Search Results for author: Nebojsa Jojic

Found 44 papers, 14 papers with code

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

no code implementations25 Sep 2023 Ida Momennejad, Hosein Hasanbeig, Felipe Vieira, Hiteshi Sharma, Robert Osazuwa Ness, Nebojsa Jojic, Hamid Palangi, Jonathan Larson

First, we propose CogEval, a cognitive science-inspired protocol for the systematic evaluation of cognitive capacities in Large Language Models.

Towards Dialogue Systems with Agency in Human-AI Collaboration Tasks

no code implementations22 May 2023 ASHISH SHARMA, Sudha Rao, Chris Brockett, Akanksha Malhotra, Nebojsa Jojic, Bill Dolan

Agency, the capacity to proactively shape events, is crucial to how humans interact and collaborate with other humans.

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

no code implementations17 May 2023 Weijia Xu, Andrzej Banburski-Fahey, Nebojsa Jojic

We introduce Reprompting, an iterative sampling algorithm that searches for 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

no code implementations25 Mar 2023 Ana Jojic, Zhen Wang, Nebojsa Jojic

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

no code implementations4 Oct 2022 Batu Ozturkler, Nikolay Malkin, Zhen Wang, Nebojsa Jojic

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

1 code implementation17 Jun 2022 Alexandros Graikos, Nikolay Malkin, Nebojsa Jojic, Dimitris Samaras

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 $\mathbf{y}$.

Combinatorial Optimization Denoising +2

Resolving label uncertainty with implicit posterior models

1 code implementation28 Feb 2022 Esther Rolf, Nikolay Malkin, Alexandros Graikos, Ana Jojic, Caleb Robinson, Nebojsa Jojic

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.

Common Sense Reasoning text-classification +1

Resolving label uncertainty with implicit generative models

no code implementations29 Sep 2021 Esther Rolf, Nikolay Malkin, Alexandros Graikos, Ana Jojic, Caleb Robinson, Nebojsa Jojic

In prediction problems, coarse and imprecise sources of input can provide rich information about labels, but are not readily used by discriminative learners.

Common Sense Reasoning text-classification +1

Studying word order through iterative shuffling

1 code implementation EMNLP 2021 Nikolay Malkin, Sameera Lanka, Pranav Goel, Nebojsa Jojic

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.

Language Modelling

Video Imprint

no code implementations7 Jun 2021 Zhanning Gao, Le Wang, Nebojsa Jojic, Zhenxing Niu, Nanning Zheng, Gang Hua

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.

Language Modelling Retrieval

GPT Perdetry Test: Generating new meanings for new words

no code implementations NAACL 2021 Nikolay Malkin, Sameera Lanka, Pranav Goel, Sudha Rao, Nebojsa Jojic

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

1 code implementation19 May 2021 Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, Nebojsa Jojic, Paul Smolensky, Jianfeng Gao

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition.

Mathematical Reasoning

Mining self-similarity: Label super-resolution with epitomic representations

1 code implementation ECCV 2020 Nikolay Malkin, Anthony Ortiz, Caleb Robinson, Nebojsa Jojic

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.

Semantic Segmentation Super-Resolution

The GeoLifeCLEF 2020 Dataset

1 code implementation8 Apr 2020 Elijah Cole, Benjamin Deneu, Titouan Lorieul, Maximilien Servajean, Christophe Botella, Dan Morris, Nebojsa Jojic, Pierre Bonnet, Alexis Joly

Understanding the geographic distribution of species is a key concern in conservation.

Local Context Normalization: Revisiting Local Normalization

1 code implementation CVPR 2020 Anthony Ortiz, Caleb Robinson, Dan Morris, Olac Fuentes, Christopher Kiekintveld, Md Mahmudulla Hassan, Nebojsa Jojic

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.

Instance Segmentation object-detection +3

A deep active learning system for species identification and counting in camera trap images

1 code implementation22 Oct 2019 Mohammad Sadegh Norouzzadeh, Dan Morris, Sara Beery, Neel Joshi, Nebojsa Jojic, Jeff Clune

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.

Active Learning Decision Making +1

Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving

3 code implementations15 Oct 2019 Imanol Schlag, Paul Smolensky, Roland Fernandez, Nebojsa Jojic, Jürgen Schmidhuber, Jianfeng Gao

We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure.

