arXiv:2605.00850v1 Announce Type: cross Abstract: Foundation models (FMs) for the Earth system learn statistical relationships between physical variables across massive datasets to enable versatile downstream applications through finetuning, separating them from task-specific weather models. Here, we introduce Earth System Foundation Model (ESFM), a fully open model building on the 3D Swin UNet backbone of the […]
URMF: Uncertainty-aware Robust Multimodal Fusion for Multimodal Sarcasm Detection
arXiv:2604.06728v2 Announce Type: replace-cross Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have improved MSD through cross-modal interaction and incongruity reasoning, most still treat modalities as equally reliable. In real social media posts, however, text and images often differ in noise level and […]
How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
arXiv:2604.05134v2 Announce Type: replace-cross Abstract: We study how reasoning evolves in a language model — from supervised fine-tuning (SFT) to reinforcement learning (RL) — by analyzing how a set of theoretically-inspired datasets influences language model performance in chess. We find that fine-tuning a model to directly predict the best move leads to effective RL and […]
CNN-based Multi-In-Multi-Out Model for Efficient Spatiotemporal Prediction
arXiv:2605.01277v1 Announce Type: cross Abstract: Recently, Convolutional Neural Network (CNN) or Transformer architecture based models have been proposed to overcome the limitations of Recurrent Neural Network (RNN) based models in spatiotemporal prediction. These models prevent the inefficiency of parallelization limitation due to the sequential properties and stacked error due to the recursive method, and show […]
Motion-Aware Caching for Efficient Autoregressive Video Generation
arXiv:2605.01725v1 Announce Type: cross Abstract: Autoregressive video generation paradigms offer theoretical promise for long video synthesis, yet their practical deployment is hindered by the computational burden of sequential iterative denoising. While cache reuse strategies can accelerate generation by skipping redundant denoising steps, existing methods rely on coarse-grained chunk-level skipping that fails to capture fine-grained pixel […]
Label-Free Microrefractometry of Interfacial Processes Using Fluorescent Smart Coverslips
arXiv:2605.01472v1 Announce Type: cross Abstract: Molecular dipoles near interfaces emit highly directional radiation due to near-field interactions, making surface-bound fluorophores sensitive probes of local physicochemical changes. We introduce smart coverslips, stably coated with uniform, brightly fluorescent nanobead films, that exploit refractive-index-dependent emission shifts for sensitive micro-refractometry in small volumes. Supercritical-angle fluorescence refractometry uses single back-focal-plane […]
Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis
arXiv:2605.01848v1 Announce Type: cross Abstract: Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pathological textures and structural features. We address this challenge for ulcerative colitis (UC) endoscopy, where severity follows a continuous ordinal progression along the Mayo Endoscopic Score (MES). Our framework, Disentangled Anatomy-Disease Diffusion […]
Forager: a lightweight testbed for continual learning with partial observability in RL
arXiv:2605.01131v1 Announce Type: cross Abstract: In continual reinforcement learning (CRL), good performance requires never-ending learning, acting, and exploration in a big, partially observable world. Most CRL experiments have focused on loss of plasticity — the inability to keep learning — in one-off experiments where some unobservable non-stationarity is added to classic fully observable MDPs. Further, […]
GraphSculptor: Sculpting Pre-training Coreset for Graph Self-supervised Learning
arXiv:2605.01310v1 Announce Type: cross Abstract: Graph self-supervised learning typically relies on large-scale unlabeled datasets, heavily inflating computational costs. However, empirical evidence suggests that these datasets contain substantial redundancy-our analysis reveals that uniformly subsampling 50% of graphs retains over 96% of downstream performance. To exploit this redundancy, we introduce GraphSculptor for pre-training coreset construction. Unlike methods […]
AMSnet-q: Unsupervised Circuit Identification and Performance Labeling for AMS Circuits
arXiv:2605.01404v1 Announce Type: cross Abstract: Analog and mixed-signal (AMS) circuit design remains heavily reliant on expert knowledge. While recent AI-driven automation tools can generate candidate topologies, they critically depend on manually curated datasets with functional and performance annotations — a requirement that current large language models (LLMs) and vision models cannot automate. Existing approaches still […]
Automated Interpretability and Feature Discovery in Language Models with Agents
arXiv:2605.01555v1 Announce Type: cross Abstract: We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system runs two coupled loops: (1) explanation refinement, where an agent proposes competing hypotheses and iteratively tests them with targeted prompt controls and a multi-metric evaluation; and (2) […]
Computational foundations of the human world
arXiv:2605.01680v1 Announce Type: cross Abstract: Human societies continuously transform scattered information into collective judgments and coordinated action, whether through markets discovering prices, governments allocating resources, communities enforcing norms, or science converging on reliable claims. Importantly, the computational difficulty of collective decision-making, particularly the time and communication required to reach solutions, imposes fundamental constraints on social […]