Related papers: Synthelite: Chemist-aligned and feasibility-aware …

Designing synthetic routes for novel molecules is pivotal in various fields like medicine and chemistry. In this process, researchers need to explore a set of synthetic reactions to transform starting molecules into intermediates step by…

Many structured prediction and reasoning tasks can be framed as program synthesis problems, where the goal is to generate a program in a domain-specific language (DSL) that transforms input data into the desired output. Unfortunately,…

We show that given a desired closed-loop response for a system, there exists an affine subspace of controllers that achieve this response. By leveraging the existence of this subspace, we are able to separate controller design from…

Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse datasets for long-context instruction tuning. Existing data…

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be…

From medicines to materials, small organic molecules are indispensable for human well-being. To plan their syntheses, chemists employ a problem solving technique called retrosynthesis. In retrosynthesis, target molecules are recursively…

Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long…

Optimization of Mixed-Integer Non-Linear Programming (MINLP) supports important decisions in applications such as Chemical Process Engineering. But current solvers have limited ability for deductive reasoning or the use of domain-specific…

High-level synthesis (HLS) tools have brought FPGA development into the mainstream, by allowing programmers to design architectures using familiar languages such as C, C++, and OpenCL. While the move to these languages has brought…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

We introduce an approach that aims to combine the usage of satisfiability modulo theories (SMT) solvers with the Combinatory Logic Synthesizer (CL)S framework. (CL)S is a tool for the automatic composition of software components from a…

Reducing hallucination of Large Language Models (LLMs) is imperative for use in the sciences, where reliability and reproducibility are crucial. However, LLMs inherently lack long-term memory, making it a nontrivial, ad hoc, and inevitably…

Prompt learning is a powerful technique for transferring Vision-Language Models (VLMs) such as CLIP to downstream tasks. However, the prompt-based methods that are fine-tuned solely with base classes may struggle to generalize to novel…

Scientific discovery plays a pivotal role in advancing human society, and recent progress in large language models (LLMs) suggests their potential to accelerate this process. However, it remains unclear whether LLMs can autonomously…

Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a…

We propose the problem of multi-agent path planning for a generalization of the classic Cops and Robbers game via reactive synthesis. Specifically, through the application of LTLt and Coordination Synthesis, we aim to check whether various…

Traditional benchmarking in NLP typically involves using static held-out test sets. However, this approach often results in an overestimation of performance and lacks the ability to offer comprehensive, interpretable, and dynamic…

Large Language Models (LLMs), deep learning architectures with typically over 10 billion parameters, have recently begun to be integrated into various cyber-physical systems (CPS) such as robotics, industrial automation, and autopilot…

Retrosynthetic planning is a fundamental task in organic chemistry, yet remains challenging due to its combinatorial complexity. To address this, conventional approaches typically rely on hybrid frameworks that combine single-step…

Translating natural language questions into SQL queries, known as text-to-SQL, is a long-standing research problem. Effective text-to-SQL synthesis can become very challenging due to (i) the extensive size of database catalogs (descriptions…