1 citations · 3 across the 16 of their papers we have counts for
18 papers
ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA
Ping-Kun Chiang, Kun-Ru Wu, Po-han Li +3
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new possibilities for 3D question answering (3D-QA), a key capability for embodied AI…
VEGAS: Human-Aligned Video Caption Evaluation via Gaze
Shenghui Chen, Po-han Li, Ximeng Sun +5
Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose VEGAS (Video caption Evaluation…
What We are Missing in Multimodal LLM Evaluation?
Po-han Li, Shenghui Chen, Sandeep Chinchali +1
Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced ra…
SSR: A Generic Framework for Text-Aided Map Compression for Localization
Mohammad Omama, Po-han Li, Harsh Goel +6
Mapping is crucial in robotics for localization and downstream decision-making. As robots are deployed in ever-broader settings, the maps they rely on continue to increase in size.…
ViSIL: Unified Evaluation of Information Loss in Multimodal Video Captioning
Po-han Li, Shenghui Chen, Ufuk Topcu +1
Multimodal video captioning condenses dense footage into a structured format of keyframes and natural language. By creating a cohesive multimodal summary, this approach anchors gen…
UNCAP: Uncertainty-Guided Neurosymbolic Planning Using Natural Language Communication for Cooperative Autonomous Vehicles
Neel P. Bhatt, Po-han Li, Kushagra Gupta +7
Safe large-scale coordination of multiple cooperative connected autonomous vehicles (CAVs) hinges on communication that is both efficient and interpretable. Existing approaches eit…
Fair Resource Allocation for Fleet Intelligence
Oguzhan Baser, Kaan Kale, Po-han Li +1
Resource allocation is crucial for the performance optimization of cloud-assisted multi-agent intelligence. Traditional methods often overlook agents' diverse computational capabil…
VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
Shenghui Chen, Po-han Li, Sandeep Chinchali +1
Many decision-making tasks, where both accuracy and efficiency matter, still require human supervision. For example, tasks like traffic officers reviewing hour-long dashcam footage…
Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
Cevahir Koprulu, Po-han Li, Tianyu Qiu +5
Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to…
Any2Any: Incomplete Multimodal Retrieval with Conformal Prediction
Po-han Li, Yunhao Yang, Mohammad Omama +2
Autonomous agents perceive and interpret their surroundings by integrating multimodal inputs, such as vision, audio, and LiDAR. These perceptual modalities support retrieval tasks,…
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features
Po-han Li, Sandeep P. Chinchali, Ufuk Topcu
Multimodal encoders like CLIP excel in tasks such as zero-shot image classification and cross-modal retrieval. However, they require excessive training data. We propose canonical s…
Exploiting Distribution Constraints for Scalable and Efficient Image Retrieval
Mohammad Omama, Po-han Li, Sandeep P. Chinchali
Image retrieval is crucial in robotics and computer vision, with downstream applications in robot place recognition and vision-based product recommendations. Modern retrieval syste…
PEERNet: An End-to-End Profiling Tool for Real-Time Networked Robotic Systems
Aditya Narayanan, Pranav Kasibhatla, Minkyu Choi +3
Networked robotic systems balance compute, power, and latency constraints in applications such as self-driving vehicles, drone swarms, and teleoperated surgery. A core problem in t…
Online Foundation Model Selection in Robotics
Po-han Li, Oyku Selin Toprak, Aditya Narayanan +2
Foundation models have recently expanded into robotics after excelling in computer vision and natural language processing. The models are accessible in two ways: open-source or pai…
Task-aware Distributed Source Coding under Dynamic Bandwidth
Po-han Li, Sravan Kumar Ankireddy, Ruihan Zhao +5
Efficient compression of correlated data is essential to minimize communication overload in multi-sensor networks. In such networks, each sensor independently compresses the data a…
Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collection
Oguzhan Akcin, Po-han Li, Shubhankar Agarwal +1
Fleets of networked autonomous vehicles (AVs) collect terabytes of sensory data, which is often transmitted to central servers (the ''cloud'') for training machine learning (ML) mo…
Differentially Private Timeseries Forecasts for Networked Control
Po-han Li, Sandeep P. Chinchali, Ufuk Topcu
We analyze a cost-minimization problem in which the controller relies on an imperfect timeseries forecast. Forecasting models generate imperfect forecasts because they use anonymiz…
Adversarial Examples for Model-Based Control: A Sensitivity Analysis
Po-han Li, Ufuk Topcu, Sandeep P. Chinchali
We propose a method to attack controllers that rely on external timeseries forecasts as task parameters. An adversary can manipulate the costs, states, and actions of the controlle…