Search Results for author:
Found 49 papers, 16 papers with code
Echoes in AI: Quantifying Lack of Plot Diversity in LLM Outputs
We examine two state-of-the-art LLMs, GPT-4 and LLaMA-3, on story generation and discover that LLM-generated stories often consist of plot elements that are echoed across a number of generations.
Game Plot Design with an LLM-powered Assistant: An Empirical Study with Game Designers
We introduce GamePlot, an LLM-powered assistant that supports game designers in crafting immersive narratives for turn-based games, and allows them to test these games through a collaborative game play and refine the plot throughout the process.
Fast constrained sampling in pre-trained diffusion models
Diffusion models have dominated the field of large, generative image models, with the prime examples of Stable Diffusion and DALL-E 3 being widely adopted.
fPLSA: Learning Semantic Structures in Document Collections Using Foundation Models
These tags can be used to model the structure of given documents and for hierarchical sampling of new texts.
Player-Driven Emergence in LLM-Driven Game Narrative
We explore how interaction with large language models (LLMs) can give rise to emergent behaviors, empowering players to participate in the evolution of game narratives.
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task.
Investigating Agency of LLMs in Human-AI Collaboration Tasks
While LLMs are being developed to simulate human behavior and serve as human-like agents, little attention has been given to the Agency that these models should possess in order to proactively manage the direction of interaction and collaboration.
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention.
GPT is becoming a Turing machine: Here are some ways to program it
We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall) programs that involve loops, including several popular algorithms found in computer science curricula or software developer interviews.
ThinkSum: Probabilistic reasoning over sets using large language models
Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs.
Diffusion models as plug-and-play priors
We consider the problem of inferring high-dimensional data $\mathbf{x}$ in a model that consists of a prior $p(\mathbf{x})$ and an auxiliary differentiable constraint $c(\mathbf{x},\mathbf{y})$ on $x$ given some additional information $\mathbf{y}$.
Resolving label uncertainty with implicit posterior models
We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label.
Coherence boosting: When your pretrained language model is not paying enough attention
Long-range semantic coherence remains a challenge in automatic language generation and understanding.
Resolving label uncertainty with implicit generative models
In prediction problems, coarse and imprecise sources of input can provide rich information about labels, but are not readily used by discriminative learners.
Studying word order through iterative shuffling
As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax.
Multi-Label Learning from Single Positive Labels
When the number of potential labels is large, human annotators find it difficult to mention all applicable labels for each training image.
Video Imprint
In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i. e., the video imprint.
GPT Perdetry Test: Generating new meanings for new words
Human innovation in language, such as inventing new words, is a challenge for pretrained language models.
Compositional Processing Emerges in Neural Networks Solving Math Problems
A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition.
High-resolution land cover change from low-resolution labels: Simple baselines for the 2021 IEEE GRSS Data Fusion Contest
We present simple algorithms for land cover change detection in the 2021 IEEE GRSS Data Fusion Contest.
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context
We explore learning web-based tasks from a human teacher through natural language explanations and a single demonstration.
Mining self-similarity: Label super-resolution with epitomic representations
We show that simple patch-based models, such as epitomes, can have superior performance to the current state of the art in semantic segmentation and label super-resolution, which uses deep convolutional neural networks.
The GeoLifeCLEF 2020 Dataset
Understanding the geographic distribution of species is a key concern in conservation.
Local Context Normalization: Revisiting Local Normalization
In many vision applications the local spatial context of the features is important, but most common normalization schemes including Group Normalization (GN), Instance Normalization (IN), and Layer Normalization (LN) normalize over the entire spatial dimension of a feature.
A deep active learning system for species identification and counting in camera trap images
However, the accuracy of results depends on the amount, quality, and diversity of the data available to train models, and the literature has focused on projects with millions of relevant, labeled training images.
Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving
We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure.
Ranked #1 on
Question Answering
on Mathematics Dataset
Human-Machine Collaboration for Fast Land Cover Mapping
This bi-directional feedback loop allows humans to learn how the model responds to new data.
