Author name cluster

Jian Yao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Diversity-Aware Policy Optimization for Large Language Model Reasoning

Jian Yao
Ran Cheng
Xingyu Wu
Jibin Wu
KC Tan

The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek-R1, which has inspired a surge of research into data quality and reinforcement learning (RL) algorithms. Despite the pivotal role diversity plays in RL, its influence on LLM reasoning remains largely underexplored. To bridge this gap, this work presents a systematic investigation into the impact of diversity in RL-based training for LLM reasoning, and proposes a novel diversity-aware policy optimization method. Across evaluations on 12 LLMs, we observe a strong positive correlation between the solution diversity and potential@k (a novel metric quantifying an LLM’s reasoning potential) in high-performing models. This finding motivates our method to explicitly promote diversity during RL training. Specifically, we design a token-level diversity and reformulate it into a practical objective, then we selectively apply it to positive samples. Integrated into the R1-zero training framework, our method achieves a 3. 5\% average improvement across four mathematical reasoning benchmarks, while generating more diverse and robust solutions.

PDF Details

IROS Conference 2024 Conference Paper

Active Pose Refinement for Textureless Shiny Objects using the Structured Light Camera

Jun Yang 0053
Jian Yao
Steven L. Waslander

6D pose estimation of textureless shiny objects has become an essential problem in many robotic applications. Many pose estimators require high-quality depth data, often measured by structured light cameras. However, when objects have shiny surfaces (e. g. , metal parts), these cameras fail to sense complete depths from a single viewpoint due to the specular reflection, resulting in a significant drop in the final pose accuracy. To mitigate this issue, we present a complete active vision framework for 6D object pose refinement and next-best-view prediction. Specifically, we first develop an optimization-based pose refinement module for the structured light camera. Our system then selects the next best camera viewpoint to collect depth measurements by minimizing the predicted uncertainty of the object pose. Compared to previous approaches, we additionally predict measurement uncertainties of future viewpoints by online rendering, which significantly improves the next-best-view prediction performance. We test our method on the real-world ROBI dataset. The results show that our pose refinement module outperforms the traditional ICP-based approach when given the same input depth data, and our next-best-view strategy can achieve high object pose accuracy with significantly fewer viewpoints than the heuristic-based policies.

Details

NeurIPS Conference 2023 Conference Paper

Policy Space Diversity for Non-Transitive Games

Jian Yao
Weiming Liu
Haobo Fu
Yaodong Yang
Stephen McAleer
Qiang Fu
Wei Yang

Policy-Space Response Oracles (PSRO) is an influential algorithm framework for approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous studies have been trying to promote policy diversity in PSRO. A major weakness with existing diversity metrics is that a more diverse (according to their diversity metrics) population does not necessarily mean (as we proved in the paper) a better approximation to a NE. To alleviate this problem, we propose a new diversity metric, the improvement of which guarantees a better approximation to a NE. Meanwhile, we develop a practical and well-justified method to optimize our diversity metric using only state-action samples. By incorporating our diversity regularization into the best response solving of PSRO, we obtain a new PSRO variant, \textit{Policy Space Diversity} PSRO (PSD-PSRO). We present the convergence property of PSD-PSRO. Empirically, extensive experiments on single-state games, Leduc, and Goofspiel demonstrate that PSD-PSRO is more effective in producing significantly less exploitable policies than state-of-the-art PSRO variants.

PDF Details

AAAI Conference 2022 Conference Paper

JPV-Net: Joint Point-Voxel Representations for Accurate 3D Object Detection

Nan Song
Tianyuan Jiang
Jian Yao

Voxel and point representations are widely applied in recent 3D object detection tasks from LiDAR point clouds. Voxel representations contribute to efficiently and rapidly locating objects, whereas point representations are capable of describing intra-object spatial relationship for detection refinement. In this work, we aim to exploit the strengths of both two representations, and present a novel two-stage detector, named Joint Point-Voxel Network (JPV-Net). Specifically, our framework is equipped with a Dual Encoders-Fusion Decoder, which consists of the dual encoders to extract voxel features of sketchy 3D scenes and point features rich in geometric context, respectively, and the Feature Propagation Fusion (FP-Fusion) decoder to attentively fuse them from coarse to fine. By making use of the advantages of these features, the refinement network can effectively eliminate false detection and achieve better accuracy. Besides, to further develop the perception characteristics of voxel CNN and point backbone, we design two novel intersection-over-union (IoU) estimation modules for proposal generation and refinement, both of which can alleviate the misalignment between the localization and the classification confidence. Extensive experiments on the KITTI dataset and the ONCE dataset demonstrate that our proposed JPV-Net outperforms other state-ofthe-art methods with remarkable margins.

