Never lost in the middle: Improving large language models via attention strengthening question answering
While large language models (LLMs) are equipped with longer text input capabilities than
before, they are struggling to seek correct information in long contexts. The" lost in the …
before, they are struggling to seek correct information in long contexts. The" lost in the …
[PDF][PDF] Explore, select, derive, and recall: Augmenting llm with human-like memory for mobile task automation
The advent of large language models (LLMs) has opened up new opportunities in the field
of mobile task automation. Their superior language understanding and reasoning …
of mobile task automation. Their superior language understanding and reasoning …
Preference-Conditioned Language-Guided Abstraction
Learning from demonstrations is a common way for users to teach robots, but it is prone to
spurious feature correlations. Recent work constructs state abstractions, ie visual …
spurious feature correlations. Recent work constructs state abstractions, ie visual …
AI for Mathematics: A Cognitive Science Perspective
Mathematics is one of the most powerful conceptual systems developed and used by the
human species. Dreams of automated mathematicians have a storied history in artificial …
human species. Dreams of automated mathematicians have a storied history in artificial …
Zero-shot compositional reinforcement learning in humans
People can easily evoke previously learned concepts, compose them, and apply the result
to solve novel tasks on the first attempt. The aim of this paper is to improve our …
to solve novel tasks on the first attempt. The aim of this paper is to improve our …
Cognitive graphs: Representational substrates for planning
Making plans for upcoming actions is a computationally demanding process. To mitigate
these demands, agents can build representations–of states, actions, and their sequential …
these demands, agents can build representations–of states, actions, and their sequential …
Importance of prefrontal meta control in human-like reinforcement learning
Recent investigation on reinforcement learning (RL) has demonstrated considerable
flexibility in dealing with various problems. However, such models often experience difficulty …
flexibility in dealing with various problems. However, such models often experience difficulty …
m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks
Real-world multi-modal problems are rarely solved by a single machine learning model, and
often require multi-step computational plans that involve stitching several models. Tool …
often require multi-step computational plans that involve stitching several models. Tool …
Exploring the hierarchical structure of human plans via program generation
Human behavior is inherently hierarchical, resulting from the decomposition of a task into
subtasks or an abstract action into concrete actions. However, behavior is typically …
subtasks or an abstract action into concrete actions. However, behavior is typically …
[PDF][PDF] Group coordination catalyzes individual and cultural intelligence
A large program of research has aimed to ground large-scale cultural phenomena in
processes taking place within individual minds. For example, investigating whether …
processes taking place within individual minds. For example, investigating whether …