Feb 16

LiDAR-Anchored Collaborative Distillation for Robust 2D Representations

arXiv:2602.12524v1 Announce Type: new Abstract: As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful...

Software Climate & Environment

arXiv CS Feb 16

Geometric Stratification for Singular Configurations of the P3P Problem via Local Dual Space

arXiv:2602.12525v1 Announce Type: new Abstract: This paper investigates singular configurations of the P3P problem. Using local dual space, a systematic algebraic-computational framework is proposed to...

Mathematics Policy

arXiv CS Feb 16

Constraint-Rectified Training for Efficient Chain-of-Thought

arXiv:2602.12526v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), especially when combined with reinforcement learning (RL)...

Software Policy

arXiv CS Feb 16

Analytical Results for Two Exponential Family Distributions in Hierarchical Dirichlet Processes

arXiv:2602.12527v1 Announce Type: new Abstract: The Hierarchical Dirichlet Process (HDP) provides a flexible Bayesian nonparametric framework for modeling grouped data with a shared yet unbounded...

Software Mathematics

arXiv CS Feb 16

DiffuRank: Effective Document Reranking with Diffusion Language Models

arXiv:2602.12528v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the...

Biology Genetics

arXiv CS Feb 16

Flow-Factory: A Unified Framework for Reinforcement Learning in Flow-Matching Models

arXiv:2602.12529v1 Announce Type: new Abstract: Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face...

Engineering Energy

arXiv CS Feb 16

Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation

arXiv:2602.12530v1 Announce Type: new Abstract: Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth...

Policy Artificial Intelligence

arXiv CS Feb 16

CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning

arXiv:2602.12532v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown a strong capability in enabling robots to execute general instructions, yet they struggle with contact-rich...

Robotics Psychology

arXiv CS Feb 16

AMPS: Adaptive Modality Preference Steering via Functional Entropy

arXiv:2602.12533v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another....

Biology Psychology