Related papers: Architecture and Knowledge Representation for Comp…
This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained…
The present paper introduces Scala-of-Coq, a new compiler that allows a Coq-based synthesis of Scala programs which are "correct-by-construction". A typical workflow features a user implementing a Coq functional program, proving this…
Scientific computing is increasingly incorporating the advancements in machine learning and the ability to work with large amounts of data. At the same time, machine learning models are becoming increasingly sophisticated and exhibit many…
The work is devoted to Computability Logic (CoL) -- the philosophical/mathematical platform and long-term project for redeveloping classical logic after replacing truth} by computability in its underlying semantics (see…
Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes. As a result, these black-box models often learn to exploit biases…
This thesis describes our ongoing work on Contrastive Predictive Coding (CPC) features for speaker verification. CPC is a recently proposed representation learning framework based on predictive coding and noise contrastive estimation. We…
With the goal of facilitating team collaboration, we propose a new approach to building vector representations of individual developers by capturing their individual contribution style, or coding style. Such representations can find use in…
We describe a novel way of representing a symbolic knowledge base (KB) called a sparse-matrix reified KB. This representation enables neural modules that are fully differentiable, faithful to the original semantics of the KB, expressive…
Causal Bayesian networks have become a powerful technology for reasoning under uncertainty in areas that require transparency and explainability, by relying on causal assumptions that enable us to simulate hypothetical interventions. The…
Knowledge representation is a popular research field in IT. As mathematical knowledge is most formalized, its representation is important and interesting. Mathematical knowledge consists of various mathematical theories. In this paper we…
The scalability of neutral-atom quantum computing is increasingly limited by a compiler--architecture challenge: logical circuits must be mapped onto dynamically reconfigurable atom arrays while controlling crosstalk, transport overhead,…
Compiler auto-tuning faces a dichotomy between traditional black-box search methods, which lack semantic guidance, and recent Large Language Model (LLM) approaches, which often suffer from superficial pattern matching and causal opacity. In…
Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent's knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection…
Model-based testing is a promising technology for black-box software and hardware testing, in which test cases are generated automatically from high-level specifications. Nowadays, systems typically consist of multiple interacting…
In this paper, we propose a novel Knowledge-based Embodied Question Answering (K-EQA) task, in which the agent intelligently explores the environment to answer various questions with the knowledge. Different from explicitly specifying the…
To develop general-purpose collaborative agents, humans need reliable AI systems that can (1) adapt to new domains and (2) transparently reason with uncertainty to allow for verification and correction. Black-box models demonstrate powerful…
Causal discovery has been widely studied, yet many existing methods rely on strong assumptions or fall into two extremes: either depending on costly interventional signals or partial ground truth as strong priors, or adopting purely data…
Accountability is an often called for property of technical systems. It is a requirement for algorithmic decision systems, autonomous cyber-physical systems, and for software systems in general. As a concept, accountability goes back to the…
We propose a perspective on knowledge compilation which calls for analyzing different compilation approaches according to two key dimensions: the succinctness of the target compilation language, and the class of queries and transformations…
We introduce ACE-TA, the Agentic Coding and Explanations Teaching Assistant framework, that autonomously routes conceptual queries drawn from programming course material to grounded Q&A, stepwise coding guidance, and automated quiz…