We compare six self-supervised pretext tasks for infant cry analysis under a fixed budget, meaning the same compact encoder of 1.17M parameters, the same 115 hours of license-verified public pretraining audio, and the same evaluation protocol for every candidate. On cry detection the reconstructive objectives dominate, and a linear probe over a masked-spectrogram encoder reaches 0.988 AUC with subject-wise splits even though the encoder never observed a cry during pretraining. On cry-reason classification over donateacry, the de facto public benchmark for cry reasons, every encoder performs at chance (0.38 to 0.54 macro AUC over 5 classes), and neither domain adaptation on 1.8 hours of real cries nor end-to-end fine-tuning moves the result. Since a frozen HuBERT-base with 80 times more parameters shows the same pattern, the bottleneck must sit in the labels and not in model capacity. We then reproduce the 90\%+ accuracies of the donateacry literature on our own system by changing nothing but the evaluation protocol: clip-wise splits raise accuracy to 85.2% (barely above the 83.8% majority-class baseline), and applying augmentation before splitting raises it to 97.9%, matching the reported state of the art, from the same model that measures 0.49 macro AUC under subject-wise splits. Under leakage-free splits, a twentyfold augmentation of the labeled set (vocoder speaker perturbation and noise mixing, 21 hours) leaves cross-subject AUC unchanged: for this task the effective sample size is the number of infants. We release code, seeds and per-clip license manifests.
Results show that function-preserving conditional residuals add input-dependent capacity while preserving the Dense path and its optimization stability, and introduce PRIME (Plug-in Residual Input-conditioned Mixture of Experts), a Dense-anchored mixture of low-rank residual experts.
Heng Yao, Si-Yun Hou, Tian-Ying Liu et al.· 0 citations
This work conducts a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry, and provides an empirically motivated six-step evaluation checklist.
It is proved that any fixed MHSA architecture that achieves exact equivariance by polynomially parameterizing unconstrained MHSA parameters inevitably leads to expressivity loss within the class of equivariant maps.
Tikun Ông· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
An alternative reward shaping method (RS) is proposed that removes deceptive rewards at the expense of theoretical guarantees of PBRS, and another method named Locally-Guided Actor Critic (LG-AC) that rewards the agent for reaching intermediate goals achieves the best overall performance across tasks.
TopGQ, an accurate post-training GNN quantization framework, alleviating redundant quantization overhead, is presented, and dual-axis scale absorption is proposed, which enables activation quantization along both the outer and inner dimensions by merging one into the adjacency matrix.
Dain Kwon, Kanghyun Choi, Hyeyoon Lee et al.· 0 citations
Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models have emerged as powerful, label-efficient tools across general remote sensing domains, yet early attempts to deploy them for agricultural applications have yielded surprisingly poor results. We hypothesize that this performance gap stems from the extreme heterogeneity of agricultural landscapes and the inherent inability of current earth observation foundation models to adapt to task-specific nuances. In this work, we systematically evaluate two critical bottlenecks hindering the deployment of foundation models in agricultural tasks, benchmarking two earth observation foundation models, a foundation model designed for tabular data, and conventional supervised baselines across seven real-world agricultural datasets spanning yield prediction, phenology estimation, and crop classification. First, we identify a pretraining-deployment modality gap: agricultural downstream tasks frequently require diverse, non-imagery data modalities that earth observation foundation models are architecturally unequipped to ingest, while a foundation model built for tabular data handles this heterogeneity more naturally. Second, we formalize the agricultural task space across five structural axes to demonstrate why current models fail to generalize reliably, resulting in highly unstable model rankings across evaluation settings. By characterizing these structural and modal gaps, our insights highlight the friction between general-purpose architectures and specialized agricultural downstream data, providing a strategic roadmap for developing the next generation of domain-aware foundation models.
Vishal Nedungadi, Xing-Kui Xiong, Marc Rußwurm et al.· 0 citations
This work underscores the need for a holistic approach to uncertainty quantification in recent development of medical vision foundation model, ensuring robust and interpretable AI-driven decision-making and highlights the importance of careful model selection and the inte- gration of both point and region prediction to enhance the reliability and trust- worthiness of medical AI systems.
Decay-Aware State Compression (DASC), which derives retention horizons from model weights, selects long-horizon state units, and packs them into a ragged state checkpoint layout to integrate efficiently with tensor-parallel inference engines.
Yanzhi Yu, Ping-Wei Sun, Jian-Chao Tan et al.· 0 citations
By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension, this work reduces memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets.
Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato et al.· 0 citations
The key innovative new feature in the proof of the analysis are suitable inverse moment bounds for the second moment process in RMSprop that hold not just for all sufficiently large n but hold for every gradient step $n=1,2,3,...$ with all error constants being explicitly specified.
Results suggest morphology-preserving beat tokenization is a compact, competitive alternative to fixed temporal patching, and beats-preserving beat tokenization is a physiologically grounded alternative to fixed temporal patching.
Ahmed Sameh, Nolan Wilson, Maxine A. Enderlein et al.· 0 citations
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
