research note
This paper addresses the challenge that large language model (LLM)-based web agents still face in planning complex, multi-step tasks on the web
research note
This paper addresses the challenge of performing test-time finetuning (TTFT) of large language models (LLMs) in a way that balances quality and low latency, critical for real-time inference
research note
This paper addresses the challenge of fairly and robustly aggregating client updates in federated learning (FL) under data heterogeneity and adversarial participation
research note
The paper addresses the critical challenge of synthetic image detection amid rapidly improving generative AI capabilities that produce highly realistic fake images
research note
This paper addresses the critical security vulnerability known as the MUD-Binding problem within the Manufacturer Usage Description (MUD) standard for IoT device network policy enforcement
research note
GenClaw addresses a key limitation of current agentic image generation systems, which rely heavily on black-box end-to-end pixel synthesis models controlled primarily via natural language prompts
research note
K-FinHallu addresses a significant gap in reliable hallucination detection for Retrieval-Augmented Generation (RAG) systems operating in high-stakes multi-turn financial dialogues in Korean
research note
This paper introduces the problem of Data Mixture Surgery (DMS), which aims to infer the domain-level composition of a large language model's (LLM) pretraining corpus solely from the model's genera…
research note
This paper addresses the challenge of providing AI writing assistance for mental health peer-support interactions using smaller, open-source large language models (LLMs)
research note
This paper addresses a fundamental coherence failure mode in multi-component large language model (LLM) agents that aggregate probabilistic claims from specialists, each viewing only a part of a jo…
research note
This paper addresses a critical limitation in current Vision-Language Models (VLMs) termed “carrier sensitivity,” where model performance degrades substantially when semantically equivalent content…
research note
This paper addresses the critical challenge of document-level machine translation (DocMT) for ultra-long texts, where limited context windows in large language models (LLMs) constrain global cohere…
