This work develops GREAT, a novel framework for crafting natural distributional backdoors in RLHF, which targets harmful response generation for a vulnerable user subpopulation featured by semantically violent requests paired with emotionally angry triggers.
Subrat Kishore Dutta, Yuelin Xu, P. Pant et al.· arXiv.org· 0 citations
This work compares the performance of PINNs in solving inverse problems with that of a traditional approach using the finite element method combined with a numerical optimizer and finds that while PINNs may require less human effort and specialized knowledge, they are outperformed by the traditional approach.
Aleksandra Jekic, Afroditi Natsaridou, Signe Riemer-Sørensen et al.· arXiv.org· 3 citations· ⚡1
This work introduces a probabilistic symbolic regression framework that represents mathematical expressions as ensembles of symbolic trees, and develops posterior concentration guarantees when symbolic expressions approximate the underlying relationship arbitrarily well, with a near-parametric rate when an exact finite formula exists.
Somjit Roy, Pritam Dey, B. Mallick et al.· 1 citation· ⚡1
Ampere is a novel collaborative training system that simultaneously minimizes on-device computation and device-server communication while improving model accuracy and reduces standard deviation of accuracy, highlighting superior performance when faced with heterogeneous data.
Zihan Zhang, Leon Wong, Blesson Varghese· IEEE Transactions on Paralle...· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
The results indicate that mixtures of M\"obius distributions provide interpretable, parsimonious models for the studied steady state density distributions, that match or outperform the alternatives.
Wanxin Gao, I. Nikolaidis, Janelle J. Harms· 2 citations
A Mixture of Multicenter Experts (MoME) framework to address AI bias in the medical domain without requiring data sharing across institutions is proposed and validated using a multimodal target volume delineation model for prostate cancer radiotherapy.
Yujin Oh, Sangjoon Park, Xiang Li et al.· 0 citations
This work revisits this design choice and proposes a sub-center modeling framework for speaker embeddings, which improves intelligibility, increases pitch variability, achieves higher naturalness ratings, and retains strong speaker verification performance in zero-shot voice conversion.
Ismail Rasim Ulgen, J. Hansen, Carlos Busso et al.· 0 citations
These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO, and study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM.
Yunpeng Ba, Zhi Zheng, Yue Xie et al.· 0 citations
This work builds a test bench on 892 yield response curves from two long running UK experiments, and sweeps the nitrogen to grain price ratio to cover all price scenarios, finding that machine learning fails as a predictor and pays as a profit scored correction to standard advice.
A neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs and a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainly for bilinear models and simultaneously enables them to predict numerical attributes.
Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini et al.· 0 citations
ContourKV, a training-free allocator built from the dropped-mass statistic, wins $93$ of $160$ paired comparisons against that state of the art and loses $22$ at the byte count of the budget-enforcing baselines, and it ties the strongest of them.
This work introduces the cross-predictive JEPA (JEPA-x), which grounds latent dynamics in privileged physical trajectories, and shows that direct physical-state regression improves decodability without improving forecastability or control, indicating that the benefit comes from shaping latent dynamics rather than merely encoding physical variables.
Kehan Wen, Ziming Li, Siyuan Luo 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.
