CUEBES

LiveGraph: Active-Structure Neural Re-ranking for Exercise Recommendation

arXiv:2602.17036v1 Announce Type: new Abstract: The continuous expansion of digital learning environments has catalyzed the demand for intelligent systems capable of providing personalized educational content....

Technology Neuroscience

arXiv CS Feb 20

Wink: Recovering from Misbehaviors in Coding Agents

arXiv:2602.17037v1 Announce Type: new Abstract: Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex...

Engineering Robotics

arXiv CS Feb 20

Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion

arXiv:2602.17040v1 Announce Type: new Abstract: Recently, generating 3D assets with the control of condition images has achieved impressive quality. However, existing 3D generation methods are...

Software Psychology

arXiv CS Feb 20

InstantRetouch: Personalized Image Retouching without Test-time Fine-tuning Using an Asymmetric Auto-Encoder

arXiv:2602.17044v1 Announce Type: new Abstract: Personalized image retouching aims to adapt retouching style of individual users from reference examples, but existing methods often require user-specific...

Software Policy

arXiv CS Feb 20

Large Language Models Persuade Without Planning Theory of Mind

arXiv:2602.17045v1 Announce Type: new Abstract: A growing body of work attempts to evaluate the theory of mind (ToM) abilities of humans and large language models...

Psychology Policy

arXiv CS Feb 20

Dynamic System Instructions and Tool Exposure for Efficient Agentic LLMs

arXiv:2602.17046v1 Announce Type: new Abstract: Large Language Model (LLM) agents often run for many steps while re-ingesting long system instructions and large tool catalogs each...

Robotics Chemistry

arXiv CS Feb 20

Amber-Image: Efficient Compression of Large-Scale Diffusion Transformers

arXiv:2602.17047v1 Announce Type: new Abstract: Diffusion Transformer (DiT) architectures have significantly advanced Text-to-Image (T2I) generation but suffer from prohibitive computational costs and deployment barriers. To...

Engineering Chemistry

arXiv CS Feb 20

StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection

arXiv:2602.17048v1 Announce Type: new Abstract: Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection...

Engineering Finance

arXiv CS Feb 20

IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents

arXiv:2602.17049v1 Announce Type: new Abstract: Computer-use agents operate over long horizons under noisy perception, multi-window contexts, evolving environment states. Existing approaches, from RL-based planners to...

Software Robotics

arXiv CS Feb 20

Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenders

arXiv:2602.17050v1 Announce Type: new Abstract: Embedding tables are critical components of large-scale recommendation systems, facilitating the efficient mapping of high-cardinality categorical features into dense vector...

Software Policy

arXiv CS Feb 20

Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data

arXiv:2602.17051v1 Announce Type: new Abstract: Analysing multilingual social media discourse remains a major challenge in natural language processing, particularly when large-scale public debates span across...

Software Energy

arXiv CS Feb 20

RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models

arXiv:2602.17053v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true...

Engineering Software

arXiv CS Feb 20

ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning

arXiv:2602.17054v1 Announce Type: new Abstract: While recent Arabic NLP benchmarks focus on scale, they often rely on synthetic or translated data which may benefit from...

Psychology Software

arXiv CS Feb 20

Decoupled Internal Energy Regulation and Inertial Response Provision for Grid-Forming Multilevel-Converter-Based E-STATCOMs

arXiv:2602.17055v1 Announce Type: new Abstract: As power systems accommodate higher shares of renewable generation, short-term power imbalances become more frequent and can manifest as pronounced...

Energy Policy

arXiv CS Feb 20

A Long-term Value Prediction Framework In Video Ranking

arXiv:2602.17058v1 Announce Type: new Abstract: Accurately modeling long-term value (LTV) at the ranking stage of short-video recommendation remains challenging. While delayed feedback and extended engagement...

Policy Psychology

arXiv CS Feb 20

Cholec80-port: A Geometrically Consistent Trocar Port Segmentation Dataset for Robust Surgical Scene Understanding

arXiv:2602.17060v1 Announce Type: new Abstract: Trocar ports are camera-fixed, pseudo-static structures that can persistently occlude laparoscopic views and attract disproportionate feature points due to specular,...

Psychology World News

arXiv CS Feb 20

Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning

arXiv:2602.17062v1 Announce Type: new Abstract: Value decomposition is a core approach for cooperative multi-agent reinforcement learning (MARL). However, existing methods still rely on a single...

Software Policy

arXiv CS Feb 20

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression

arXiv:2602.17063v1 Announce Type: new Abstract: Sub-bit model compression seeks storage below one bit per weight; as magnitudes are aggressively compressed, the sign bit becomes a...

Psychology Software

arXiv CS Feb 20

Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization

arXiv:2602.17066v1 Announce Type: new Abstract: We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss...

Software Technology

arXiv CS Feb 20

StoryLensEdu: Personalized Learning Report Generation through Narrative-Driven Multi-Agent Systems

arXiv:2602.17067v1 Announce Type: new Abstract: Personalized feedback plays an important role in self-regulated learning (SRL), helping students track progress and refine their strategies. However, current...

Policy Biology

arXiv CS Feb 20

Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal control

arXiv:2602.17068v1 Announce Type: new Abstract: Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing...

Software Policy

arXiv CS Feb 20

AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

arXiv:2602.17071v1 Announce Type: new Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic...

World News Neuroscience

arXiv CS Feb 20

BankMathBench: A Benchmark for Numerical Reasoning in Banking Scenarios

arXiv:2602.17072v1 Announce Type: new Abstract: Large language models (LLMs)-based chatbots are increasingly being adopted in the financial domain, particularly in digital banking, to handle customer...

Technology Psychology

arXiv CS Feb 20

Cross Pseudo Labeling For Weakly Supervised Video Anomaly Detection

arXiv:2602.17077v1 Announce Type: new Abstract: Weakly supervised video anomaly detection aims to detect anomalies and identify abnormal categories with only video-level labels. We propose CPL-VAD,...

Policy