MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Extending Med-DDPM to AD, synthetic MRIs conditioned on anatomical masks produce segmentation models with Dice 0.6532 (synthetic-only) and 0.7244 (hybrid real+synthetic), outperforming real-only training at 0.6513.
A deterministic forensic preprocessing framework with set-theoretic formalizations, four theorems on determinism and preservation, and empirical validation showing 100% output consistency on three network datasets.
SECDA-DSE uses LLMs with RAG and chain-of-thought to generate three FPGA accelerator designs that synthesize and run on hardware, extending prior SECDA work.
MedThink, a two-stage teacher-guided reasoning correction distillation framework, boosts small language models' medical diagnostic accuracy by up to 12.7% on benchmarks and achieves 56.4% on a gastroenterology dataset.
Monte Carlo simulations of the diphoton Higgs channel in an effective coupling model reproduce the official ATLAS and CMS constraints on the gluon coupling modifier kappa_g.
citing papers explorer
-
MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering
MultiFinRAG is a multimodal RAG framework that improves accuracy on financial QA tasks involving text, tables, and images by 19 percentage points over ChatGPT-4o while running on commodity hardware.
-
Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks
Extending Med-DDPM to AD, synthetic MRIs conditioned on anatomical masks produce segmentation models with Dice 0.6532 (synthetic-only) and 0.7244 (hybrid real+synthetic), outperforming real-only training at 0.6513.
-
A Deterministic Forensic Preprocessing Framework for Heterogeneous Network Datasets: Formal Foundations, Implementation, and Empirical Validation
A deterministic forensic preprocessing framework with set-theoretic formalizations, four theorems on determinism and preservation, and empirical validation showing 100% output consistency on three network datasets.
-
Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA
SECDA-DSE uses LLMs with RAG and chain-of-thought to generate three FPGA accelerator designs that synthesize and run on hardware, extending prior SECDA work.
-
MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction
MedThink, a two-stage teacher-guided reasoning correction distillation framework, boosts small language models' medical diagnostic accuracy by up to 12.7% on benchmarks and achieves 56.4% on a gastroenterology dataset.
-
Constraints on the Higgs-gluon effective coupling through $h \to \gamma\gamma$ decays at the LHC
Monte Carlo simulations of the diphoton Higgs channel in an effective coupling model reproduce the official ATLAS and CMS constraints on the gluon coupling modifier kappa_g.