9 papers
The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption
Timothy Duggan, Pierrick Lorang, Hong Lu +1
Vision-Language-Action (VLA) models have recently been proposed as a pathway toward generalist robotic policies capable of interpreting natural language and visual inputs to genera…
Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
Chao Yu, Qixin Tan, Jiaxuan Gao +7
Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time…
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning
Senjie Jin, Lu Chen, Zhiheng Xi +9
Natural language chain-of-thought (N-CoT) and Program chain-of-thought (P-CoT) have emerged as two primary paradigms for large language models (LLMs) to solve mathematical reasonin…
Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control
Zhe Wu, Hongjin Lu, Junliang Xing +10
Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches rely on dire…
RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow
Liang Yao, Fan Liu, Hongbo Lu +5
Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships bey…
QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hongzhou Lin, Hong Lu +5
Reinforcement learning (RL) has emerged as a central paradigm for training large language models (LLMs) in reasoning tasks. Yet recent studies question RL's ability to incentivize…
ClipGrader: Leveraging Vision-Language Models for Robust Label Quality Assessment in Object Detection
Hong Lu, Yali Bian, Rahul C. Shah
High-quality annotations are essential for object detection models, but ensuring label accuracy - especially for bounding boxes - remains both challenging and costly. This paper in…
ICPL: Few-shot In-context Preference Learning via LLMs
Chao Yu, Qixin Tan, Hong Lu +5
Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tab…
General Compression Framework for Efficient Transformer Object Tracking
Lingyi Hong, Jinglun Li, Xinyu Zhou +10
Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. Howe…