📌 Weak Segmentation-Guided GAN for~Realistic Color Edition

Vincent Auriau, Emmanuel Malherbe, Matthieu Perrot

#arXiv #cs.AI

AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems

Eugenio Cainelli et al.

#arXiv #cs.AI #cs.LG #math.CO

📌 Boosting the Learning for Ranking Patterns

Nassim Belmecheri et al.

#arXiv #cs.AI

When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models

Shuhul Razdan, R Balamurugan

#arXiv #cs.AI

Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints

Yutao Xie et al.

#arXiv #cs.AI

Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another

Wangshu Zhu, Qianwen Guo, Yushun Dong

#arXiv #cs.AI #cs.CL

Cross-Protocol Personality Assessment with LLMs: Aligning Behavioral Evidence with Human Ratings

Wei Shan et al.

#arXiv #cs.AI

Multi-Horizon Explainable Queue Forecasting and Resource-Aware Decision Support for Intelligent Border Control Using LightGBM

Varvara Mama et al.

#arXiv #cs.AI

History Replays Itself: Unleashing Long-Context Capability in Linear Attention

Li Nanbo et al.

#arXiv #cs.AI #cs.LG

Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play

Yisong Xiao et al.

#arXiv #cs.AI #cs.CL

CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets

Anahita Sharma et al.

#arXiv #cs.AI

CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition

Xiangqing Lu et al.

#arXiv #cs.AI

Words to World: Benchmarking LLMs in Interactive Physical Environments

Xinnan Dai et al.

#arXiv #cs.AI

VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning

Jiahe Feng

#arXiv #cs.AI

EvoCowork: A Benchmark for Real-World Office Tasks

Zhou Liu et al.

#arXiv #cs.AI

A new approach lets self-evolving agents predict modification outcomes before costly evaluations, using an editable Improvement Dynamics Model refined over generations. Building on HyperAgents, the work is tested across…

#Robotics #AI #MachineLearning #ArXiv
https://arxiv.org/abs/2610.13991

Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation

Yaoxiang Wang et al.

#arXiv #cs.AI #cs.LG

Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning

Haodong Chen et al.

#arXiv #cs.AI #cs.CL #cs.IR #cs.LG

PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation

Wenji Zhang et al.

#arXiv #cs.AI #cs.SI

Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions

Xiaofan Li, Fengchun Qiao, Xing Gao

#arXiv #cs.AI #cs.CL #cs.SE