Researchers proposed a compliance-aware federated learning framework that adjusts differential privacy noise to accommodate varying institutional data standards and resource levels.
Researchers have developed a variation-aware entropy scheduling method to improve reinforcement learning performance in environments subject to drift.
Researchers have introduced TADPO, a reinforcement learning approach designed to improve autonomous vehicle navigation in complex, unmapped off-road environments.
A comparative study using NLP metrics reveals similarities and differences in how humans and leading large language models navigate conceptual spaces during semantic memory retrieval.
The authors investigate how the training duration of individual domain experts influences the performance of merged large language models.
Plug Power has sold a Texas industrial site to Stream Data Centers, which intends to repurpose the land for data center infrastructure.
Researchers have introduced Visual Access Sweep, a causal intervention method to study how Vision-Language Models utilize image tokens during long Chain-of-Thought reasoning.
Researchers introduced Cost-Governed RAG, an architecture designed to attribute both retrieval and generation costs to individual tenants in multi-user language model systems.
Researchers introduced PM-Bench, a text-based benchmark designed to evaluate the prospective memory capabilities of large language model agents.
This work discusses the application of evidence-grounded AI systems to support the longitudinal management and rehabilitation of musculoskeletal diseases.
This paper investigates a vulnerability in large language model plan evaluators where strategic plans are rewarded for omitting explicit details.
Researchers proposed a method for automatic speech recognition using a discrete diffusion language model to transcribe audio in parallel rather than through traditional autoregressive decoding.
Research indicates that current state-of-the-art LLMs struggle significantly with bidirectional Korean-Braille translation, highlighting gaps in accessibility-focused capabilities.
The authors introduce a method called CARE-LoRA designed to reduce memory usage during the fine-tuning of large pre-trained models.
A new signal-guided optimization technique aims to improve machine unlearning by addressing the varying memorization strengths of individual training samples.
The authors introduce an agentic approach for localizing vulnerability triggers in code by performing interprocedural causal reasoning.
This study introduces a method using sparse autoencoders to better detect out-of-distribution data by analyzing intermediate layers of neural networks.
Researchers have developed a unified approach for rectified flow models that combines velocity and endpoint prediction to improve generative model training.
Fin-Analyst is a hybrid trading agent that utilizes a multi-specialist LLM pipeline to process diverse financial data sources for automated equity market analysis.
Researchers introduced a new method using execution-based semantic interaction graphs to better quantify uncertainty in code-generating large language models.
This research proposes a framework for detecting health misinformation in low-resource languages by combining small language models with culturally sensitive NLP techniques.
Researchers propose a vendor-neutral metric to evaluate the reconstructability and validity of AI agent safety testing results.
The EG-VAR architecture uses the Lean 4 kernel to verify agentic reasoning and tool usage, aiming to reduce hallucinations in empirical inference.
Researchers have developed a method to improve the real-time control of robots by optimizing the asynchronous inference of vision-language-action models on edge hardware.