Author name cluster

Ricardo Cabral

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Logic.py: Bridging the Gap between LLMs and Constraint Solvers

Pascal Kesseli
Peter O'Hearn
Ricardo Cabral

We present a novel approach to formalise and solve search-based problems using large language models, which significantly improves upon previous state-of-the-art results. We demonstrate the efficacy of this approach on benchmarks like the logic puzzles tasks in ZebraLogicBench. Instead of letting the LLM attempt to directly solve the puzzles, our method prompts the model to formalise the problem in a logic-focused, human-readable domain-specific language (DSL) called Logic. py. This formalised representation is then solved using a constraint solver, leveraging the strengths of both the language model and the solver. Our approach achieves a remarkable 65% absolute improvement over the baseline performance of Llama 3. 1 70B on ZebraLogicBench, setting a new state-of-the-art with an accuracy of over 90%. This significant advancement demonstrates the potential of combining language models with domain-specific languages and auxiliary tools on traditionally challenging tasks for LLMs.

PDF Details

NeurIPS Conference 2011 Conference Paper

Matrix Completion for Multi-label Image Classification

Ricardo Cabral
Fernando Torre
Joao Costeira
Alexandre Bernardino

Recently, image categorization has been an active research topic due to the urgent need to retrieve and browse digital images via semantic keywords. This paper formulates image categorization as a multi-label classification problem using recent advances in matrix completion. Under this setting, classification of testing data is posed as a problem of completing unknown label entries on a data matrix that concatenates training and testing features with training labels. We propose two convex algorithms for matrix completion based on a Rank Minimization criterion specifically tailored to visual data, and prove its convergence properties. A major advantage of our approach w. r. t. standard discriminative classification methods for image categorization is its robustness to outliers, background noise and partial occlusions both in the feature and label space. Experimental validation on several datasets shows how our method outperforms state-of-the-art algorithms, while effectively capturing semantic concepts of classes.

PDF Details

IROS Conference 1990 Conference Paper

An algorithm for the steering control of mobile robots

Carlos Resendes
Ricardo Cabral
M. Isabel Ribeiro

Presents a method that combines the path planning and the steering control of autonomous mobile robots (AMR) in uncertain environments. The two problems are solved independently, using off-line and on-line procedures respectively, the link between them being established by a set of critical points defined along the trajectory. The path planner evaluates these points by modeling the free space using a quadtree. The steering control algorithm derives the local feedback control to guide the AMR through a collision-free trajectory. The approach taken considers a modification of the generalized potential field technique leading to improvements in the motion smoothness and in the trajectory local optimization. Simulation results are presented.

Details