CUEBES

Few-Shot Domain Adaptation with Temporal References and Static Priors for Glacier Calving Front Delineation

arXiv:2601.21663v1 Announce Type: new Abstract: During benchmarking, the state-of-the-art model for glacier calving front delineation achieves near-human performance. However, when applied in a real-world setting...

World News Software

arXiv CS Jan 30

SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework

arXiv:2601.21664v1 Announce Type: new Abstract: Bridging the gap between data-rich training regimes and observation-sparse deployment conditions remains a central challenge in spatiotemporal field reconstruction, particularly...

Engineering Software

arXiv CS Jan 30

AdaptBPE: From General Purpose to Specialized Tokenizers

arXiv:2601.21665v1 Announce Type: new Abstract: Subword tokenization methods, such as Byte-Pair Encoding (BPE), significantly impact the performance and efficiency of large language models (LLMs). The...

Software Artificial Intelligence

arXiv CS Jan 30

SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding

arXiv:2601.21666v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static...

Artificial Intelligence Psychology

arXiv CS Jan 30

From Instruction to Event: Sound-Triggered Mobile Manipulation

arXiv:2601.21667v1 Announce Type: new Abstract: Current mobile manipulation research predominantly follows an instruction-driven paradigm, where agents rely on predefined textual commands to execute tasks. However,...

Software Policy

arXiv CS Jan 30

A Hybrid semi-Lagrangian Flow Mapping Approach for Vlasov Systems: Combining Iterative and Compositional Flow Maps

arXiv:2601.21668v1 Announce Type: new Abstract: We propose a hybrid semi-Lagrangian scheme for the Vlasov--Poisson equation that combines the Numerical Flow Iteration (NuFI) method with the...

Software Engineering

arXiv CS Jan 30

Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling

arXiv:2601.21669v1 Announce Type: new Abstract: Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a...

Policy Engineering

arXiv CS Jan 30

When Gradient Optimization Is Not Enough: $\dagger$ Dispersive and Anchoring Geometric Regularizer for Multimodal Learning

arXiv:2601.21670v1 Announce Type: new Abstract: Multimodal learning aims to integrate complementary information from heterogeneous modalities, yet strong optimization alone does not guaranty well-structured representations. Even...

Energy Policy

arXiv CS Jan 30

Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification

arXiv:2601.21673v1 Announce Type: new Abstract: High-dimensional structural MRI (sMRI) images are widely used for Alzheimer's Disease (AD) diagnosis. Most existing methods for sMRI representation learning...

Software Energy

arXiv CS Jan 30

Rethinking Fusion: Disentangled Learning of Shared and Modality-Specific Information for Stance Detection

arXiv:2601.21675v1 Announce Type: new Abstract: Multi-modal stance detection (MSD) aims to determine an author's stance toward a given target using both textual and visual content....

Software Energy

arXiv CS Jan 30

Scale-Dependent Semantic Dynamics Revealed by Allan Deviation

arXiv:2601.21678v1 Announce Type: new Abstract: While language progresses through a sequence of semantic states, the underlying dynamics of this progression remain elusive. Here, we treat...

Policy Technology

arXiv CS Jan 30

BAP-SRL: Bayesian Adaptive Priority Safe Reinforcement Learning for Vehicle Motion Planning at Mixed Traffic Intersections

arXiv:2601.21679v1 Announce Type: new Abstract: Navigating urban intersections, especially when interacting with heterogeneous traffic participants, presents a formidable challenge for autonomous vehicles (AVs). In such...

Biology Robotics

arXiv CS Jan 30

Incremental Fingerprinting in an Open World

arXiv:2601.21680v1 Announce Type: new Abstract: Network protocol fingerprinting is used to identify a protocol implementation by analyzing its input-output behavior. Traditionally, fingerprinting operates under a...

Psychology Software

arXiv CS Jan 30

LLM4Fluid: Large Language Models as Generalizable Neural Solvers for Fluid Dynamics

arXiv:2601.21681v1 Announce Type: new Abstract: Deep learning has emerged as a promising paradigm for spatio-temporal modeling of fluid dynamics. However, existing approaches often suffer from...

Software Artificial Intelligence

arXiv CS Jan 30

FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning

arXiv:2601.21682v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate impressive capabilities across diverse tasks but raise concerns about privacy, copyright, and harmful materials. Existing...

Materials Science Cybersecurity

arXiv CS Jan 30

Can Local Learning Match Self-Supervised Backpropagation?

arXiv:2601.21683v1 Announce Type: new Abstract: While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised...

Artificial Intelligence Neuroscience

arXiv CS Jan 30

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling

arXiv:2601.21684v1 Announce Type: new Abstract: Test-Time Scaling enhances the reasoning capabilities of Large Language Models by allocating additional inference compute to broaden the exploration of...

Finance Policy

arXiv CS Jan 30

Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold

arXiv:2601.21686v1 Announce Type: new Abstract: Key--value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM)...

Software Policy

arXiv CS Jan 30

XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision

arXiv:2601.21688v1 Announce Type: new Abstract: Disentangled representation learning aims to map independent factors of variation to independent representation components. On one hand, purely unsupervised approaches...

Software Quantum Computing

arXiv CS Jan 30

Understanding Model Merging: A Unified Generalization Framework for Heterogeneous Experts

arXiv:2601.21690v1 Announce Type: new Abstract: Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original...

Environment Policy

arXiv CS Jan 30

TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning

arXiv:2601.21692v1 Announce Type: new Abstract: Fine-Tuning-as-a-Service (FTaaS) facilitates the customization of Multimodal Large Language Models (MLLMs) but introduces critical backdoor risks via poisoned data. Existing...

Politics Policy

arXiv CS Jan 30

ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing

arXiv:2601.21694v1 Announce Type: new Abstract: Charts are a fundamental visualization format for structured data analysis. Enabling end-to-end chart editing according to user intent is of...

Software Engineering

arXiv CS Jan 30

AtPatch: Debugging Transformers via Hot-Fixing Over-Attention

arXiv:2601.21695v1 Announce Type: new Abstract: Transformer-based deep neural networks (DNNs) affected by backdoor attacks and unfairness typically exhibit anomalous attention patterns, leading to over-attend to...

Technology Neuroscience

arXiv CS Jan 30

Curriculum Learning for LLM Pretraining: An Analysis of Learning Dynamics

arXiv:2601.21698v1 Announce Type: new Abstract: Curriculum learning changes the order of pre-training data, but it remains unclear whether it changes the learning trajectory or mainly...

Business Policy