media Interconnects · 7d ago

State of the Interconnects Blog Mid-2026

The author outlines three core goals: clarifying frontier AI model evolution, building an open AI ecosystem, and creating institutions to support these missions. Interconnects serves as a raw, independent voice for frontier AI thinking, with a dedicated technical audience of over 70K subscribers. The blog maintains paywalled comments to prevent AI-generated noise, and the author plans to reach 1000 paid subscribers by summer, emphasizing financial sustainability and independence amid rising AI service costs.

arxiv arXiv cs.LG · 8d ago

INI-VPINN: Physics-Informed Neural Network with Implicit Boundary Handling

INI-VPINN is a variational physics-informed neural network that implicitly enforces Neumann and interface conditions using compact support weighting functions and integration by parts. It achieves higher accuracy and faster convergence than existing PINN methods in solving multi-material problems with geometric singularities and mixed boundary conditions, and is publicly available on GitHub.

arxiv arXiv cs.LG · 8d ago

ConTex: Global Counterfactual Generation for Time Series Forecasting

ConTex reformulates counterfactual generation for time series forecasting as a globally consistent intervention problem. It achieves state-of-the-art validity with sparse, interpretable interventions, reduces computational cost by 12-36x, and enables real-time inference in approximately 0.007 seconds.

arxiv arXiv cs.LG · 8d ago

Deep Reinforcement Learning for Minimum Zero-Forcing Sets

This paper proposes SD-ZFS, a deep reinforcement learning framework adapted from S2V-DQN, to solve the NP-hard minimum zero-forcing set problem on undirected graphs. The framework demonstrates strong performance compared to optimal solutions and greedy heuristics, showing effective generalization, scalability, and transfer across diverse graph structures.

arxiv arXiv cs.LG · 8d ago

LiL-Q: Convex Method for Nonlinear PDEs with PINNs

A new convex quasilinearization method, LiL-Q, solves nonlinear PDEs by reducing them to linear subproblems using physics-informed neural networks. LiL-Q converges in single-digit iterations across seven benchmarks, achieving machine precision when the exact solution lies in the trial space, and requires up to two orders of magnitude fewer parameters than standard PINN solvers.

arxiv arXiv cs.LG · 8d ago

Do Distilled Sets Outperform Coresets?

Large-scale experiments show that state-of-the-art dataset distillation methods are comparable to or worse than coreset selection on ImageNet and ImageNette. Coresets consistently achieve better data coverage and are more computationally efficient, highlighting their practical superiority over distilled sets.

arxiv arXiv cs.LG · 8d ago

Sign-Rank, Index, and List Replicability: Connections and Separations

The paper establishes that the \mathbb{Z}_2\-index is upper-bounded by a linear function of the list replicability number. It proves a strong separation between sign rank and \mathbb{Z}_2\-index and shows that list replicability is bounded above by height and minimum star number, with a composition result for the product of concept classes.

arxiv arXiv cs.CL · 8d ago

Security and Privacy Prompts in User-LLM Conversations

A study of 14,727 security and privacy prompts from 3.2M real-world user-LLM conversations identifies nine categories of S&P queries. Commercial LLMs outperform open models, with GPT 5.5 providing good responses on 98% of prompts versus Llama 4 at 47%, though some commercial models produce contradictory responses across runs.

arxiv arXiv cs.LG · 8d ago

MGUP: Momentum-Gradient Alignment for Selective Optimization

MGUP introduces a selective update mechanism that applies larger step-sizes to a fixed proportion of parameters in stochastic optimization, while using smaller, non-zero step-sizes for the rest. It integrates seamlessly with optimizers like AdamW, Lion, and Muon, providing theoretical convergence guarantees for MGUP-AdamW and demonstrating superior or more stable performance in training large language models and MAE pretraining tasks.

arxiv arXiv cs.LG · 8d ago

NYC Congestion Pricing Boosts Transit Use Amid Spatially Uneven Demand Shifts

New York City's 2025 congestion pricing led to significant increases in bus and subway ridership, with gains extending beyond Manhattan's core. Overall travel demand decreased modestly, primarily within the Congestion Relief Zone, and neighborhood-level responses reveal uneven socio-demographic adaptation.

