AniME: Adaptive Multi-Agent Planning for Long Animation Generation arXiv:2508.18781v2 Announce Type: replace Abstract: We present AniME, a director-oriented multi-agent system for automated long-form anime production, covering the full workflow from a story to the final video. The director agent keeps…
Patch Progression Masked Autoencoder with Fusion CNN Network for Classifying Evolution Between Two Pairs of 2D OCT Slices arXiv:2508.20064v1 Announce Type: cross Abstract: Age-related Macular Degeneration (AMD) is a prevalent eye condition affecting visual acuity. Anti-vascular endothelial growth factor (anti-VEGF)…
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation arXiv:2506.18088v2 Announce Type: replace-cross Abstract: Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain…
PGAD: Prototype-Guided Adaptive Distillation for Multi-Modal Learning in AD Diagnosis arXiv:2503.04836v2 Announce Type: replace-cross Abstract: Missing modalities pose a major issue in Alzheimer’s Disease (AD) diagnosis, as many subjects lack full imaging data due to cost and clinical constraints. While…
From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity arXiv:2508.19172v2 Announce Type: replace-cross Abstract: Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains…
Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs arXiv:2508.08292v2 Announce Type: replace-cross Abstract: Current mathematical reasoning benchmarks for large language models (LLMs) are approaching saturation, with some achieving > 90% accuracy, and are increasingly…
Bootstrapping Learned Cost Models with Synthetic SQL Queries arXiv:2508.19807v1 Announce Type: cross Abstract: Having access to realistic workloads for a given database instance is extremely important to enable stress and vulnerability testing, as well as to optimize for cost and…
PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense arXiv:2508.19488v1 Announce Type: new Abstract: Cyber defense requires automating defensive decision-making under stealthy, deceptive, and continuously evolving adversarial strategies. The FlipIt game provides a foundational framework for modeling interactions between…
A Survey on Training-free Alignment of Large Language Models arXiv:2508.09016v2 Announce Type: replace-cross Abstract: The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely…
Data-Efficient Symbolic Regression via Foundation Model Distillation arXiv:2508.19487v1 Announce Type: new Abstract: Discovering interpretable mathematical equations from observed data (a.k.a. equation discovery or symbolic regression) is a cornerstone of scientific discovery, enabling transparent modeling of physical, biological, and economic systems.…
