Related papers: On the Executability of Interactive Computation
Quantum computations usually take place under the control of the classical world. We introduce a Classically-controlled Quantum Turing Machine (CQTM) which is a Turing Machine (TM) with a quantum tape for acting on quantum data, and a…
We propose a logic of interactive proofs as a framework for an intuitionistic foundation for interactive computation, which we construct via an interactive analog of the Goedel-McKinsey-Tarski-Artemov definition of Intuitionistic Logic as…
In multi-agent IR pipelines for tasks such as search and ranking, LLM-based agents exchange intermediate reasoning in terms of Chain-of-Thought (CoT) with each other. Current CoT evaluation narrowly focuses on target task accuracy. However,…
We look at consciousness through the lens of Theoretical Computer Science, a branch of mathematics that studies computation under resource limitations, distinguishing functions that are efficiently computable from those that are not. From…
Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…
Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs' privileged access to their own internals can be leveraged…
Design-by-contract is an important technique for model-based design in which a composite system is specified by a collection of contracts that specify the behavioural assumptions and guarantees of each component. In this paper, we describe…
This work aims at shedding some light on connections between finite state machines (FSMs), and recurrent neural networks (RNNs). Examined connections in this master's thesis is threefold: the extractability of finite state machines from…
While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where…
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering RNN-based approaches is improving their explainability and interpretability. In this work we present MEME: a model…
Regular functions from infinite words to infinite words can be equivalently specified by MSO-transducers, streaming $\omega$-string transducers as well as deterministic two-way transducers with look-ahead. In their one-way restriction, the…
We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users. RecSim allows the creation of new environments that reflect particular…
Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…
We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making. MTM takes a trajectory, such as a state-action sequence, and aims to reconstruct the trajectory conditioned on random subsets of the same…
STEM education researchers are often interested in identifying moments of students' mechanistic reasoning for deeper analysis, but have limited capacity to search through many team conversation transcripts to find segments with a high…
Machine learning often requires millions of examples to produce static, black-box models. In contrast, interactive task learning (ITL) emphasizes incremental knowledge acquisition from limited instruction provided by humans in modalities…
Test-Time Compute (TTC) has emerged as a powerful paradigm for enhancing the performance of Large Language Models (LLMs) at inference, leveraging strategies such as Test-Time Training (TTT) and Retrieval-Augmented Generation (RAG). However,…
This paper discusses "computational" systems capable of "computing" functions not computable by predefined Turing machines if the systems are not isolated from their environment. Roughly speaking, these systems can change their finite…
Teachable interfaces can empower end-users to attune machine learning systems to their idiosyncratic characteristics and environment by explicitly providing pertinent training examples. While facilitating control, their effectiveness can be…
In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the redundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to…