Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
FloDR, an invertible dimensionality reduction method based on a normalising flow, embeds high-dimensional data into two dimensions while retaining all coordinates to enable exact inverse and density calculations. Unlike …
A new study presents a federated physics-informed neural network (PINN) for privacy-preserving brain tumor biomechanical modeling, achieving 91.4% accuracy against 90.0% for a non-federated baseline. The method combines …
A study using CT Foundation embeddings achieved a Receiver Operating Characteristic Area Under the Curve (AUC) of 0.791 for predicting distant metastasis risk in head and neck cancer, outperforming radiomics (AUC 0.772) …
Researchers introduce TraceCLIP, a training-free framework that recovers latent patch-level semantic evidence from CLIP's CLS attention output, achieving gains of 1.3 to 4.5 points in average mIoU over prior training-fre…
MoSAIC, a latent diffusion framework for part-local reference-conditioned motion style transfer, achieves a preserved-region error of 66.45 mm and off-target leakage of 9.88 mm, outperforming whole-body routing by reduci…
A new arXiv study evaluating local LLM machine translation finds that dedicated MT systems from OPUS-MT and NLLB-200 remain stronger overall than three instruction-tuned LLMs (llama3.2:3b, mistral:latest, qwen2.5:14b) on…
Researchers introduced a model-side aggregation interface using Hash-based HyperLogLog (HLL) sketches that maintains compact 2 KiB states alongside frozen language models, achieving 1.6% mean relative error in distinct-c…
A new diagnostic benchmark, EC-Reason-Bench, reveals that general large language models (LLMs) score near zero on complete enzyme classification (EC) number prediction, with accuracy dropping sharply from coarse to fine-…
Researchers have developed a deep neural network approach to estimate weight, height, and Body Mass Index (BMI) from a single human image captured in the wild, achieving best results with full-body images. The team creat…
Voice Memory, a new inference-only scheme for agentic speech recognition, reduces weighted word error rate from 8.36% to 7.52% across ten HyPoradise domains without regressing any dataset below its 1-best baseline, accor…
Researchers propose AtmosERC, a graph-based framework for Emotion Recognition in Conversation (ERC) that models dialogue-level affective atmosphere to improve emotion prediction. The framework uses a relation-aware graph…
Researchers propose Zero-Fi, a contrastive signal-language alignment framework that enables zero-shot Wi-Fi-based human activity recognition by aligning Wi-Fi signal features with natural-language activity descriptions i…
Pangram Labs released Pangram 4, a deep-learning AI-text classification model achieving an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. The model shows improved accuracy ove…
A new study from arXiv finds that fine-tuned compact encoders match or exceed large language models in classifying fine-grained inconsistencies in financial disclosure text. Using a 5,940-instance snapshot of the SBID-FD…
Researchers introduced CMT-RAG, a complementary memory framework for multi-turn multi-hop retrieval-augmented generation that aligns conversational memory with retrieval by representing dialogue context as sub-question-l…
Researchers introduce WildShadowRemover, a framework that adapts a pretrained video diffusion model via LoRA fine-tuning for robust video shadow removal in unconstrained real-world scenarios. The method augments the froz…
A new study from arXiv reveals that large reasoning models fine-tuned via reinforcement learning (RL) outperform supervised fine-tuned (SFT) models on mathematical reasoning due to more linearly separable and hierarchica…
A systematic analysis of language sensitivity in codec-based self-supervised learning (SSL) models shows that downstream performance is insensitive to the neural audio codec (NAC) training language but strongly dependent…
Five emerging developer tools are transforming AI and cloud workflows, including NovaCode, an open-source AI coding assistant from ex-Google engineers; EthicalGuard, a bias detection SDK; DeployML, a unified ML deploymen…
A principal data engineer argues that teams migrating to vector databases often silently drop BM25 keyword search, harming recall on identifier queries critical for fraud detection. In a fraud queue, BM25 correctly ranks…