22 citations · 42 across the 13 of their papers we have counts for
14 papers
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
Kostas Triaridis, Morris E. Sharp, Nebojsa Jojic
Modern generative models produce high-quality individual outputs but struggle to sample diversely, even when explicitly instructed to do so. We introduce MINE-SAMPLE-RENDER (MSR),…
Rushes: A Human Preference Dataset for Pluralistic Alignment
Michael Xu, Jorge Leandro, Sudha Rao +5
We introduce Rushes, a dataset and benchmark for studying revealed human engagement preferences in interactive narrative environments. Rushes is collected through a game interface…
GenZ: Foundational models as latent variable generators within traditional statistical models
Marko Jojic, Nebojsa Jojic
We present GenZ, a hybrid model that bridges foundational models and statistical modeling through interpretable semantic features. While large language models possess broad domain…
Can MLLMs Find Their Way in a City? Exploring Emergent Navigation from Web-Scale Knowledge
Dwip Dalal, Utkarsh Mishra, Narendra Ahuja +1
Leveraging multimodal large language models (MLLMs) to develop embodied agents offers significant promise for addressing complex real-world tasks. However, current evaluation bench…
Learning Informative Attention Weights for Person Re-Identification
Yancheng Wang, Nebojsa Jojic, Yingzhen Yang
Attention mechanisms have been widely used in deep learning, and recent efforts have been devoted to incorporating attention modules into deep neural networks (DNNs) for person Re-…
Make Some Noise: Towards LLM audio reasoning and generation using sound tokens
Shivam Mehta, Nebojsa Jojic, Hannes Gamper
Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. He…
Echoes in AI: Quantifying lack of plot diversity in LLM outputs
Weijia Xu, Nebojsa Jojic, Sudha Rao +2
With rapid advances in large language models (LLMs), there has been an increasing application of LLMs in creative content ideation and generation. A critical question emerges: can…
Game Plot Design with an LLM-powered Assistant: An Empirical Study with Game Designers
Seyed Hossein Alavi, Weijia Xu, Nebojsa Jojic +6
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 co…
fLSA: Learning Semantic Structures in Document Collections Using Foundation Models
Weijia Xu, Nebojsa Jojic, Nicolas Le Roux
Humans can learn to solve new tasks by inducing high-level strategies from example solutions to similar problems and then adapting these strategies to solve unseen problems. Can we…
Player-Driven Emergence in LLM-Driven Game Narrative
Xiangyu Peng, Jessica Quaye, Sudha Rao +10
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. Our testbed…
GENEVA: GENErating and Visualizing branching narratives using LLMs
Jorge Leandro, Sudha Rao, Michael Xu +4
Dialogue-based Role Playing Games (RPGs) require powerful storytelling. The narratives of these may take years to write and typically involve a large creative team. In this work, w…
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Xinyuan Wang, Chenxi Li, Zhen Wang +6
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 instinc…
Evaluating Cognitive Maps and Planning in Large Language Models with CogEval
Ida Momennejad, Hosein Hasanbeig, Felipe Vieira +5
Recently an influx of studies claim emergent cognitive abilities in large language models (LLMs). Yet, most rely on anecdotes, overlook contamination of training sets, or lack syst…
Iterative Refinement of the Approximate Posterior for Directed Belief Networks
R Devon Hjelm, Kyunghyun Cho, Junyoung Chung +3
Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods. Recent a…