Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Deltatensors, a new open-source tool, compresses fine-tuned neural network model deltas into small .wdelta files, achieving near-lossless compression with sub-1% perplexity difference. Tested on Qwen2.5-0.5B fine-tuned o…
An ML engineer built a system that automatically rolls back machine learning models before they harm production data by routing a small percentage of live traffic to a canary model, continuously measuring its error rate …
Agencies including WPP, Dentsu, and Butler/Till are racing to develop AI agents for media buying and planning, aiming to gain a competitive edge. However, brands like Hyundai are using the same technology to bring market…
Researchers introduced Sol Video Inference Engine, an agent-native full-stack acceleration framework for video diffusion models that achieves over 2x end-to-end speedup with near-lossless quality across models from 2B to…
Researchers propose ModTGCN, a modularity-aware graph neural network for text classification that jointly optimizes cross-entropy and a modularity-based auxiliary objective to promote class-coherent document communities.…
Researchers at arXiv found that self-generated text recognition (SGTR) finetuning can prevent and reverse emergent misalignment in large language models, outperforming other interventions. The study across GPT-4.1, Qwen2…
Researchers introduced QuechuaTok, a benchmark evaluating tokenization strategies for Southern Quechua, a low-resource agglutinative language. They found that BPE achieved the lowest fertility rate but only 6.67% morphol…
Researchers introduced the MELD dataset to evaluate whether embedding models capture mathematical equivalence, finding that current models group statements by terminology rather than underlying math. They proposed a cont…
Researchers developed an automated pipeline to explore heterogeneous 4-expert mixture-of-experts architectures, generating 4,463 candidate models over 28 days. The search was biased toward the AirNet family due to an enu…
Researchers compared six offline reinforcement-learning methods for distilling reasoning from large language models into smaller ones, finding that SFT, RFT, and RIFT produce nearly identical weight updates and accuracy,…
A new survey systematically reviews federated causal discovery and inference, organizing methods by design decisions, federation topology, and structural scope. The work formalizes the connection between causal discovery…
Researchers developed low-power analogue neural networks with trainable nonlinear connections, inspired by Kolmogorov-Arnold networks, achieving efficient continuous control tasks like robotic kinematics and photovoltaic…
Researchers introduced SurfBind, a surface-centric learning framework that directly models 3D molecular surfaces for accurate epitope prediction. SurfBind uses a Transformer-based architecture with patch-level surface mo…
Researchers reconstructed GRACE-like terrestrial water storage anomalies back to 1940 using a spatio-temporal graph neural network (MTGNN) applied to South America. The model achieved high correlations and low bias, outp…
Researchers propose a frequency-guided feature representation learner for small object detection that shifts from spatial to spectral processing. The method, instantiated via lightweight plug-and-play modules, achieves c…
Researchers propose TheProfessor, a multi-teacher prompt distillation method for vision-language models that ensembles a domain-finetuned teacher and a zero-shot teacher. On four datasets, confidence-weighted ensembling …
Researchers introduced DriveStack-VLA, a framework that enhances Vision-Language-Action driving models with Bird-Eye-View representations and Render-Teacher Alignment to improve spatial intelligence. The model achieved s…
Researchers propose EMRFormer, a spiking neural network architecture that applies spike-driven transformers to automatic modulation recognition, achieving state-of-the-art accuracy while reducing theoretical energy consu…
Researchers propose Progressive Pixel-Neighborhood Deformable Cross-Attention (PNAFusion) for multispectral object detection, achieving state-of-the-art results on FLIR, M3FD, and DroneVehicle datasets while reducing GPU…
A new study on arXiv systematically examines the order of preprocessing techniques for sentiment analysis on Twitter datasets, finding that tokenisation is the most impactful technique while spelling correction is the le…