91 citations · 173 across the 9 of their papers we have counts for
10 papers
Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
David Acuna, Chao-Han Huck Yang, Yuntian Deng +6
Despite rapid progress, multimodal reasoning still lacks a systematic approach to synthesize large-scale vision-centric datasets beyond visual math. We introduce a framework able t…
LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception
Yuan-Hong Liao, Sven Elflein, Liu He +4
Recent reasoning models through test-time scaling have demonstrated that long chain-of-thoughts can unlock substantial performance boosts in hard reasoning tasks such as math and c…
Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler +1
Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitativel…
Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?
Yuan-Hong Liao, Rafid Mahmood, Sanja Fidler +1
Enhancing semantic grounding abilities in Vision-Language Models (VLMs) often involves collecting domain-specific training data, refining the network architectures, or modifying th…
Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
Yuan-Hong Liao, Amlan Kar, Sanja Fidler
Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge…
Emergent Road Rules In Multi-Agent Driving Environments
Avik Pal, Jonah Philion, Yuan-Hong Liao +1
For autonomous vehicles to safely share the road with human drivers, autonomous vehicles must abide by specific "road rules" that human drivers have agreed to follow. "Road rules"…
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
Xavier Puig, Tianmin Shu, Shuang Li +5
In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex hous…
Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
Tseng-Hung Chen, Yuan-Hong Liao, Ching-Yao Chuang +3
Impressive image captioning results are achieved in domains with plenty of training image and sentence pairs (e.g., MSCOCO). However, transferring to a target domain with significa…
Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
Yen-Chen Lin, Zhang-Wei Hong, Yuan-Hong Liao +3
We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting att…
Leveraging Video Descriptions to Learn Video Question Answering
Kuo-Hao Zeng, Tseng-Hung Chen, Ching-Yao Chuang +3
We propose a scalable approach to learn video-based question answering (QA): answer a "free-form natural language question" about a video content. Our approach automatically harves…