Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers propose MiGHT-EHR, a multi-task graph transformer for heterogeneous temporal electronic health records, which jointly models heterogeneous clinical entities, longitudinal patient trajectories, and shared depe…
A new public benchmark, UAV3DCrop, evaluates 3D reconstruction methods for crop monitoring using 88,830 RGB images from 91 scenes of corn, soybean, wheat, and oat. The study finds that no single method excels across appe…
Researchers propose a new contextual bandit algorithm that explicitly models reward decay to improve iterative refinement in Large Language Models (LLMs), addressing over-exploitation from static prompts. The method, whi…
Researchers from Malta Lab introduced LaFaCt, a misinformation detection framework that uses activation engineering to identify false claims by projecting last-token activations onto a 'misinformation direction' in a lan…
Researchers introduced Adversarial Causal Intervention Falsification (ACIF), a sequential game where a structural causal generator proposes observational and interventional distributions and an adversarial experimentalis…
Researchers introduced SNI-GNN, a SmartNIC-assisted full-graph GNN training system that reduces communication by 21–45% and achieves 1.3–3.6× end-to-end speedups over BNS-GCN and up to 1.29× over SANCUS, with accuracy lo…
Researchers introduced a masked evidential loss for Deep Evidential Regression (DER) to estimate forest height from multimodal satellite imagery, achieving predictive performance comparable to a deterministic U-Net while…
Researchers propose PAST, a prompt-adaptive sampling termination method that improves reinforcement learning fine-tuning for diffusion models by up to 66.7% in computational efficiency and up to 29.5% in preference optim…
A new arXiv preprint (2608.06486) proposes Signed Integrated Gradients attribution for feature-tokenized transformers such as BiomeGPT, addressing limitations of nonnegative attention weights that cannot separate disease…
A new arXiv study (2608.06520v1) on online cooperative control of multi-agent systems under Byzantine attacks shows that an attacker observing planned actions induces an exact $(s,a)$-rectangular robust Markov decision p…
Researchers introduced NS-RIS, a Newton-Schulz Retraction-based Inference algorithm for learning hidden quantum Markov models (HQMMs), which for the first time significantly outperforms classical hidden Markov models (HM…
Researchers introduced CrystalGRPO, a reinforcement-learning post-training framework for flow-based crystal structure prediction that jointly optimizes coordinates and lattice parameters. In tests on MP-20 and MPTS-52 da…
Researchers introduced the first adversarial attack that directly optimizes an encoder-attention objective in detection transformers, reducing DETR-R50 mAP on COCO from 42.1 to 0.97, a ~4x reduction over the strongest ex…
Researchers propose CoDAT, a Collaborative Dual-Attention Transformer for efficient edge action recognition, which replaces multi-head attention with a lightweight dual-branch module and a parameter-free TShift module fo…
Researchers introduced GraphVerse, a benchmark for evaluating multimodal large language models (MLLMs) on visual graph reasoning, which tests perception, structural understanding, and multi-step reasoning over graph-base…
Researchers introduced EntropyMoE, a Mixture-of-Experts architecture for byte-level large language models that routes tokens based on patch entropy, achieving the lowest held-out bits-per-byte among matched dense and spa…
Researchers propose LUCID, an LLM-guided, interpretable, training-free, and unsupervised community detection method that achieves state-of-the-art performance on real-world datasets, outperforming leading unsupervised an…
Researchers introduced TaskSense, a task-centric world modeling framework that uses differentiable stochastic spatial attention conditioned on the previous latent state to focus on control-relevant regions, augmented wit…
A new arXiv paper (2608.06668v1) reports that deep reinforcement learning-based vehicle routing optimization achieved over 10% total cost reduction compared to baseline results in three industrial logistics use cases inv…
Researchers at arXiv (2608.06469v1) introduced Fairis, a server-side reweighting scheme for collaborative machine learning that provably contains fairness poisoning attacks by malicious clients. Fairis guarantees every c…