arxiv arXiv cs.LG · 8d ago

SPHERE-JEPA: Family of Statistical Regularizers for Hypersphere

SPHERE-JEPA introduces deterministic statistical regularizers on the hypersphere, replacing stochastic sliced methods with analytically integrated objectives like MMD, KSD, and KL divergence. Rotationally invariant kernels based on heat and bandlimited filters ensure spatial bias-free learning, with empirical results showing improved convergence and performance on ImageNet and Galaxy10, and superior instance separation in procedural texture retrieval using KL divergence.

arxiv arXiv cs.LG · 8d ago

TUNEAHEAD Predicts Fine-tuning Performance Before Training

TUNEAHEAD is a lightweight framework that predicts fine-tuning performance using meta-feature vectors from dataset descriptors and short probe runs. It outperforms baselines like Early-Stop Extrapolation and ProxyLM, achieving an RMSE of 1.47 percentage points and 95.1% of predictions within ±3 percentage points of true scores on 370 held-out runs.

arxiv arXiv cs.LG · 8d ago

Confusion-Aware Transfer Teacher Curriculum Learning Framework

A confusion-aware difficulty score is introduced within the Transfer Teacher framework to improve model interpretability and data efficiency. Evaluations on CIFAR-10 show that confusion-aware curriculum ordering outperforms random ordering by up to 8.7% at 20% data, demonstrating consistent data-efficiency gains. However, curriculum or anti-curriculum ordering does not improve accuracy over standard training at full data, indicating that scoring function improvements alone are insufficient to overcome curriculum learning failure modes.

arxiv arXiv cs.LG · 8d ago

SMAA-Fair: A Fairness-Aware Extension of SMAA for Ranking

SMAA-Fair extends Stochastic Multicriteria Acceptability Analysis by reweighting rankings based on group fairness. It incorporates fairness metrics like Statistical Parity, rKL, and nDKL, adjusting acceptability indices to better represent protected groups while maintaining robustness to preference uncertainty.

arxiv arXiv cs.LG · 8d ago

Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery

The paper proposes an unsupervised framework to recover latent domains and signals from corrupted observations by discovering data symmetries. It models observations as linear measurements of signals from a latent random field and uses a shallow group-convolutional network with stationarity and locality constraints to learn latent symmetry actions and filters, enabling recovery from unstructured data.

arxiv arXiv cs.LG · 8d ago

QueryMarket: Cost-Aware Online Active Learning in Data Markets

QueryMarket introduces OVBAL, an online variance-based active learning framework that estimates each data point's marginal utility using a D-optimality criterion with exponential forgetting. OVBAL selects samples based on utility and price, operating under rolling budget constraints and adapting to concept drift, showing improved error-cost trade-offs in solar power forecasting tasks.

arxiv arXiv cs.LG · 8d ago

No-Free-Fairness: Fundamental Limits in Learning Systems

The paper introduces 'No-Free-Fairness' theorems that prove three fundamental limits in learning systems. These include inherent fairness-cost trade-offs, unavoidable subgroup disparity in finite samples, and model expressivity constraints that prevent fairness regardless of data. The results show fairness is constrained by problem structure, data limits, and model capacity, not just biased data.

arxiv arXiv cs.LG · 8d ago

Meta-classification of one-class models via ranking and nearest neighbor

This paper proposes a meta-classification method for one-class classification models by representing them as normality rankings and using ranking correlation and nearest neighbor metrics. The approach achieves high accuracy in classifying models based on training datasets, algorithms, and hyperparameters, and works even when datasets share the same class. The method effectively classifies datasets by treating multiple samples as a single input, offering a unified solution for OCC models, datasets, and rankings.

arxiv arXiv cs.LG · 8d ago

McWC: Forecasting with Cyclicity, Trend, and Channel Correlation

McWC introduces a model that separately captures cyclicity, trend, and inter-channel correlations in long-term time series forecasting. It uses multi-layer cyclicity construction, wavelet decomposition, and a multi-layer perceptron to extract and fuse high- and low-frequency information, while decoupling intra-channel autocorrelations via frequency-domain loss. Experiments on six real-world datasets show McWC achieves state-of-the-art performance with high computational efficiency.

arxiv arXiv cs.LG · 8d ago

BLITZ: Fast and Calibrated Nonparametric Conditional Independence Test

BLITZ introduces a two-stage regression method for nonparametric conditional independence testing. It first removes broad smooth dependencies using polynomial regression, then applies shallow tree regressions to residualize nonlinear features, enabling accurate and fast testing with improved null calibration compared to existing methods.