9 citations · 32 across the 14 of their papers we have counts for
17 papers
Sparse RL Relaxation for LLM Reasoning
Jiabin Fan, Matthias Lindemann, Zita Marinho +2
Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the ide…
Native Hierarchical and Compositional Representations with Subspace Embeddings
Gabriel Moreira, Zita Marinho, Manuel Marques +2
Traditional embeddings represent datapoints as vectors, which makes similarity easy to compute but limits how well they capture hierarchies and compositionality. We propose a funda…
AuPair: Golden Example Pairs for Code Repair
Aditi Mavalankar, Hassan Mansoor, Zita Marinho +2
Scaling up inference-time compute has proven to be a valuable strategy in improving the performance of Large Language Models (LLMs) without fine-tuning. An important task that can…
Chunk-based Nearest Neighbor Machine Translation
Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Semi-parametric models, which augment generation with retrieval, have led to impressive results in language modeling and machine translation, due to their ability to retrieve fine-…
Efficient Machine Translation Domain Adaptation
Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus…
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos, Eszter Vértes, Zita Marinho +7
Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with…
Self-Consistent Models and Values
Gregory Farquhar, Kate Baumli, Zita Marinho +4
Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment. In particular, models enable planning,…
-former: Infinite Memory Transformer
Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Transformers are unable to model long-term memories effectively, since the amount of computation they need to perform grows with the context length. While variations of efficient t…
Priberam at MESINESP Multi-label Classification of Medical Texts Task
Ruben Cardoso, Zita Marinho, Afonso Mendes +1
Medical articles provide current state of the art treatments and diagnostics to many medical practitioners and professionals. Existing public databases such as MEDLINE contain over…
Sparse Text Generation
Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Current state-of-the-art text generators build on powerful language models such as GPT-2, achieving impressive performance. However, to avoid degenerate text, they require sampling…
Sparse and Structured Visual Attention
Pedro Henrique Martins, Vlad Niculae, Zita Marinho +1
Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some pro…
Joint Learning of Named Entity Recognition and Entity Linking
Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Named entity recognition (NER) and entity linking (EL) are two fundamentally related tasks, since in order to perform EL, first the mentions to entities have to be detected. Howeve…
Jointly Extracting and Compressing Documents with Summary State Representations
Afonso Mendes, Shashi Narayan, Sebastião Miranda +3
We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the…
Automated Fact Checking in the News Room
Sebastião Miranda, David Nogueira, Afonso Mendes +5
Fact checking is an essential task in journalism; its importance has been highlighted due to recently increased concerns and efforts in combating misinformation. In this paper, we…
Recurrent Predictive State Policy Networks
Ahmed Hefny, Zita Marinho, Wen Sun +2
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in par…
Unsupervised Learning for Nonlinear PieceWise Smooth Hybrid Systems
Gilwoo Lee, Zita Marinho, Aaron M. Johnson +3
This paper introduces a novel system identification and tracking method for PieceWise Smooth (PWS) nonlinear stochastic hybrid systems. We are able to correctly identify and track…
Functional Gradient Motion Planning in Reproducing Kernel Hilbert Spaces
Zita Marinho, Anca Dragan, Arun Byravan +3
We introduce a functional gradient descent trajectory optimization algorithm for robot motion planning in Reproducing Kernel Hilbert Spaces (RKHSs). Functional gradient algorithms…