6 papers
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
Kimia Kazemian, Zhenzhen Liu, Yangfanyu Yang +9
Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years…
On the Feasibility and Opportunity of Autoregressive 3D Object Detection
Zanming Huang, Jinsu Yoo, Sooyoung Jeon +6
LiDAR-based 3D object detectors typically rely on proposal heads with hand-crafted components like anchor assignment and non-maximum suppression (NMS), complicating training and li…
Learning from Synthetic Data Improves Multi-hop Reasoning
Anmol Kabra, Yilun Yin, Albert Gong +6
Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL…
DiffuBox: Refining 3D Object Detection with Point Diffusion
Xiangyu Chen, Zhenzhen Liu, Katie Z Luo +10
Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining h…
Denoising Vision Transformers
Jiawei Yang, Katie Z Luo, Jiefeng Li +6
We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs i…
Orchestrating LLMs with Different Personalizations
Jin Peng Zhou, Katie Z Luo, Jingwen Gu +3
This paper presents a novel approach to aligning large language models (LLMs) with individual human preferences, sometimes referred to as Reinforcement Learning from \textit{Person…