Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers propose ProMUSE, a progressive multi-modal uncertainty-guided network for Alzheimer's disease classification that adaptively determines when additional imaging modalities are needed, reducing MRI/PET usage by…
Researchers introduced Emyx, a 140M-parameter conditional flow matching model for all-atom protein generation, which outperforms larger models like RFdiffusion3 on enzyme design benchmarks while requiring only 682 GPU-ho…
Researchers propose LEAP, a training curriculum for Vision Transformer feature-based knowledge distillation that uses the teacher's intermediate feature maps as progressively difficult targets. LEAP achieves 90.1% accura…
Researchers introduced a decentralized coalition formation model driven by unilateral exit-and-join decisions, using the Aumann-Dreze value for local payoff calculations. The model links cooperative payoff allocation wit…
Researchers introduced MiqraBERT, a Sentence-BERT model finetuned from AlephBERT for detecting verse-level semantic similarity in Biblical Hebrew. The model improves distributional separation 2.7-fold over the pre-traine…
Researchers propose HypOProto, a hyperbolic prototype-based framework for interpretable left ventricular filling pressure classification from B-mode echocardiography, achieving state-of-the-art performance while maintain…
Researchers introduced self-function vectors to quantify aleatoric uncertainty in in-context learning for large language models, enabling more reliable prediction confidence and applications like hallucination detection.…
A new human-in-the-loop pipeline measures how completely a computer science program covers international curricular guidelines, applied longitudinally to one accredited BSc program against CS2013 and CS2023. The program …
Researchers introduced FlexLAM, a latent action model that replaces fixed-capacity bottlenecks with variable-length codes trained via nested dropout, resolving the trade-off between discarding transition cues and preserv…
Researchers developed a self-play reinforcement learning method for autonomous driving that uses only 30 minutes of human demonstrations, 2500 times less than imitation learning, to train policies that coordinate with hu…
Researchers propose TeleMorpher, a one-shot framework for simultaneous motion-location editing in videos, addressing a gap in diffusion model-based editing. The method disentangles protagonist and background, uses motion…
Researchers argue that aggregate-score leaderboards for LLM agent benchmarks systematically underspecify deployed-agent evaluation, as rankings do not transfer to out-of-distribution settings. They propose ranking config…
Researchers introduced BrainG3N, a dual-purpose tokenizer for 3D brain MRI generation that decouples encoder and decoder using a masked-autoencoder, enabling both clinically informative embeddings and anatomically faithf…
Researchers propose a method to learn asynchronous denoising schedules for multi-representation diffusion models, improving visual synthesis. On ImageNet 256x256, their approach achieves FID 1.05 with 4x less training th…
A new study measures the linearity of transformer feed-forward blocks, finding that linear recoverability (R²_lin) varies widely across blocks and is a learned property, not an architectural one. The analysis of GPT-2, P…
Researchers introduced VERITAS, a zero-shot framework for formal theorem proving that leverages rich verifier signals through a two-phase protocol combining Best-of-N sampling and critic-guided Monte Carlo tree search. V…
Researchers introduced DeXposure-Claw, an agentic system for DeFi risk supervision that uses a graph time-series foundation model and structured evidence to reduce false alarms. The system, evaluated on five years of rea…
Researchers propose a new framework integrating LLaVA and two-stage fine-tuning to improve composed image retrieval in fashion, addressing data scarcity and negative sampling limitations. The method enhances contrastive …
Researchers derived a three-force decomposition of AdamW training dynamics explaining Weibull weight-scale parameter evolution in transformers, finding alignment force dominates growth. A spline displacement method recov…
FocusOnFun team's Vortex system achieved 90.5% in the Preliminary Round and 'Excellent' overall performance with 'Outstanding' QA results at the Ho Chi Minh City AI Challenge 2025. The multimodal video retrieval system i…