Related papers: The Ratchet Effect in Silico through Interaction-D…
CLIP is one of the most popular foundation models and is heavily used for many vision-language tasks, yet little is known about its inner workings. As CLIP is increasingly deployed in real-world applications, it is becoming even more…
Model collapse, a phenomenon characterized by performance degradation due to iterative training on synthetic data, has been widely studied. However, its implications for bias amplification, the progressive intensification of pre-existing…
Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or…
Humans quite frequently interact with conversational agents. The rapid advancement in generative language modeling through neural networks has helped advance the creation of intelligent conversational agents. Researchers typically evaluate…
Social learning plays an important role in the development of human intelligence. As children, we imitate our parents' speech patterns until we are able to produce sounds; we learn from them praising us and scolding us; and as adults, we…
In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…
Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents.…
Global aging calls for scalable and engaging cognitive interventions. Computerized cognitive training (CCT) is a promising non-pharmacological approach, yet many unsupervised programs rely on rigid, hand-authored puzzles that are difficult…
Artificial Intelligence has been developed for decades with the achievement of great progress. Recently, deep learning shows its ability to solve many real world problems, e.g. image classification and detection, natural language…
Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…
The training and deployment of large language models (LLMs) create a feedback loop with human users: models learn human beliefs from data, reinforce these beliefs with generated content, reabsorb the reinforced beliefs, and feed them back…
The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…
When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a "rationality coefficient" capturing…
Biological systems can share and collectively process information to yield emergent effects, despite inherent noise in communication. While man-made systems often employ intricate structural solutions to overcome noise, the structure of…
Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language…
Online platforms increasingly rely on opinion aggregation to allocate real-world attention and resources, yet common signals such as engagement votes or capital-weighted commitments are easy to amplify and often track visibility rather than…
Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they…
Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…
Large language models exhibit societal biases associated with demographic information, including race, gender, and others. Endowing such language models with personalities based on demographic data can enable generating opinions that align…
In social-ecological systems (SESs), social and biophysical dynamics interact within and between structural levels separated by spatial and temporal scales. Cross-scale interactions (CSIs) are interdependences between processes at different…