Claude Code version 2.1.196 introduces organization default models, clickable file attachments, and improved security for MCP server approvals. The update also enhances background session reliability, fixes various agent status reporting issues, and optimizes token usage in code review workflows.
Researchers introduce MotifGen, a generative model designed for the spatiotemporal interpolation of tropical cyclone microwave images from multiple geospatial sources with irregular time intervals and geographic misalignment. The model addresses the challenge of high heterogeneity in microwave data by combining inputs from various instruments to fill gaps caused by long satellite revisit times.
This paper introduces two neural-network-based numerical schemes for solving systems of coupled ergodic Backward Stochastic Differential Equations (eBSDEs), motivated by approximating optimal strategies in regime-switching stochastic factor models.
This paper introduces the PROTECT-90 dataset, an open electromagnetic transient (EMT)-simulated reference benchmark designed to address the lack of standardized, publicly available high-voltage waveform datasets for power system protection. The release aims to enable transparent and reproducible evaluation of data-driven methods through consistent digital-fault-recorder-like measurements.
This study proposes two hardware-agnostic dynamic scheduling strategies, a model-free Reinforcement Learning agent and an on-the-fly Approximated Prediction method, to manage volatile energy in batteryless IoT systems without prior task profiles. Evaluated against adaptive and static baselines using a custom simulation framework, the research highlights distinct operational trade-offs for different system constraints.
The authors introduce OVBEVSeg, a framework for open-vocabulary bird's-eye view (BEV) segmentation that utilizes vision-language models to recognize categories beyond the training set while maintaining real-time efficiency. To address the 3D geometric inconsistency inherent in lifting 2D semantics into BEV, the method employs robust 3D geometric constraints across three progressive stages.
The authors introduce PHANTOM, a large-scale open-source dataset containing 47,524 pre-generated adversarial attacks designed to evaluate the safety and robustness of vision-language models (VLMs). This resource consolidates existing benchmarks and extends them with new categories to provide diverse and practical evaluation data for the research community.
The authors propose H-Res (Hierarchical Residual Steering), a mechanism that adapts large Transformer models by modulating their effective energy landscape without altering global equilibrium or expanding sequence length. This approach formulates adaptation as a control problem on the activation manifold to steer token trajectories into task-specific basins of attraction.
This paper introduces RE4, a framework for imitation learning that combines principled manipulation theories with modern benchmarks to preserve both performance and interpretability in object interaction tasks. The approach utilizes lightweight, self-supervised pose estimation and mode-aware transformations to retrieve and replan demonstrations effectively.
LongCat-2.0 is introduced as a large-scale Mixture of Experts (MoE) language model featuring 1.6 trillion total parameters with approximately 48 billion activated per token.
This work introduces natural identifiers (NIDs), which are structured random strings like cryptographic hashes and shortened URLs found in LLM training data, to address the challenges of auditing large language model privacy. NIDs enable scalable, post-hoc differential privacy auditing without costly retraining and facilitate dataset inference without requiring private held-out datasets.
This article investigates whether partial data augmentation can achieve the same statistical benefits as full augmentation by developing a framework using Fourier analysis and representation theory of finite groups.
This article introduces PCFM, a flow matching approach for medical point cloud completion that integrates Point Transformer v3 (PTv3) with continuous-time generative modeling. The method is evaluated on the SkullFix, SkullBreak, and Mandibular Defect datasets to assess its performance in anatomical reconstruction tasks.
Researchers have developed an agnostic model for the Photosynthetic Habitable Zone (PHZ) based on thermodynamics and redox chemistry, eliminating Earth-centric biases found in previous estimates. By optimizing a generic photochemical reaction against exoplanet irradiance spectra using a genetic algorithm, the study predicts that photosynthetic viability declines linearly with orbital distance rather than quadratically.
This paper proposes a knowledge-guided two-stage transfer learning framework to address bearing fault diagnosis challenges involving dataset heterogeneity, operating condition variations, and limited labeled data. The approach utilizes a lightweight GPT-2-style Transformer with causal self-attention for hierarchical feature extraction from vibration signals.
CrossPool is a serving engine designed for cold Mixture-of-Experts (MoE) models that addresses GPU memory inefficiencies by separating FFN weights and KV-cache into distinct pools. This disaggregation allows the system to consolidate static weights while dynamically provisioning active KV-cache demand, overcoming the limitations of monolithic memory allocation.
This study conducts a rigorous reevaluation of nine recent Graph Foundation Models (GFMs) for node property prediction to address the lack of unified evaluation standards in the field. The authors compare these models against strong Graph Neural Network (GNN) baselines to determine their relative performance and efficiency.
This paper reinterprets Large Language Models as high-dimensional Dense Associative Memories where correct reasoning corresponds to deep attractor basins in the energy landscape. The authors introduce a retrieval mechanism that samples multiple reasoning paths and weights them by inverse energy to approximate the equilibrium distribution.
This paper introduces EERLoss, a subdifferentiable approximation of the Equal Error Rate (EER) designed to align deep biometric model training with primary evaluation metrics. Validated on keystroke dynamics verification using the KVC-onGoing benchmark, the approach addresses the misalignment between optimization objectives and performance assessment.
The authors propose QC-SMOTE, a quality-controlled oversampling framework designed to address the generation of low-quality synthetic samples in noisy or overlapping regions common in imbalanced classification tasks. This method estimates minority sample reliability using a composite neighborhood trustworthiness score and employs an IPQ-guided best-of-K strategy for generating synthetic candidates.