Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning
arXiv:2602.18591v1 Announce Type: new Abstract: A fundamental problem in multi-task learning (MTL) is identifying groups of tasks that should be learned together. Since training MTL models for all possible combinations of tasks is prohibitively expensive for large task sets, a...
Non-Interfering Weight Fields: Treating Model Parameters as a Continuously Extensible Function
arXiv:2602.18628v1 Announce Type: new Abstract: Large language models store all learned knowledge in a single, fixed weight vector. Teaching a model new capabilities requires modifying those same weights, inevitably degrading previously acquired knowledge. This fundamental limitation, known as catastrophic forgetting,...
Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models
arXiv:2602.18639v1 Announce Type: new Abstract: World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the DINO world model (DINO-WM), display a...
Adaptive Time Series Reasoning via Segment Selection
arXiv:2602.18645v1 Announce Type: new Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model...
Global Low-Rank, Local Full-Rank: The Holographic Encoding of Learned Algorithms
arXiv:2602.18649v1 Announce Type: new Abstract: Grokking -- the abrupt transition from memorization to generalization after extended training -- has been linked to the emergence of low-dimensional structure in learning dynamics. Yet neural network parameters inhabit extremely high-dimensional spaces. How can...
Communication-Efficient Personalized Adaptation via Federated-Local Model Merging
arXiv:2602.18658v1 Announce Type: new Abstract: Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments. In this regime, personalization...
Large Causal Models for Temporal Causal Discovery
arXiv:2602.18662v1 Announce Type: new Abstract: Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset. Such an approach limits the potential of multi-dataset pretraining. The concept...
Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data
arXiv:2602.18674v1 Announce Type: new Abstract: We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation...
Transformers for dynamical systems learn transfer operators in-context
arXiv:2602.18679v1 Announce Type: new Abstract: Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional understanding of learning and adaptation in physical systems....
In-Context Planning with Latent Temporal Abstractions
arXiv:2602.18694v1 Announce Type: new Abstract: Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts...
Insertion Based Sequence Generation with Learnable Order Dynamics
arXiv:2602.18695v1 Announce Type: new Abstract: In many domains generating variable length sequences through insertions provides greater flexibility over autoregressive models. However, the action space of insertion models is much larger than that of autoregressive models (ARMs) making the learning challenging....
Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering
arXiv:2602.18728v1 Announce Type: new Abstract: Unsupervised multi-view clustering (MVC) aims to partition data into meaningful groups by leveraging complementary information from multiple views without labels, yet a central challenge is to obtain a reliable shared structural signal to guide representation...
HONEST-CAV: Hierarchical Optimization of Network Signals and Trajectories for Connected and Automated Vehicles with Multi-Agent Reinforcement Learning
arXiv:2602.18740v1 Announce Type: new Abstract: This study presents a hierarchical, network-level traffic flow control framework for mixed traffic consisting of Human-driven Vehicles (HVs), Connected and Automated Vehicles (CAVs). The framework jointly optimizes vehicle-level eco-driving behaviors and intersection-level traffic signal control...
RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data
arXiv:2602.18744v1 Announce Type: new Abstract: Radio maps are essential for efficient radio resource management in future 6G and low-altitude networks. While deep learning (DL) techniques have emerged as an efficient alternative to conventional ray-tracing for radio map estimation (RME), most...
GLaDiGAtor: Language-Model-Augmented Multi-Relation Graph Learning for Predicting Disease-Gene Associations
arXiv:2602.18769v1 Announce Type: new Abstract: Understanding disease-gene associations is essential for unravelling disease mechanisms and advancing diagnostics and therapeutics. Traditional approaches based on manual curation and literature review are labour-intensive and not scalable, prompting the use of machine learning on...
From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
arXiv:2602.18793v1 Announce Type: new Abstract: Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of "one-model-for-one-dataset", requiring dataset-specific...
SGNO: Spectral Generator Neural Operators for Stable Long Horizon PDE Rollouts
arXiv:2602.18801v1 Announce Type: new Abstract: Neural operators provide fast PDE surrogates and often generalize across parameters and resolutions. However, in the short train long test setting, autoregressive rollouts can become unstable. This typically happens for two reasons: one step errors...
L2G-Net: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations
arXiv:2602.18837v1 Announce Type: new Abstract: Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks (GNNs) due to the cost of computing the eigenbasis and the lack of vertex-domain locality...
Exact Attention Sensitivity and the Geometry of Transformer Stability
arXiv:2602.18849v1 Announce Type: new Abstract: Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, why DeepNorm uses $N^{-1/4}$ scaling, and why warmup is necessary, all from first principles. Our...
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
arXiv:2602.18851v1 Announce Type: new Abstract: Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk in low-precision training. We derive a \emph{rank-aware concentration inequality}: when the interaction matrix $M =...
Issues with Measuring Task Complexity via Random Policies in Robotic Tasks
arXiv:2602.18856v1 Announce Type: new Abstract: Reinforcement learning (RL) has enabled major advances in fields such as robotics and natural language processing. A key challenge in RL is measuring task complexity, which is essential for creating meaningful benchmarks and designing effective...
VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning
arXiv:2602.18857v1 Announce Type: new Abstract: Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents achieve this, but obtaining the belief-state and performing planning are both typically...
Hyperbolic Busemann Neural Networks
arXiv:2602.18858v1 Announce Type: new Abstract: Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural networks require intrinsic and efficient components that operate directly in hyperbolic space....
Boosting for Vector-Valued Prediction and Conditional Density Estimation
arXiv:2602.18866v1 Announce Type: new Abstract: Despite the widespread use of boosting in structured prediction, a general theoretical understanding of aggregation beyond scalar losses remains incomplete. We study vector-valued and conditional density prediction under general divergences and identify stability conditions under...
HEHRGNN: A Unified Embedding Model for Knowledge Graphs with Hyperedges and Hyper-Relational Edges
arXiv:2602.18897v1 Announce Type: new Abstract: Knowledge Graph(KG) has gained traction as a machine-readable organization of real-world knowledge for analytics using artificial intelligence systems. Graph Neural Network(GNN), is proven to be an effective KG embedding technique that enables various downstream tasks...
PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
arXiv:2602.18904v1 Announce Type: new Abstract: Vector-quantized autoencoders deliver high-fidelity latents but suffer inherent flaws: the quantizer is non-differentiable, requires straight-through hacks, and is prone to collapse. We address these issues at the root by replacing VQ with a simple, principled,...
Court holds that U.S. Postal Service can’t be sued over intentionally misdelivered mail
A divided Supreme Court sided with the federal government on Tuesday in U.S. Postal Service v. Konan, a dispute over mishandled mail. Writing for a 5-4 majority, Justice Clarence Thomas […]The postCourt holds that U.S. Postal Service can’t be sued...
The sudden return of summary reversals
Nuts and Bolts is a recurring series by Stephen Wermiel providing insights into the mechanics of how the Supreme Court works. A Supreme Court shortcut for deciding cases without full […]The postThe sudden return of summary reversalsappeared first onSCOTUSblog.
Oral argument live blog for Monday, March 2
On Monday, March 2, we will be live blogging as the court hears argument in United States v. Hemani, on whether a federal statute that prohibits gun possession by users […]The postOral argument live blog for Monday, March 2appeared first...
Standing in and after Bost
Controlling Opinions is a recurring series by Richard Re that explores the interaction of law, ideology, and discretion at the Supreme Court. The Supreme Court’s recent decision in Bost v. […]The postStanding in and after Bostappeared first onSCOTUSblog.