Search Results for author:
Found 15 papers, 3 papers with code
Can Memory-Augmented Language Models Generalize on Reasoning-in-a-Haystack Tasks?
This generalization of MemReasoner is achieved using none-to-weak supporting fact supervision (using none and 1\% of supporting facts for one- and two-hop tasks, respectively).
Large Language Models can be Strong Self-Detoxifiers
Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs).
Generation Constraint Scaling Can Mitigate Hallucination
Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge.
Needle in the Haystack for Memory Based Large Language Models
Current large language models (LLMs) often perform poorly on simple fact retrieval tasks.
Larimar: Large Language Models with Episodic Memory Control
Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today.
NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models
Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks.
Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes
In particular, we are interested in discovering instance-level causal structures in an unsupervised manner.
Cardinality-Regularized Hawkes-Granger Model
In this paper, we propose a mathematically well-defined sparse causal learning framework based on a cardinality-regularized Hawkes process, which remedies the pathological issues of existing approaches.
Directed Graph Auto-Encoders
We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels.
Projection techniques to update the truncated SVD of evolving matrices
This paper considers the problem of updating the rank-k truncated Singular Value Decomposition (SVD) of matrices subject to the addition of new rows and/or columns over time.
Accelerating Physics-Based Simulations Using Neural Network Proxies: An Application in Oil Reservoir Modeling
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers.
Low rank methods for multiple network alignment
While there are a large number of effective techniques for pairwise problems with two networks that scale in terms of edges, these cannot be readily extended to align multiple networks as the computational complexity will tend to grow exponentially with the number of networks. In this paper we introduce a new multiple network alignment algorithm and framework that is effective at aligning thousands of networks with thousands of nodes.
Provably convergent acceleration in factored gradient descent with applications in matrix sensing
We present theoretical results on the convergence of \emph{non-convex} accelerated gradient descent in matrix factorization models with $\ell_2$-norm loss.
MXNET-MPI: Embedding MPI parallelism in Parameter Server Task Model for scaling Deep Learning
In this paper, we discuss the drawbacks of such approaches and propose a generic framework supporting both PS and MPI programming paradigms, co-existing at the same time.
