Framework for consolidating scientific knowledge in AI-driven computational physics, addressing knowledge accumulation beyond routine execution.
Adaptive contracts framework for cost-effective AI delegation in text generation tasks with selective evaluation methods.
DriveVLM-RL combines vision-language models with reinforcement learning for autonomous driving, addressing safety and latency challenges.
CaP-X framework for benchmarking Code-as-Policy agents in robot manipulation tasks using executable code and vision-language-action methods.
Lightweight uncertainty quantification method for neural networks using gradient norms and isotropy assumptions.
RAG reranker optimization using LLM feedback and reinforcement learning to align with downstream generation tasks.
Modular framework deploying VLM-guided reinforcement learning for autonomous driving via sim-to-real transfer.
Evaluation of multilingual prompt localization in agent-as-judge frameworks across 55 developer tasks and six backbones.
Study of cultural stereotypes and biases in vision-language models across different cultural contexts.
Autonomous LLM agents reproduce and critique published computational physics papers using first-principles ground truth.
Contract-based interface model for modular embodied agent capabilities with versioning and governance support.
Analysis of Claude Code architecture and design principles for agentic coding tools compared with open-source alternatives.
LLM-based agentic framework for XANES simulation and curation in computational chemistry with workflow automation.
Study of misaligned behaviors in frontier AI models including peer-preservation behavior across eight models.
Communication-efficient federated fine-tuning of LLMs on edge devices using Fisher-guided token quantization.
Claim verification system for semantic aggregates generated by LLMs from relational databases.
Medical diagnosis framework bridging vision-language models with clinical expertise via latent memory evolution.
Regression test selection framework for ML systems with modular capability components.
Theoretical analysis showing transformer components emerge from geometric state estimation problem with polar coordinates.
Theoretical work on inverse reinforcement learning using trust region methods and explicit dual ascent optimization.
Semantic code search system using concept-to-code alignment for explainable and generalizable retrieval.
LLM-based agent framework using contrastive learning to guide automated vulnerability repair in software systems.
LLM-based agentic RAG system for file-level bug localization in software maintenance and automated program repair.
Research on variational autoencoders studying constant collapse phenomenon using simplex witnesses and certificates.
Benchmark evaluating physics foundation models across 8 dynamics, 3 training mixtures, and 25 test regimes to assess generalization.
Dataset and pipeline for benchmarking LLM diagnostic reasoning using HL7 FHIR-compliant structured EHR data from unstructured text.
Method for multi-answer QA using tool-augmented LLM agents with peer-advantage rewards for discovering comprehensive answer sets.
Theoretical analysis showing equivariant latent world models achieve zero-shot generalization across symmetry groups via invariant prediction loss.
Technique for KV cache optimization in diffusion language models handling bidirectional attention patterns during inference.
Benchmark for evaluating autonomous AI agents on 40 scientific research tasks across 10 domains grounded in published papers.
Fused kernel library enabling efficient quantized LLM inference on AMD NPUs with mixed-precision support for on-device deployment.
Large-scale dataset of 4M anonymized clinical notes from Italian emergency departments with 6K expert-annotated subset for NLP research.
arXiv paper on IoU insensitivity in surface defect detection models. Computer vision quality metrics optimization.
arXiv paper on instruction-guided audio editing using diffusion transformers with rectified flow for semantic alignment.
arXiv paper presenting KernelSight-LM, a simulator for evaluating LLM inference performance across hardware and serving parameters.
arXiv paper studying undergraduate reliance patterns on LLMs for academic writing. Identifies four types and predictors of LLM use.
arXiv paper on arbitrary-scale image super-resolution using Gaussian splatting. Computer vision focused, not AI/ML tools.
arXiv paper on using LLMs to translate natural language into formal temporal specifications for multi-agent systems verification.
arXiv paper on learned multigrid preconditioner for solving Helmholtz equations using phase-space methods. Physics/numerics focused.
arXiv paper on resolving superposition in neural networks for biological data interpretability and cross-modal alignment in patient imaging.
arXiv paper introducing WorldOdysseyBench benchmark for evaluating long-horizon stability of interactive world models across four dimensions.
arXiv paper evaluating sparse autoencoders for concept manipulation and unlearning in diffusion models, focusing on object erasure.
arXiv paper on using LLMs for re-ranking in industrial recommendation systems. Addresses gaps in adopting LLMs for multi-stage ranking.
arXiv paper proposing BaRA, a budget-constrained LLM web agent for multimodal data collection with fixed interaction budgets.
arXiv paper on personalized retrieval for long-term conversational agents using profile-guided memory recall in LLM-based systems.
Hybrid neuroevolution and supervised learning for RIS-aided mobile tracking with power-efficient localization using feedback control.
Quantum machine learning study of spectral geometry in graph-regularized quantum networks using two-boson interference probes.
Tutorial on world models as action-conditioned predictive models for embodied AI, comparing observation-space vs state-space approaches with trade-offs.
MemSyco-Bench evaluates sycophancy in LLM-agent memory systems where retrieved memories cause over-alignment with users at cost of factual accuracy.
Study of stale rollout effects in asynchronous GRPO for high-throughput RLHF, analyzing learning-rate scaling laws for decoupled policy optimization.