CUEBES

Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks

arXiv:2601.21572v1 Announce Type: new Abstract: Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement...

Policy Neuroscience

arXiv CS Jan 30

Chain Of Thought Compression: A Theoritical Analysis

arXiv:2601.21576v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive computational costs...

Biology Psychology

arXiv CS Jan 30

Learning the Mechanism of Catastrophic Forgetting: A Perspective from Gradient Similarity

arXiv:2601.21577v1 Announce Type: new Abstract: Catastrophic forgetting during knowledge injection severely undermines the continual learning capability of large language models (LLMs). Although existing methods attempt...

Neuroscience Psychology

arXiv CS Jan 30

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

arXiv:2601.21579v1 Announce Type: new Abstract: The success of Hyper-Connections (HC) in neural networks (NN) has also highlighted issues related to its training instability and restricted...

Artificial Intelligence Neuroscience

arXiv CS Jan 30

Evaluating Prediction Uncertainty Estimates from BatchEnsemble

arXiv:2601.21581v1 Announce Type: new Abstract: Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble} as...

Biology Software

arXiv CS Jan 30

Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves

arXiv:2601.21582v1 Announce Type: new Abstract: Depth-recurrence facilitates latent reasoning by sharing parameters across depths. However, prior work lacks combined FLOP-, parameter-, and memory-matched baselines, underutilizes...

Politics Policy

arXiv CS Jan 30

CORDS: Continuous Representations of Discrete Structures

arXiv:2601.21583v1 Announce Type: new Abstract: Many learning problems require predicting sets of objects when the number of objects is not known beforehand. Examples include object...

Software Mathematics

arXiv CS Jan 30

Frequency as Aperture: Enabling Embeddable Near-Field Sensing for 6G Wireless Radios

arXiv:2601.21584v1 Announce Type: new Abstract: Integrated sensing and communication (ISAC) is expected to be natively supported by future 6G wireless radios, yet most mmWave sensing...

Technology Cybersecurity

arXiv CS Jan 30

ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses

arXiv:2601.21586v1 Announce Type: new Abstract: In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness against...

Software Cybersecurity

arXiv CS Jan 30

Language Models as Artificial Learners: Investigating Crosslinguistic Influence

arXiv:2601.21587v1 Announce Type: new Abstract: Despite the centrality of crosslinguistic influence (CLI) to bilingualism research, human studies often yield conflicting results due to inherent experimental...

Neuroscience Psychology

arXiv CS Jan 30

Heterogeneity-Aware Knowledge Sharing for Graph Federated Learning

arXiv:2601.21589v1 Announce Type: new Abstract: Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from...

Neuroscience Engineering

arXiv CS Jan 30

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

arXiv:2601.21590v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training is a dominant approach for improving the reasoning performance of large language models (LLMs), yet growing...

Software Artificial Intelligence

arXiv CS Jan 30

Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration

arXiv:2601.21592v1 Announce Type: new Abstract: All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are often...

Policy Psychology

arXiv CS Jan 30

Is My RPC Response Reliable? Detecting RPC Bugs in Ethereum Blockchain Client under Context

arXiv:2601.21593v1 Announce Type: new Abstract: Blockchain clients are fundamental software for running blockchain nodes. They provide users with various RPC (Remote Procedure Call) interfaces to...

Software Technology

arXiv CS Jan 30

HydroSense: A Dual-Microcontroller IoT Framework for Real-Time Multi-Parameter Water Quality Monitoring with Edge Processing and Cloud Analytics

arXiv:2601.21595v1 Announce Type: new Abstract: The global water crisis necessitates affordable, accurate, and real-time water quality monitoring solutions. Traditional approaches relying on manual sampling or...

Technology Environment

arXiv CS Jan 30

Beyond Imitation: Reinforcement Learning for Active Latent Planning

arXiv:2601.21598v1 Announce Type: new Abstract: Aiming at efficient and dense chain-of-thought (CoT) reasoning, latent reasoning methods fine-tune Large Language Models (LLMs) to substitute discrete language...

Policy Software

arXiv CS Jan 30

CORE: Collaborative Reasoning via Cross Teaching

arXiv:2601.21600v1 Announce Type: new Abstract: Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while...

Policy Biology

arXiv CS Jan 30

Dynamics Reveals Structure: Challenging the Linear Propagation Assumption

arXiv:2601.21601v1 Announce Type: new Abstract: Neural networks adapt through first-order parameter updates, yet it remains unclear whether such updates preserve logical coherence. We investigate the...

Neuroscience Engineering

arXiv CS Jan 30

AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation

arXiv:2601.21602v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models have achieved remarkable success in ground-based embodied intelligence, their application to Aerial Manipulation Systems (AMS) remains...

Software Robotics

arXiv CS Jan 30

Age Matters: Analyzing Age-Related Discussions in App Reviews

arXiv:2601.21605v1 Announce Type: new Abstract: In recent years, mobile applications have become indispensable tools for managing various aspects of life. From enhancing productivity to providing...

Software Artificial Intelligence

arXiv CS Jan 30

Search-Based Risk Feature Discovery in Document Structure Spaces under a Constrained Budget

arXiv:2601.21608v1 Announce Type: new Abstract: Enterprise-grade Intelligent Document Processing (IDP) systems support high-stakes workflows across finance, insurance, and healthcare. Early-phase system validation under limited budgets...

Health Biology

arXiv CS Jan 30

RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems

arXiv:2601.21609v1 Announce Type: new Abstract: Agentic recommender systems leverage Large Language Models (LLMs) to model complex user behaviors and support personalized decision-making. However, existing methods...

Psychology Policy

arXiv CS Jan 30

WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models

arXiv:2601.21610v1 Announce Type: new Abstract: Digital watermarking is essential for securing generated images from diffusion models. Accurate watermark evaluation is critical for algorithm development, yet...

Technology Software

arXiv CS Jan 30

Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance

arXiv:2601.21611v1 Announce Type: new Abstract: Effective relevance modeling is crucial for e-commerce search, as it aligns search results with user intent and enhances customer experience....

Software Biology