The standard method for aligning Language Learning Models (LLMs) is known as RLHF, or Reinforcement Learning from Human Feedback. However, new developments in offline alignment methods - such as Direct Preference Optimization (DPO) - challenge RLHF's reliance on on-policy sampling. Unlike online methods, offline algorithms use existing datasets, making them simpler, cheaper, and often more…
Artificial Intelligence (AI) systems have demonstrated a fascinating trend of converging data representations across different architectures, training objectives, and modalities. Researchers propose the "Platonic Representation Hypothesis" to explain this phenomenon. Essentially, this hypothesizes that various AI models are striving to capture a unified representation of the underlying reality that forms the basis for observable data.…
A team of researchers from MIT and other institutions has discovered a remarkable cause of performance deterioration in chatbots and found a simple solution that allows persistent, uninterrupted dialogue. This problem occurs when human-AI interaction involves continuous rounds of conversation, which can overburden the large language machine-learning models that power chatbots like ChatGPT.
The researchers have…
Researchers from MIT and other institutions have developed a method that prevents large AI language machines from crashing during lengthy dialogues. The solution, known as StreamingLLM, tweaks the key-value cache (a sort of conversation memory) of large language models to ensure the first few data pieces remain in memory. Typically, once the cache's capacity is…
Artificial neural networks (ANNs) have remarkable capabilities when trained on natural data. Regardless of exact initialization, dataset, or training objective, neural networks trained on the same data domain tend to converge to similar patterns. For different image models, the initial layer weights typically converge to Gabor filters and color-contrast detectors, underlying a sort of "universal"…
Researchers from MIT and other institutions have found a solution to an issue that causes machine-learning model-run chatbots to malfunction during long, continuous dialogues. They found that significant delays or crashes happen when the key-value cache, essentially the conversation memory, becomes overloaded leading to early data being ejected and the model to fail. The researchers…
Large models pre-training on time series data is a frequent challenge due to the absence of a comprehensive public time series repository, diverse time series characteristics, and emerging benchmarks for model testing. Despite this, time series analysis remains integral in various fields, including weather forecasting, heart rate irregularity detection, and anomaly identification in software deployments.…
Researchers from MIT and the University of Basel in Switzerland have developed a new machine-learning framework that can map phase diagrams for novel physical systems automatically. By applying generative artificial intelligence models, the team has developed a more efficient method for tracking and understanding phase transitions in water and other complex physical systems, which offers…
In the fields of traffic management and urban planning, understanding the most efficient routes based on multiple variables has significant potential benefits. This approach assumes that when individuals are choosing a route, they're trying to minimize certain costs such as travel time, comfort, tolls, and distance. Understanding these costs can help improve traffic flow and…