NOMAD: Generating Embeddings for Massive Distributed Graphs
Scalable method for generating node embeddings on massive distributed graphs with millions to billions of nodes.
Scalable method for generating node embeddings on massive distributed graphs with millions to billions of nodes.
AdaCubic optimizer using adaptive cubic regularization with Hutchinson's method for approximating Hessian in deep learning.
One-step diffusion model for efficient chest X-ray report generation reducing inference latency compared to autoregressive models.
Method for safely updating deep reinforcement learning policies while preserving safety guarantees on previously encountered tasks.
Hardware optimization using electro-optic nonlinearities to replace softmax bottleneck in transformer attention mechanisms.
Application of world models paradigm to computational epidemiology for reasoning about latent disease burden and intervention effects.
High-fidelity cyber operations simulator (NetForge_RL) using temporal graph networks for multi-agent reinforcement learning in cybersecurity.
OmniBehavior benchmark for evaluating LLMs as user simulators on long-horizon, cross-scenario behavior traces from real-world data.
Investigation of self-sovereign AI agents that can economically sustain themselves without human involvement using LLMs and agent frameworks.
Analysis of how bias mitigation reshapes embedding spaces in BERT and Llama2 through representational analysis of gender-occupation associations.
Systematic evaluation of chain-of-thought vs zero-shot prompting across temperature settings using Grok-4.1 for extended reasoning LLMs.
Research on attention-based sampling for diffusion language models enabling parallel decoding instead of sequential auto-regressive approach.
Tree-structured sparse feed-forward layers as drop-in MLP replacements in transformers enabling conditional computation via routing.
Comparative study of LLMs vs fine-tuned Arabic BERT models on sentiment classification of Gaza War news headlines.
GAN-enhanced deep reinforcement learning for semantic-aware resource allocation in 6G wireless networks.
Theoretical framework for reward fine-tuning of diffusion models using stochastic optimal control and adjoint matching.
Protocol governing autonomous agent mutations with execution-bound safety checks and evidence chains for API-centric architectures.
Open-source browser extension for AI-assisted title and abstract screening in literature review with no-code, serverless architecture.
Attack method on LLM orchestration systems where single requests decompose into benign subtasks that jointly violate security policies.
Multimodal approach for detecting hate and threats in digital forensic evidence combining images, documents, and text.
Longitudinal case study of autonomous personalization systems in CRM with human-in-the-loop oversight requirements.
Theoretical framework analyzing generalization in overparameterized interpolating estimators via spectral-transport stability.
Method to reduce hallucinations in 3D embodied AI agents using visual contrastive decoding on multimodal LLMs.
Differentiable probabilistic programming for gamma-ray astrophysical analysis using GPU acceleration and vectorization.
Multimodal inference task with text, audio, video for producing calibrated probability estimates of hypotheses with fine-grained uncertainty.
LLM application translating network quality metrics to user experience quality using large language models for multimedia systems.
Deep learning framework for tracking and reconstructing ligament lineage during liquid sheet breakup using multi-object tracking.
Hybrid behavioral analysis framework combining static and dynamic analysis for early-stage ransomware detection before file encryption.
Active learning strategy for predicting detonation performance of energetic materials using limited experimental data.
Probabilistic framework for inferring 3D cloud microphysical properties from 2D satellite observations for weather modeling.
Hardware-agnostic world models for quadrupedal robots using morphology conditioning to generalize across different robot embodiments.
Deep learning approach for detecting stepping-stone intrusions by correlating network flows at relay hosts with low false positive rates.
Statistical framework for designing large-scale factorial experiments with overlapping conditions on shared user populations.
Multi-view circuit graph benchmark suite standardizing representations for GNN-based physical design tasks from RTL to GDSII.
Scene graph benchmark for content moderation with spatial grounding and interpretability for detecting sensitive behavior in images.
Transformer architecture with uncertainty quantification for medical image classification, addressing overconfident predictions in clinical settings.
RL framework for improving LLM reasoning by optimizing for logical consistency and structural integrity of reasoning processes, not just final answers.
Proposes utility-centric approach to information retrieval for RAG systems, optimizing retrieved documents for task completion rather than topical relevance.
Novel algorithm for learning directed acyclic graphs from observational data with positive-valued variables using moment-ratio scoring.
Supervised adaptation of vision-language models outperforms prompting for cloud segmentation in remote sensing under domain shift.
Projected functional gradient descent algorithm for online quantile regression in nonparametric additive models.
ASTRA: Adaptive semantic tree reasoning architecture for table question answering using LLMs with improved serialization and schema flexibility.
Hypergraph neural networks applied to enumerate Minimal Unsatisfiable Subsets in constraint satisfaction problems more efficiently.
Regime-conditional retrieval approach with transferable router for two-hop QA using surface-text predicates for routing decisions.
ImageProtector method prevents multi-modal LLMs from analyzing images via visual prompt injection for privacy protection.
Multi-agent mixture of experts with plasticity enhancement for UAV communication networks under non-stationary conditions using deep RL.
Proposes Advantage-Guided Diffusion for model-based RL using diffusion world models to reduce compounding errors in trajectory generation.
Continual visual place recognition system for aerial autonomy addressing catastrophic forgetting using geometric memory management in dynamic environments.
NyayaMind framework for transparent legal judgment prediction in Indian courts using structured reasoning aligned with legal methodology.
CLIP-Inspector framework for detecting backdoor attacks in prompt-tuned CLIP models via out-of-distribution trigger inversion.