Question Answering

Label super-resolution networks

no code implementations ICLR 2019 Kolya Malkin, Caleb Robinson, Le Hou, Nebojsa Jojic

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.

Semantic Segmentation Super-Resolution

Label Super Resolution with Inter-Instance Loss

no code implementations9 Apr 2019 Maozheng Zhao, Le Hou, Han Le, Dimitris Samaras, Nebojsa Jojic, Danielle Fassler, Tahsin Kurc, Rajarsi Gupta, Kolya Malkin, Shroyer Kenneth, Joel Saltz

On the other hand, collecting low resolution labels (labels for a block of pixels) for these high resolution images is much more cost efficient.

Semantic Segmentation Super-Resolution

FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary

no code implementations ICLR 2020 Yingzhen Yang, Jiahui Yu, Nebojsa Jojic, Jun Huan, Thomas S. Huang

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.

General Classification Image Classification +4

A Spatial Model for Extracting and Visualizing Latent Discourse Structure in Text

no code implementations ACL 2018 Shashank Srivastava, Nebojsa Jojic

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.

Information Retrieval Reading Comprehension +4

Discovering Order in Unordered Datasets: Generative Markov Networks

no code implementations ICLR 2018 Yao-Hung Hubert Tsai, Han Zhao, Nebojsa Jojic, Ruslan Salakhutdinov

The assumption that data samples are independently identically distributed is the backbone of many learning algorithms.

Learning Markov Chain in Unordered Dataset

no code implementations ICLR 2018 Yao-Hung Hubert Tsai, Han Zhao, Ruslan Salakhutdinov, Nebojsa Jojic

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

no code implementations ICCV 2017 Alessandro Perina, Sadegh Mohammadi, Nebojsa Jojic, Vittorio Murino

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.

General Classification

Steering Output Style and Topic in Neural Response Generation

1 code implementation EMNLP 2017 Di Wang, Nebojsa Jojic, Chris Brockett, Eric Nyberg

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation.

Response Generation Text Generation

On the Suboptimality of Proximal Gradient Descent for $\ell^{0}$ Sparse Approximation

no code implementations5 Sep 2017 Yingzhen Yang, Jiashi Feng, Nebojsa Jojic, Jianchao Yang, Thomas S. Huang

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.

Compressive Sensing Dimensionality Reduction

Discriminative Similarity for Clustering and Semi-Supervised Learning

no code implementations5 Sep 2017 Yingzhen Yang, Feng Liang, Nebojsa Jojic, Shuicheng Yan, Jiashi Feng, Thomas S. Huang

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.


Iterative Refinement of the Approximate Posterior for Directed Belief Networks

1 code implementation NeurIPS 2016 R. Devon Hjelm, Kyunghyun Cho, Junyoung Chung, Russ Salakhutdinov, Vince Calhoun, Nebojsa Jojic

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

no code implementations12 Mar 2015 Nebojsa Jojic, Alessandro Perina, Dongwoo Kim

The counting grid is a grid of microtopics, sparse word/feature distributions.

General Classification

Capturing spatial interdependence in image features: the counting grid, an epitomic representation for bags of features

no code implementations23 Oct 2014 Alessandro Perina, Nebojsa Jojic

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.

Scene Recognition

Documents as multiple overlapping windows into grids of counts

no code implementations NeurIPS 2013 Alessandro Perina, Nebojsa Jojic, Manuele Bicego, Andrzej Truski

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.

Document Classification Retrieval +1

A Comparative Framework for Preconditioned Lasso Algorithms

no code implementations NeurIPS 2013 Fabian L. Wauthier, Nebojsa Jojic, Michael. I. Jordan

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

no code implementations CVPR 2013 Alessandro Perina, Nebojsa Jojic

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

no code implementations26 Apr 2013 Alessandro Perina, Nebojsa Jojic

We introduce and we analyze a new dataset which resembles the input to biological vision systems much more than most previously published ones.

Exact inference and learning for cumulative distribution functions on loopy graphs

no code implementations NeurIPS 2010 Nebojsa Jojic, Chris Meek, Jim C. Huang

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.


Structural epitome: a way to summarize one’s visual experience

no code implementations NeurIPS 2010 Nebojsa Jojic, Alessandro Perina, Vittorio Murino

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).


Free energy score space

no code implementations NeurIPS 2009 Alessandro Perina, Marco Cristani, Umberto Castellani, Vittorio Murino, Nebojsa Jojic

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.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.