Label super-resolution networks
We present a deep learning-based method for super-resolving coarse (low-resolution) labels assigned to groups of image pixels into pixel-level (high-resolution) labels, given the joint distribution between those low- and high-resolution labels.
Label Super Resolution with Inter-Instance Loss
On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient.
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
FSNet has the same architecture as that of the baseline CNN to be compressed, and each convolution layer of FSNet has the same number of filters from FS as that of the basline CNN in the forward process.
A Spatial Model for Extracting and Visualizing Latent Discourse Structure in Text
We present a generative probabilistic model of documents as sequences of sentences, and show that inference in it can lead to extraction of long-range latent discourse structure from a collection of documents.
Discovering Order in Unordered Datasets: Generative Markov Networks
The assumption that data samples are independently identically distributed is the backbone of many learning algorithms.
WSNet: Compact and Efficient Networks Through Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks.
Learning Markov Chain in Unordered Dataset
In this technical report, we introduce OrderNet that can be used to extract the order of data instances in an unsupervised way.
Summarization and Classification of Wearable Camera Streams by Learning the Distributions Over Deep Features of Out-Of-Sample Image Sequences
In particular, we use constrained Markov walks over a counting grid for modeling image sequences, which not only yield good latent representations, but allow for excellent classification with only a handful of labeled training examples of the new scenes or objects, a scenario typical in lifelogging applications.
Steering Output Style and Topic in Neural Response Generation
We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation.
Discriminative Similarity for Clustering and Semi-Supervised Learning
By generalization analysis via Rademacher complexity, the generalization error bound for the kernel classifier learned from hypothetical labeling is expressed as the sum of pairwise similarity between the data from different classes, parameterized by the weights of the kernel classifier.
On the Suboptimality of Proximal Gradient Descent for $\ell^{0}$ Sparse Approximation
We study the proximal gradient descent (PGD) method for $\ell^{0}$ sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper.
ER3: A Unified Framework for Event Retrieval, Recognition and Recounting
We develop a unified framework for complex event retrieval, recognition and recounting.
Iterative Refinement of the Approximate Posterior for Directed Belief Networks
Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods.
Hierarchical learning of grids of microtopics
The counting grid is a grid of microtopics, sparse word/feature distributions.
Capturing spatial interdependence in image features: the counting grid, an epitomic representation for bags of features
The space of all possible feature count combinations is constrained both by the properties of the larger scene and the size and the location of the window into it.
Documents as multiple overlapping windows into grids of counts
The counting grid \cite{cgUai} models this spatial metaphor literally: it is multidimensional grid of word distributions learned in such a way that a document's own distribution of features can be modeled as the sum of the histograms found in a window into the grid.
A Comparative Framework for Preconditioned Lasso Algorithms
The Lasso is a cornerstone of modern multivariate data analysis, yet its performance suffers in the common situation in which covariates are correlated.
Capturing Layers in Image Collections with Componential Models: From the Layered Epitome to the Componential Counting Grid
Recently, the Counting Grid (CG) model [5] was developed to represent each input image as a point in a large grid of feature counts.
In the sight of my wearable camera: Classifying my visual experience
We introduce and we analyze a new dataset which resembles the input to biological vision systems much more than most previously published ones.
Structural epitome: a way to summarize one’s visual experience
In order to study the properties of total visual input in humans, a single subject wore a camera for two weeks capturing, on average, an image every 20 seconds (www. research. microsoft. com/~jojic/aihs).
Exact inference and learning for cumulative distribution functions on loopy graphs
We compare the performance of the resulting algorithm to Mathematica and D*, and we apply our method to learning models for rainfall and H1N1 data, where we show that CDNs with cycles are able to provide a significantly better fits to the data as compared to tree-structured and unstructured CDNs and other heavy-tailed multivariate distributions such as the multivariate copula and logistic models.
Free energy score space
Score functions induced by generative models extract fixed-dimension feature vectors from different-length data observations by subsuming the process of data generation, projecting them in highly informative spaces called score spaces.
