38 citations · 71 across the 13 of their papers we have counts for
14 papers
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue +7
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rew…
Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey
Matthieu Lin, Jenny Sheng, Andrew Zhao +7
This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded L…
DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints
Andrew Zhao, Quentin Xu, Matthieu Lin +4
Recent advances in large language model assistants have made them indispensable, raising significant concerns over managing their safety. Automated red teaming offers a promising a…
Exploring Text-to-Motion Generation with Human Preference
Jenny Sheng, Matthieu Lin, Andrew Zhao +5
This paper presents an exploration of preference learning in text-to-motion generation. We find that current improvements in text-to-motion generation still rely on datasets requir…
Augmenting Unsupervised Reinforcement Learning with Self-Reference
Andrew Zhao, Erle Zhu, Rui Lu +3
Humans possess the ability to draw on past experiences explicitly when learning new tasks and applying them accordingly. We believe this capacity for self-referencing is especially…
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Shenzhi Wang, Qisen Yang, Jiawei Gao +6
Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the i…
TBench: Benchmarking Current Progress in Text-to-3D Generation
Yuze He, Yushi Bai, Matthieu Lin +6
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3…
DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models
Zhiyao Sun, Tian Lv, Sheng Ye +5
The generation of stylistic 3D facial animations driven by speech presents a significant challenge as it requires learning a many-to-many mapping between speech, style, and the cor…
Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement
Sheng Ye, Yubin Hu, Matthieu Lin +4
The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. R…
ExpeL: LLM Agents Are Experiential Learners
Andrew Zhao, Daniel Huang, Quentin Xu +3
The recent surge in research interest in applying large language models (LLMs) to decision-making tasks has flourished by leveraging the extensive world knowledge embedded in LLMs.…
O-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
Yubin Hu, Sheng Ye, Wang Zhao +5
Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propo…
Boosting Offline Reinforcement Learning with Action Preference Query
Qisen Yang, Shenzhi Wang, Matthieu Gaetan Lin +2
Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tunin…
A Mixture of Surprises for Unsupervised Reinforcement Learning
Andrew Zhao, Matthieu Gaetan Lin, Yangguang Li +2
Unsupervised reinforcement learning aims at learning a generalist policy in a reward-free manner for fast adaptation to downstream tasks. Most of the existing methods propose to pr…
DETR for Crowd Pedestrian Detection
Matthieu Lin, Chuming Li, Xingyuan Bu +5
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…