A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
S. Motwani, Alesia Ivanova, Ziyang Cai, et al.
Introduces a scalable method using curriculum RL on synthetically composed short-horizon data to boost long-horizon reasoning, achieving up to 2.06x accuracy gains on competition-level benchmarks.
Philipp Alexander Kreer, Wilson Wu, Maxwell Adam, et al.
Proposes Bayesian influence functions (BIF) that replace Hessian inversion with loss landscape statistics from stochastic-gradient MCMC for scalable data attribution in large neural networks.
Alvin Rajkomar, Eyal Oren, Kai Chen, et al.
Proposes a deep learning approach using raw EHR data in FHIR format to accurately predict multiple clinical outcomes across hospitals without site-specific harmonization.
Maria Rita Palattella, Mischa Döhler, Alfredo Grieco, et al.
This paper analyzes how 5G technologies can serve as a key enabler for the Internet of Things by addressing connectivity fragmentation and enabling ubiquitous, reliable, scalable, and cost-efficient IoT services.
Unknown
Proposes a scalable and domain-general abstractive proposition segmentation model by training LLMs on synthetic multi-domain data.
Xin Chan, Xiaoyang Wang, Dian Yu, et al.
Persona Hub introduces a scalable method to create diverse synthetic data by using 1 billion automatically curated personas from web data.
David A Cook, Joshua Overgaard, V Shane Pankratz, et al.
LLM-powered virtual patients can generate authentic clinician-patient dialogues, represent preferences, and provide personalized feedback at low cost.
Unknown
LLaVA 1.6 enhances multimodal AI with dynamic high-resolution processing, improved OCR, and scalable LLM integration.
Unknown
MAmmoTH2 introduces a scalable pipeline to harvest 10 million natural instruction-response pairs from web corpora, boosting LLM reasoning without manual annotation.
Iz Beltagy, Matthew E. Peters, Arman Cohan
Longformer introduces a linearly scalable attention mechanism for transformers, enabling efficient processing of long documents.
Unknown
Proposes Dynamic Sparse Attention (DSA) to efficiently exploit dynamic sparse patterns in attention for scalable transformer acceleration.
Tianyi Zhang, Anshumali Shrivastava
Leanquant introduces a loss-error-aware grid quantization method for LLMs that achieves accurate and scalable compression by minimizing quantization error with respect to the model's loss function.