1 citations · 1 across the 9 of their papers we have counts for
10 papers
SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions
Fucai Ke, Sukai Huang, Junyi Hao +4
Robotic perception must remain reliable when extreme environmental conditions severely degrade the primary RGB observation. Although robotic platforms commonly carry complementary…
What We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variatio…
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction…
MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
Zhixi Cai, Fucai Ke, Kevin Leo +4
Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional m…
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Fucai Ke, Joy Hsu, Zhixi Cai +10
Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground inte…
ALIGN: Word Association Learning for Cultural Alignment in Large Language Models
Chunhua Liu, Kabir Manandhar Shrestha, Sukai Huang
Large language models (LLMs) exhibit cultural bias from overrepresented viewpoints in training data, yet cultural alignment remains a challenge due to limited cultural knowledge an…
Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
Sukai Huang, Trevor Cohn, Nir Lipovetzky
The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tas…
Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts
Sukai Huang, Nir Lipovetzky, Trevor Cohn
Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination.…
The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards
Sukai Huang, Shu-Wei Liu, Nir Lipovetzky +1
While Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by…
A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents
Sukai Huang, Nir Lipovetzky, Trevor Cohn
Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Wit…