Researchers have developed a new reinforcement learning framework called DARS for instruction-based image editing. The framework assigns credit to bot...
The authors argue that software is undergoing a third paradigm shift, from traditional instructions to data-driven machine learning, to context- and r...
Researchers have created a benchmark called MemTrapBench to test how large language models use memory. They found that even when memories are accurate...
ContractScrub is a benchmark designed to evaluate the ability of large language models (LLMs) to review and correct errors in legal contracts. The ben...
Researchers have developed an automated method to classify changes in Electronic Navigational Charts (ENCs) used in maritime navigation. The system us...
Researchers have introduced InsufficiencyBench, a new benchmark for evaluating the performance of large language models (LLMs) in providing legal advi...
Researchers have created a benchmark called RuleMaze to test the ability of large language models to perform visual spatial planning under specific ru...
Researchers have developed QUASAR, a quantum-classical neural network that provides robust physical-layer authentication (PLA) to X-band SAR satellite...
Researchers have developed an adaptive reasoning model that can adjust its own computational effort based on the difficulty of a problem. The model, t...
Researchers have developed a machine learning model to predict fraudulent 'memecoins' on the Solana blockchain. These coins are designed to quickly ga...
Researchers have been studying how large language model (LLM) agents can learn skills from one task and apply them to another. A recent study publishe...
Researchers have developed a method to audit self-improvement in language models. They tested three rounds of LoRA self-training on the Qwen3-8B model...