Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
LG AI Research presented its Exaone model's industrial applications at the International Conference on Machine Learning in Seoul, including AI-discovered materials like a hair loss treatment ingredient and a cooling flui…
A developer has published a guide for building an Agentic OS, a lightweight automation layer that enables AI to autonomously inspect repositories, assign tasks, verify outputs, and enforce budgets. The system separates A…
A new arXiv paper demonstrates that standard importance weighting fails to correct for selection bias in machine learning when selection depends on unobservables correlated with outcomes. The authors adapt Heckman's 1979…
Researchers proposed a method to estimate observation parameters and noise in inverse problems using a diffusion-based prior model within a Bayesian framework. The approach enables optimal estimation of both parameters a…
Researchers propose a decision-focused generative framework for correlated scenario generation in distributionally robust optimization (DRO)-based power grid dispatch, which reduces operational costs by 0.80%-2.02% compa…
Researchers introduced EquiFiLM, a lightweight extension that adds continuous external conditioning to equivariant foundation machine learning force fields via per-layer Feature-wise Linear Modulation. Applied to charged…
Researchers introduced Self-Review Reinforcement Learning (SRRL), a training framework that embeds a self-review step into each RL episode to help large language models learn from sparse feedback. SRRL outperformed stand…
Researchers propose CcGAN-AVAR, an imbalance-robust extension of Continuous conditional GAN that uses adaptive vicinal learning and auxiliary regularization to improve generation quality and label consistency. The method…
Researchers proposed a fine-grained multimodal framework for automatic depression detection using audio-visual data, featuring a Binary Advantage-weighting Ranking Loss that optimizes latent space distribution through ha…
Researchers proposed a low-overhead error-correction technique for quantum convolutional neural networks (QCNNs) using bivariate bicycle (BB) codes. Simulations showed that an unprotected 4-qubit QCNN fails to converge u…
Researchers introduced PCBWorld, an open-source engine-grounded PCB routing environment built on the KiCad EDA engine, enabling agents to route boards interactively using design rule feedback. The accompanying PCBWorld-B…
Researchers propose MuCoDi, a pretraining framework that distills knowledge from multiple large pathology foundation models into compact edge-oriented encoders, achieving near-teacher performance with orders-of-magnitude…
Researchers proposed a controllability-observability framework for compressing deep neural networks by viewing them as nonlinear dynamical systems. The method achieved up to 83% parameter compression on CIFAR-10 with neg…
Researchers introduced TAIL, a transformer-based algorithm-implicit meta-learner that generalizes across tasks with varying domains, modalities, and label configurations. TAIL achieves state-of-the-art few-shot performan…
Researchers introduced a Gibbs posterior sampler for solving inverse problems using a diffusion-based prior model. The method addresses ill-posed linear inverse problems with Bayesian regularization, offering simplicity …
Researchers derived smooth Monte-Carlo estimators for Minkowski functionals of neural fields, achieving 1-3% accuracy in 2D and 3D topology estimation at 250x speedup over persistent homology. However, in 3D neural-SDF f…
Researchers introduced AdaStop, a cost-aware early stopping framework for deep neural network testing that determines when to stop labeling inputs by comparing the marginal fault discovery rate to a cost-benefit threshol…
Researchers introduced SearchEyes, a multimodal search agent that uses a typed knowledge graph to unify training data, search environments, and reward signals, achieving state-of-the-art performance on six benchmarks. Th…
Researchers introduced REVIVE, a multi-modal framework for detecting and recovering from vandalism-induced occlusion attacks on autonomous vehicle cameras. The system combines detection, segmentation, and type-aware inpa…
Researchers propose TurnOPD, a turn-level budgeting strategy for efficient on-policy distillation of long-horizon language agents. The method addresses inefficiencies in vanilla agent OPD by using adaptive rollout-depth …