Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
ICONIP 2026, a major conference on neural networks and intelligent systems, may pull a sole author's paper from the proceedings if the author skips the in-person presentation without arranging a substitute. Organizers ty…
Researchers are using artificial intelligence to mine 500 years of Spanish colonial records, uncovering hidden shipwrecks and lost cargo that traditional methods missed.
A new arXiv study (2608.17325v1) finds that jointly optimizing tokenization with language modeling fundamentally alters token structure, with SSLMs recovering morphologically aligned and contextually efficient tokens whi…
Researchers introduced ICD-Deepresearch, a DeepResearch workflow that combines structured EHR foundation models with language foundation models to forecast ICD codes for future clinical visits, achieving patient-averaged…
Researchers released ArguLens, an open-source automated essay scoring system that decomposes scoring into three components: a discourse-move classifier, a LightGBM scorer, and a label-aware feedback generator. On the PER…
Researchers propose MD-SigLIP, a margin-regularized structured semantic alignment framework that directly aligns brain embeddings with text embeddings in a shared semantic space for retrieval-based decoding, achieving st…
Researchers introduced Q-Interference, a classical quantum-inspired attention mechanism for autoregressive language modeling that augments query and key features with amplitude and learned phase, enabling constructive or…
Researchers propose Data-DPO, a target model-oriented data selection method for supervised fine-tuning that uses one-step probing to capture target-model-aware data preferences and combines them with external quality sco…
A new arXiv paper (2608.17188v1) presents a practitioner framework for token optimization and context-window management in multi-agent AI workflows, reporting a 60-70% token reduction and cutting cold-load latency to 61-…
Researchers introduced Polaris, a system that trains a large language model to generate table descriptions optimized for retrieval effectiveness using Direct Preference Optimization (DPO) on existing table retrieval benc…
Researchers propose MASS, a hierarchical data selection method that uses manifold coverage and sparse feature coverage to improve LLM post-training efficiency. In experiments on Vision Flan and LLaVA-CoT, MASS outperform…
A new study from arXiv (2608.17095v1) introduces inference-time attention steering for vision-language-action (VLA) driving models, applying a bounded additive pre-softmax attention bias to visual tokens of detector-loca…
Researchers propose ADAPT (Adversarial Disentangled Prompt Tuning), a robust prompt tuning framework that mitigates robust generalization overfitting in vision-language models by disentangling robust features from pseudo…
Researchers at arXiv (2608.17170v1) introduced an automated approach using Large Language Models (LLMs) in an agentic check-fix-verify loop to synthesize executable Python feature extractors for constraint satisfaction p…
Researchers introduced PROBE, a framework for benchmarking and finetuning vision-language model (VLM) agents on Manipulation-Grounded Visual Question Answering (MG-VQA), where robots must physically move objects to answe…
A new study from arXiv (2608.16931v1) introduces SW-ProxyCE, a query-free attack framework that exploits public EEG foundation encoders to generate adversarial examples that transfer to private downstream models, achievi…
Researchers introduced Loki-OT, a method that uses Unbalanced Optimal Transport to propagate region-level tissue reasoning to individual cell predictions, improving lymphocyte mimicry correction in pathology. On the TCGA…
Researchers propose MultiSigBERT, a multimodal sequential survival model for oncology that integrates free-text medical reports, numerical measurements, and structured variables using path signature representations. On a…
Researchers introduced UniQuery4R, a query-conditioned framework for unified 4D scene reconstruction that encodes a multi-frame clip once and selects source and target views at decoding time, achieving the best macro-ave…
A new arXiv paper (2608.17088v1) proves that the minimum dimensionality required for perfect multilingual embedding spaces grows only logarithmically with the number of languages, showing there is no theoretical curse of…