10 citations · 38 across the 13 of their papers we have counts for
14 papers
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
Zichao Li, Gang Wu, Zichao Wang +5
Large language model agents operate in partially observable, long-horizon settings where obtaining supervision remains a major bottleneck. We address this by utilizing a source of…
Anticipatory Planning for Multimodal AI Agents
Yongyuan Liang, Shijie Zhou, Yu Gu +6
Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reaso…
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Mohamed Elmoghany, Liangbing Zhao, Xiaoqian Shen +27
Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model th…
Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse
Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel +4
Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficientl…
GUI Agents: A Survey
Dang Nguyen, Jian Chen, Yu Wang +27
Graphical User Interface (GUI) agents, powered by Large Foundation Models, have emerged as a transformative approach to automating human-computer interaction. These agents autonomo…
VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Yizhou Wang, Ruiyi Zhang, Haoliang Wang +3
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, th…
Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
Zhengmian Hu, Gang Wu, Saayan Mitra +4
In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attac…
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Sicheng Zhu, Ruiyi Zhang, Bang An +6
Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against…
Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention
Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli +2
We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched. Our m…
Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes
Aravind Reddy, Ryan A. Rossi, Zhao Song +6
In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbi…
HighlightMe: Detecting Highlights from Human-Centric Videos
Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli +2
We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. Our method works on the graph-based representation of multipl…
Structured Policy Iteration for Linear Quadratic Regulator
Youngsuk Park, Ryan A. Rossi, Zheng Wen +2
Linear quadratic regulator (LQR) is one of the most popular frameworks to tackle continuous Markov decision process tasks. With its fundamental theory and tractable optimal policy,…
Scalable Bid Landscape Forecasting in Real-time Bidding
Aritra Ghosh, Saayan Mitra, Somdeb Sarkhel +3
In programmatic advertising, ad slots are usually sold using second-price (SP) auctions in real-time. The highest bidding advertiser wins but pays only the second-highest bid (know…
Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs
Ryan A. Rossi, Anup Rao, Sungchul Kim +3
In this paper, we introduce the notion of motif closure and describe higher-order ranking and link prediction methods based on the notion of closing higher-order network motifs. Th…