Machine Learning News

A pretrained teacher-guided low-fidelity framework, TGL-NSGA-II, achieved measured Kendall-τ values of 0.74 on keyword spotting and 0.62 on bird-call classification, exceeding predicted lower bounds of 0.60 and 0.46, acc…

Researchers introduced Atelier, a transformer-based hypernetwork that amortizes implicit neural representation fitting for reconstructed cryoEM maps, pretrained on 5,439 Electron Microscopy Data Bank maps. Atelier genera…

A new inference-time sampler lets pretrained diffusion models construct the central anatomy of the population they synthesize, called the intrinsic atlas, without any retraining or deformable registration, according to a…

Researchers introduced MM-VeriAgent, a reinforcement-learning-trained LVLM agent that learns to verify mixed-source multimodal misinformation using a specialized toolkit called MM-VeriTools, according to the arXiv paper …

A new arXiv paper (2609.30647v1) formalizes visual representation learning as a conditional predictive sufficient statistic (CPSS), showing that predicting the next patch embedding with a cosine loss is maximum likelihoo…

Researchers introduced SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images, detailed in arXiv paper 2609.30682v1. SGMA combines a content-adaptive quadtree tokenizer that co…

A multitask self-supervised pretraining framework that jointly optimizes voxel-level brain age prediction and image inpainting consistently outperformed single-task pretrained models and training from scratch across most…

Researchers posted arXiv paper 2609.30703v1, titled "SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion," proposing a unified framework that integrates frequency equaliz…

Researchers proposed VLALight, a lightweight end-to-end vision-language-action framework that maps intersection observations and signal-phase information directly to discrete traffic signal actions using a compact 0.5 B-…

A new arXiv paper (2609.30906v1) proposes ToolSearcher, a reinforcement learning framework for large-scale tool selection by LLM agents, addressing settings where real-world tool repositories are too large to fit within …

Researchers introduced SEA-CLIP-Tiny, a multilingual text-vision embedding model with fewer than 50M parameters for seven Southeast Asian languages, according to an arXiv paper (2609.30739v1). SEA-CLIP-Tiny reached 12.9%…

Researchers introduced asymmetric classifier-free guidance (CFG) for target-speaker automatic speech recognition using Whisper, reporting relative word error rate reductions of up to 21.8% over the condition-only baselin…

A new attention-free architecture that replaces Transformer attention with a stack of autoencoder-based mixing modules achieves a significant portion of attention's performance at about 1.9x fewer FLOPs when pretrained o…

A survey published on arXiv (2609.30292v1) reviews 211 studies on fake review detection from 2018 to early 2026, tracing the field from traditional machine learning and deep learning to pre-trained language model (PLM) a…

A new arXiv paper (2609.30298v1) introduces SRBench, a benchmark dataset of 45,064 labeled entries drawn from 32 curated secondary studies, for evaluating large language model performance in systematic review screening. …

A new arXiv paper (2609.31571v1) reports that self-training on strategically diverse data outperforms IID sampling, with self-training on strategically diverse but incorrect traces from Qwen3-4B beating IID distillation …

RAZOR, a training-free expert pruning method for mixture-of-experts (MoE) large language models, achieved the highest nine-task macro average among evaluated pruning methods in all eight settings tested on GLM-4.7-Flash,…

A study on arXiv (2609.30540v1) finds that the CLAP score, the standard objective metric for text-to-music faithfulness, fails to capture fine-grained musical meaning such as attribute bindings. Testing four contrastive …

LAVOIR, a method that adds value-of-information routing to single-pass decision encoders, matches a greedy oracle question policy on seen schemas (AUC 0.799 vs. 0.797) and is 14.1 points more accurate than never asking w…

A paper on arXiv (2609.30784v1) proposes a symbiotic architecture that gives frozen large language models audio-understanding capabilities by having an injector module write audio-conditioned vectors directly into the LL…