CUEBES

Sparse Concept Anchoring for Interpretable and Controllable Neural Representations

arXiv:2512.12469v2 Announce Type: replace Abstract: We introduce Sparse Concept Anchoring, a method that biases latent space to position a targeted subset of concepts while allowing...

Software Neuroscience

arXiv CS Jan 28

Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection

arXiv:2512.12884v2 Announce Type: replace Abstract: In automotive sensor fusion systems, smart sensors and Vehicle-to-Everything (V2X) modules are commonly utilized. Sensor data from these systems are...

Software Biology

arXiv CS Jan 28

Modeling Collaborative Problem Solving Dynamics from Group Discourse: A Text-Mining Approach with Synergy Degree Model

arXiv:2512.13061v2 Announce Type: replace Abstract: Measuring collaborative problem solving (CPS) synergy remains challenging in learning analytics, as classical manual coding cannot capture emergent system-level dynamics....

Artificial Intelligence Genetics

arXiv CS Jan 28

neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings

arXiv:2512.13481v2 Announce Type: replace Abstract: Envy shapes competitiveness and cooperation in human groups, yet its role in large language model interactions remains largely unexplored. As...

Neuroscience Artificial Intelligence

arXiv CS Jan 28

ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs

arXiv:2512.14908v3 Announce Type: replace Abstract: We present ATLAS (Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs), a novel graph learning algorithm that addresses...

Artificial Intelligence Neuroscience

arXiv CS Jan 28

Reexamining Paradigms of End-to-End Data Movement

arXiv:2512.15028v3 Announce Type: replace Abstract: The pursuit of high-performance data transfer often focuses on raw network bandwidth, where international links of 100 Gbps or higher...

Technology Software

arXiv CS Jan 28

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?

arXiv:2512.15468v2 Announce Type: replace Abstract: The success of large language models for code relies on vast amounts of code data, including public open-source repositories, such...

Technology Software

arXiv CS Jan 28

Data Valuation for LLM Fine-Tuning: Efficient Shapley Value Approximation via Language Model Arithmetic

arXiv:2512.15765v2 Announce Type: replace Abstract: Data is a critical asset for training large language models (LLMs), alongside compute resources and skilled workers. While some training...

Software Artificial Intelligence

arXiv CS Jan 28

OLAF: Towards Robust LLM-Based Annotation Framework in Empirical Software Engineering

arXiv:2512.15979v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as...

Engineering Technology

arXiv CS Jan 28

Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms

arXiv:2512.16034v2 Announce Type: replace Abstract: Recent work has explored the use of personal information in the form of persona sentences or self-disclosures to improve modeling...

arXiv CS Jan 28

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

arXiv:2512.16912v3 Announce Type: replace Abstract: This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of...

Artificial Intelligence

arXiv CS Jan 28

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

arXiv:2512.17008v2 Announce Type: replace Abstract: Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying...

Artificial Intelligence Software

arXiv CS Jan 28

A Reproducible and Fair Evaluation of Partition-aware Collaborative Filtering

arXiv:2512.17015v3 Announce Type: replace Abstract: Similarity-based collaborative filtering (CF) models have long demonstrated strong offline performance and conceptual simplicity. However, their scalability is limited by...

arXiv CS Jan 28

GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping

arXiv:2512.17570v2 Announce Type: replace Abstract: SSD-offloaded training offers a practical and promising approach to making LLM training cost-effective. Building on gradient accumulation with micro-batches, this...

Artificial Intelligence Software

arXiv CS Jan 28

SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

arXiv:2512.18470v4 Announce Type: replace Abstract: Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or implementing a small...

Software Engineering

arXiv CS Jan 28

Sprecher Networks: A Parameter-Efficient Kolmogorov-Arnold Architecture

arXiv:2512.19367v2 Announce Type: replace Abstract: We introduce Sprecher Networks (SNs), a family of trainable architectures derived from David Sprecher's 1965 constructive form of the Kolmogorov-Arnold...

Biology Materials Science

arXiv CS Jan 28

Kolmogorov-Arnold graph neural networks for chemically informed prediction tasks on inorganic nanomaterials

arXiv:2512.19494v2 Announce Type: replace Abstract: The recent development of Kolmogorov-Arnold Networks (KANs) has found its application in the field of Graph Neural Networks (GNNs) particularly...

Materials Science Chemistry

arXiv CS Jan 28

CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal

arXiv:2512.19554v2 Announce Type: replace Abstract: Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all...

Software Space & Astronomy

arXiv CS Jan 28

Gaussian Variational Inference with Non-Gaussian Factors for State Estimation: A UWB Localization Case Study

arXiv:2512.19855v2 Announce Type: replace Abstract: This letter extends the exactly sparse Gaussian variational inference (ESGVI) algorithm for state estimation in two complementary directions. First, ESGVI...

Software Artificial Intelligence

arXiv CS Jan 28

SLIDE: Simultaneous Model Downloading and Inference at the Wireless Network Edge

arXiv:2512.20946v2 Announce Type: replace Abstract: To support on-device inference, the next-generation mobile networks are expected to support real-time model downloading services to mobile users. However,...

Artificial Intelligence Energy

arXiv CS Jan 28

One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents

arXiv:2512.20957v5 Announce Type: replace Abstract: Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing...

Software Artificial Intelligence

arXiv CS Jan 28

LLM Personas as a Substitute for Field Experiments in Method Benchmarking

arXiv:2512.21080v2 Announce Type: replace Abstract: Field experiments (A/B tests) are often the most credible benchmark for methods (algorithms) in societal systems, but their cost and...

Artificial Intelligence Software

arXiv CS Jan 28

MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models

arXiv:2512.21231v3 Announce Type: replace Abstract: Large Language Models can develop reasoning capabilities through online fine-tuning with rule-based rewards. However, recent studies reveal a critical constraint:...

Chemistry Materials Science

arXiv CS Jan 28

A Reinforcement Learning Approach to Synthetic Data Generation

arXiv:2512.21395v2 Announce Type: replace Abstract: Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet,...

Software Cybersecurity