PDF Details

NeurIPS Conference 2022 Conference Paper

Self-supervised Amodal Video Object Segmentation

Jian Yao
Yuxin Hong
Chiyu Wang
Tianjun Xiao
Tong He
Francesco Locatello
David P Wipf
Yanwei Fu

Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of Self-supervised amodal Video object segmentation (SaVos). Our method efficiently leverages the visual information of video temporal sequences to infer the amodal mask of objects. The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned. Accordingly, we derive a novel self-supervised learning paradigm that efficiently utilizes the visible object parts as the supervision to guide the training on videos. In addition to learning type prior to complete masks for known types, SaVos also learns the spatiotemporal prior, which is also useful for the amodal task and could generalize to unseen types. The proposed framework achieves the state-of-the-art performance on the synthetic amodal segmentation benchmark FISHBOWL and the real world benchmark KINS-Video-Car. Further, it lends itself well to being transferred to novel distributions using test-time adaptation, outperforming existing models even after the transfer to a new distribution.

PDF Details

NeurIPS Conference 2021 Conference Paper

GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction

Longyuan Li
Jian Yao
Li Wenliang
Tong He
Tianjun Xiao
Junchi Yan
David Wipf
Zheng Zhang

Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems. This is challenging because humans make decisions based on complex social relations and personal intents, resulting in highly complex uncertainties over trajectories. To address this problem, we propose a conditional deep generative model that combines advances in graph neural networks. The prior and recognition model encodes two types of latent codes for each agent: an inter-agent latent code to represent social relations and an intra-agent latent code to represent agent intentions. The decoder is carefully devised to leverage the codes in a disentangled way to predict multi-modal future trajectory distribution. Specifically, a graph attention network built upon inter-agent latent code is used to learn continuous pair-wise relations, and an agent's motion is controlled by its latent intents and its observations of all other agents. Through experiments on both synthetic and real-world datasets, we show that our model outperforms previous work in multiple performance metrics. We also show that our model generates realistic multi-modal trajectories.

PDF Details

YNICL Journal 2020 Journal Article

Protein-based amide proton transfer-weighted MR imaging of amnestic mild cognitive impairment

Zewen Zhang
Caiqing Zhang
Jian Yao
Xin Chen
Fei Gao
Shanshan Jiang
Weibo Chen
Jinyuan Zhou

Amide proton transfer-weighted (APTw) MRI is a novel molecular imaging technique that can noninvasively detect endogenous cellular proteins and peptides in tissue. Here, we demonstrate the feasibility of protein-based APTw MRI in characterizing amnestic mild cognitive impairment (aMCI). Eighteen patients with confirmed aMCI and 18 matched normal controls were scanned at 3 Tesla. The APTw, as well as conventional magnetization transfer ratio (MTR), signal differences between aMCI and normal groups were assessed by the independent samples t-test, and the receiver-operator-characteristic analysis was used to assess the diagnostic performance of APTw. When comparing the normal control group, aMCI brains typically had relatively higher APTw signals. Quantitatively, APTw intensity values were significantly higher in nine of 12 regions of interest in aMCI patients than in normal controls. The largest areas under the receiver-operator-characteristic curves were 0.88 (gray matter in occipital lobe) and 0.82 (gray matter in temporal lobe, white matter in occipital lobe) in diagnosing aMCI patients. On the contrary, MTR intensity values were significantly higher in only three of 12 regions of interest in the aMCI group. Additionally, the age dependency analyses revealed that these cross-sectional APTw/MTR signals had an increasing trend with age in most brain regions for normal controls, but a decreasing trend with age in most brain regions for aMCI patients. Our early results show the potential of the APTw signal as a new imaging biomarker for the noninvasive molecular diagnosis of aMCI.

Details DOI