CUEBES

Strengthening Generative Robot Policies through Predictive World Modeling

arXiv:2502.00622v3 Announce Type: replace Abstract: We present generative predictive control (GPC), a learning control framework that (i) clones a generative diffusion-based policy from expert demonstrations,...

Policy Robotics

arXiv CS Mar 10

General Coded Computing in a Probabilistic Straggler Regime

arXiv:2502.00645v2 Announce Type: replace Abstract: Coded computing has demonstrated promising results in addressing straggler resiliency in distributed computing systems. However, most coded computing schemes are...

Software Neuroscience

arXiv CS Mar 10

VL-Nav: A Neuro-Symbolic Approach for Reasoning-based Vision-Language Navigation

arXiv:2502.00931v4 Announce Type: replace Abstract: Navigating unseen, large-scale environments based on complex and abstract human instructions remains a formidable challenge for autonomous mobile robots. Addressing...

Robotics Neuroscience

arXiv CS Mar 10

A Single Model Ensemble Framework for Neural Machine Translation using Pivot Translation

arXiv:2502.01182v2 Announce Type: replace Abstract: Despite the recent remarkable advances in neural machine translation, translation quality for low-resource language pairs remains subpar. Ensembling multiple systems...

Technology Neuroscience

arXiv CS Mar 10

GRADIEND: Feature Learning within Neural Networks Exemplified through Biases

arXiv:2502.01406v4 Announce Type: replace Abstract: AI systems frequently exhibit and amplify social biases, leading to harmful consequences in critical areas. This study introduces a novel...

Software Neuroscience

arXiv CS Mar 10

Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis

arXiv:2502.01853v2 Announce Type: replace Abstract: Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the...

Software Artificial Intelligence

arXiv CS Mar 10

An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks

arXiv:2502.02197v4 Announce Type: replace Abstract: Signed networks, where edges are labeled as positive or negative to represent friendly or antagonistic interactions, provide a natural framework...

Software World News

arXiv CS Mar 10

Controllable Sequence Editing for Biological and Clinical Trajectories

arXiv:2502.03569v3 Announce Type: replace Abstract: Conditional generation models for longitudinal sequences can produce new or modified trajectories given a conditioning input. However, they often lack...

Software Biology

arXiv CS Mar 10

SoK: "Interoperability vs Security" Arguments: A Technical Framework

arXiv:2502.04538v3 Announce Type: replace Abstract: Concerns about big tech's monopoly power have featured prominently in recent media and policy discourse, as regulators across the EU,...

Engineering Software

arXiv CS Mar 10

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs

arXiv:2502.05087v3 Announce Type: replace Abstract: Federated learning (FL) is a popular paradigm for collaborative training which avoids direct data exposure between clients. However, data privacy...

Policy Technology

arXiv CS Mar 10

Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoising

arXiv:2502.06432v3 Announce Type: replace Abstract: Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and...

Software Engineering

arXiv CS Mar 10

Active Advantage-Aligned Online Reinforcement Learning with Offline Data

arXiv:2502.07937v4 Announce Type: replace Abstract: Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In...

Policy Technology

arXiv CS Mar 10

Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative

arXiv:2502.08942v3 Announce Type: replace Abstract: While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving...

Software Policy

arXiv CS Mar 10

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

arXiv:2502.17262v4 Announce Type: replace Abstract: The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for...

Policy Software

arXiv CS Mar 10

HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture

arXiv:2502.19747v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory...

Hardware Technology

arXiv CS Mar 10

Pricing for Routing and Flow-Control in Payment Channel Networks

arXiv:2502.20203v2 Announce Type: replace Abstract: A payment channel network is a blockchain-based overlay mechanism that allows parties to transact more efficiently than directly using the...

Psychology Policy

arXiv CS Mar 10

Diffusion Stabilizer Policy for Automated Surgical Robot Manipulations

arXiv:2503.01252v2 Announce Type: replace Abstract: Intelligent surgical robots have the potential to revolutionize clinical practice by enabling more precise and automated surgical procedures. However, the...

Robotics Policy

arXiv CS Mar 10

The State-Dependent Riccati Equation in Nonlinear Optimal Control: Analysis, Error Estimation and Numerical Approximation

arXiv:2503.01587v2 Announce Type: replace Abstract: The State-Dependent Riccati Equation (SDRE) approach is extensively utilized in nonlinear optimal control as a reliable framework for designing robust...

Technology Chemistry

arXiv CS Mar 10

Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization

arXiv:2503.02312v2 Announce Type: replace Abstract: Machine unlearning aims to remove the influence of problematic training data after a model has been trained. The primary challenge...

Psychology Software

arXiv CS Mar 10

Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft

arXiv:2503.03505v2 Announce Type: replace Abstract: Recent advancements in Large Language Model~(LLM)-based Multi-Agent Systems (MAS) have demonstrated remarkable potential for tackling complex decision-making tasks. However, existing...

Environment Psychology

arXiv CS Mar 10

ViLAM: Distilling Vision-Language Reasoning into Attention Maps for Social Robot Navigation

arXiv:2503.09820v2 Announce Type: replace Abstract: We introduce ViLAM, a novel method for distilling vision-language reasoning from large Vision-Language Models (VLMs) into spatial attention maps for...

Robotics Software

arXiv CS Mar 10

IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models

arXiv:2503.10110v3 Announce Type: replace Abstract: Motion planning involves determining a sequence of robot configurations to reach a desired pose, subject to movement and safety constraints....

Software Biology

arXiv CS Mar 10

Characterizing Nonlinear Dynamics via Smooth Prototype Equivalences

arXiv:2503.10336v2 Announce Type: replace Abstract: Characterizing the long term behavior of dynamical systems given limited measurements is a common challenge throughout the physical and biological...

Psychology Biology

arXiv CS Mar 10

MUSS: Multilevel Subset Selection for Relevance and Diversity

arXiv:2503.11126v3 Announce Type: replace Abstract: The problem of relevant and diverse subset selection has a wide range of applications, including recommender systems and retrieval-augmented generation...

Software World News