Search Results for author:
Found 9 papers, 5 papers with code
Do Llamas Work in English? On the Latent Language of Multilingual Transformers
Tracking intermediate embeddings through their high-dimensional space reveals three distinct phases, whereby intermediate embeddings (1) start far away from output token embeddings; (2) already allow for decoding a semantically correct next token in the middle layers, but give higher probability to its version in English than in the input language; (3) finally move into an input-language-specific region of the embedding space.
Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access
This paper introduces sketch-guided constrained decoding (SGCD), a novel approach to constrained decoding for blackbox LLMs, which operates without access to the logits of the blackbox LLM.
The CausalBench challenge: A machine learning contest for gene network inference from single-cell perturbation data
In drug discovery, mapping interactions between genes within cellular systems is a crucial early step.
Learning DAGs from Data with Few Root Causes
We prove identifiability in this new setting and show that the true DAG is the global minimizer of the $L^0$-norm of the vector of root causes.
Causal Fourier Analysis on Directed Acyclic Graphs and Posets
Specifically, we model the spread of an infection on such a DAG obtained from real-world contact tracing data and learn the infection signal from samples assuming sparsity in the Fourier domain.
Instance-wise algorithm configuration with graph neural networks
We pose this task as a supervised learning problem: First, we compile a large dataset of the solver performance for various configurations and all provided MILP instances.
Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases
Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain.
Discrete Signal Processing with Set Functions
Set functions are functions (or signals) indexed by the powerset (set of all subsets) of a finite set N. They are fundamental and ubiquitous in many application domains and have been used, for example, to formally describe or quantify loss functions for semantic image segmentation, the informativeness of sensors in sensor networks the utility of sets of items in recommender systems, cooperative games in game theory, or bidders in combinatorial auctions.
Powerset Convolutional Neural Networks
We present a novel class of convolutional neural networks (CNNs) for set functions, i. e., data indexed with the powerset of a finite set.
