A new post-training method uses multi-metric perceptual rewards to optimize speech enhancement models. It directly applies non-differentiable metrics like DNSMOS, WER, and UTMOS as rewards via Group Sequence Policy Optimization, achieving state-of-the-art results on DNS2020. Human evaluation confirms that combining multiple metrics outperforms single-metric approaches, reducing reward hacking.
Native space-based UNet pipelines outperform template space ones in subcortical segmentation, showing higher Dice scores and lower HD95 values for the Subthalamic Nucleus, Red Nucleus, and Substantia Nigra. Performance drops significantly when applied to 3T images, with synthetic 3T training data providing only modest gains, highlighting a persistent domain gap between 7T and 3T MRI.
A study validates a Cross-Correlation Function method to identify optimal temporal and depth lags between meteorological variables and soil moisture. Using satellite and meteorological data across seven agricultural plots in southeastern Spain, deep learning models achieved significant improvements: a per-pixel CNN reached R² = 0.877, while a CNN-LSTM hybrid achieved the highest overall performance with R² = 0.930. Subsurface depth information and meteorological features substantially enhanced estimation accuracy.
A formal proof shows no equivalence exists between adversarial risk and regularized risk in two-layer networks. Empirical results on Wide-ResNets confirm this impossibility persists in deeper, more expressive architectures.
A machine learning model developed using pre-colonoscopy clinical features predicts high-risk colorectal polyps in African Americans. The model, validated in a diverse urban cohort, uses demographic, lifestyle, and comorbidity data to identify patients at higher risk, with external validation conducted in 2023-2024.
A study introduces JS divergence in GRPO-style autoregressive text-to-image alignment, showing it effectively balances policy optimization and generation diversity. Experiments on LlamaGen and Janus-7B demonstrate JS divergence achieves top or competitive performance across metrics while preserving diverse outputs.
The paper introduces Federated TGCN-A2C, a privacy-preserving framework that achieves 99.48% and 99.61% test accuracy on CICDDoS 2019 and TON-IoT benchmarks, outperforming Fed-Inforce-Fusion by 0.21 percentage points. It includes anomaly detection, digital twin-based scoring, adaptive action selection, and an enhanced honeypot layer, with all major attack classes achieving F1 scores above 0.92 and 0.94, respectively, and provides post-hoc explainability via SHAP, LIME, Grad-CAM, and counterfactual analysis.
Analytic Policy Gradients (APG) enables exact gradient computation via backpropagation through simulation when environment dynamics are differentiable. APG outperforms Proximal Policy Optimization (PPO) on four continuous control tasks, showing superior sample and learning efficiency with a segmented backpropagation scheme that reduces gradient degradation on long-horizon tasks.
A user reports that fine-tuning wav2vec2-base or wavlm-base-plus for 3-class audio classification achieves only 33% accuracy, matching chance levels. The model is trained with only the classification head updated, using padded clips of 1.0s duration without attention masks, and with a learning rate of 1e-3, leading to poor performance despite class imbalance and short input clips.
ParaPairAudioBench introduces a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions. It reveals that current LALM judges lag human judgments by 32% on average and fail to calibrate, especially in tie cases where abstention is correct.
AI-PAVE-Br uses large language models to enhance product attribute value extraction in Brazilian e-commerce. The system outperforms traditional NER methods, with a new Golden Set dataset providing a manually annotated benchmark for Portuguese product data.
DREAM uses autoregressive next-token prediction to supervise dense retrieval embedding training. It injects query-document similarity scores into a frozen LLM's attention heads, enabling gradient backpropagation for retriever optimization. DREAM outperforms baselines on BEIR and RTEB benchmarks across model scales.
CN-NewsTTS Bench v0.1 is an open benchmark for evaluating Chinese news TTS systems' ability to correctly pronounce raw text targets. It includes 200 development and 800 public test records, 992 auto-evaluable targets, and results for seven TTS systems, with the best achieving 0.879 strict accuracy and several below 0.60.
We propose decomposing structured annotation tasks into sub-tasks to reduce overall inferential load. By identifying salient anchor entities—centers in the space of valid annotations—we constrain output complexity and improve cost-efficiency. We provide guidelines for decomposition and a procedure to allocate sub-tasks across human and model annotators for optimal quality under fixed budgets.
CANDLE is a lightweight system that uses Connectionist Temporal Classification to deduplicate repeated characters in Arabic text, without relying on handcrafted rules or morphological analyzers. It achieves a Sentence Error Rate of 5.37% and reduces tokenizer fertility by up to 12.8%, lowering inference costs and improving context window usage.
A new study decomposes agent memory into four core modules and evaluates 12 systems across five benchmark workloads. It finds no single architecture dominates, with performance dependent on alignment with workload bottlenecks, and reveals that localized maintenance is more cost-efficient than global reorganization.
L3Cube-MahaPOS introduces a gold-standard part-of-speech tagging dataset for Marathi, manually annotated with 32,354 sentences from news text. It includes a 16-tag Universal Dependencies scheme and benchmarks six model families, achieving 88.67% token-level accuracy and 81.67% macro-F1 on 15 tag classes using MahaBERT-v2.
We construct and release a large biomedical dataset with 1.88 million PMC articles. Analysis shows author-written abstracts vary in quality and alignment with source articles, enabling effective training-data selection. Training on high-quality subsets outperforms random sampling and matches larger random subsets on factuality metrics.
A computational analysis of the Complete Tang Poems shows that poets' geographic origins leave detectable linguistic traces. Models using character n-gram TF-IDF and domain features achieve 0.69 accuracy in predicting broad regional origin (South vs. North), surpassing chance, and correctly classify finer circuit-level origins. The study finds linguistic distance between circuits correlates with geographic distance, with regional divergence increasing in the Late Tang, and highlights historical biases in early Tang poetic style.
This study analyzes algorithm influence through co-occurrence networks in natural language processing, using full-text academic papers. It reveals that algorithm networks exhibit complex network features, with denser connections emerging over two decades, and that classic algorithms at research intersections show high centrality and balanced influence. The research provides a temporal and structural view of algorithm evolution and lays groundwork for future studies on algorithm, scholar, and task networks.