BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Nan Ye

Nan Ye appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Machine Learningmath.DGArtificial IntelligenceComputer Visionecon.EMRobotics

Catalog footprint

What is connected

9works
6topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

9 published item(s)

preprint2026arXiv

DINO-MVR: Multi-View Readout of Frozen DINOv3 for Annotation-Efficient Medical Segmentation

Adapting foundation models to medical segmentation typically requires either backbone fine-tuning or high-capacity task-specific decoders, both of which are difficult to fit reliably when annotations are scarce. We show that frozen DINOv3 features already contain useful structural and boundary cues for medical segmentation, and that the main bottleneck lies in how these features are read out. We propose DINO-MVR, a Multi-View Readout framework for annotation-efficient medical segmentation. DINO-MVR trains only lightweight MLP probes on features from the final three transformer blocks of a frozen DINOv3 backbone, without updating the backbone itself. At inference, each input is interpreted through complementary resolutions and test-time augmentations, whose probability maps are combined by entropy-weighted fusion and refined with simple spatial regularization. For volumetric inputs, Gaussian z-axis smoothing further improves inter-slice consistency. Under fixed evaluation protocols on endoscopy, dermoscopy, and MRI benchmarks, DINO-MVR achieves strong readout-only performance, including 0.895 Dice on Kvasir-SEG, 0.897 Dice on ISIC 2018, and 0.908 Dice on BraTS FLAIR whole-tumor segmentation. With only five annotated BraTS patients, it recovers 98.4% of the performance obtained by the 40-patient BraTS reference run. These results suggest that frozen self-supervised vision backbones can support accurate medical segmentation when paired with an effective multi-view readout.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adaptive Discretization using Voronoi Trees for Continuous-Action POMDPs

Solving Partially Observable Markov Decision Processes (POMDPs) with continuous actions is challenging, particularly for high-dimensional action spaces. To alleviate this difficulty, we propose a new sampling-based online POMDP solver, called Adaptive Discretization using Voronoi Trees (ADVT). It uses Monte Carlo Tree Search in combination with an adaptive discretization of the action space as well as optimistic optimization to efficiently sample high-dimensional continuous action spaces and compute the best action to perform. Specifically, we adaptively discretize the action space for each sampled belief using a hierarchical partition which we call a Voronoi tree. A Voronoi tree is a Binary Space Partitioning (BSP) that implicitly maintains the partition of a cell as the Voronoi diagram of two points sampled from the cell. This partitioning strategy keeps the cost of partitioning and estimating the size of each cell low, even in high-dimensional spaces where many sampled points are required to cover the space well. ADVT uses the estimated sizes of the cells to form an upper-confidence bound of the action values of the cell, and in turn uses the upper-confidence bound to guide the Monte Carlo Tree Search expansion and further discretization of the action space. This strategy enables ADVT to better exploit local information in the action space, leading to an action space discretization that is more adaptive, and hence more efficient in computing good POMDP solutions, compared to existing solvers. Experiments on simulations of four types of benchmark problems indicate that ADVT outperforms and scales substantially better to high-dimensional continuous action spaces, compared to state-of-the-art continuous action POMDP solvers.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations

Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex visual observations. This paper presents Discriminative Particle Filter Reinforcement Learning (DPFRL), a new reinforcement learning framework for complex partial observations. DPFRL encodes a differentiable particle filter in the neural network policy for explicit reasoning with partial observations over time. The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making. We show that using the discriminative update instead of standard generative models results in significantly improved performance, especially for tasks with complex visual observations, because they circumvent the difficulty of modeling complex observations that are irrelevant to decision making. In addition, to extract features from the particle belief, we propose a new type of belief feature based on the moment generating function. DPFRL outperforms state-of-the-art POMDP RL models in Flickering Atari Games, an existing POMDP RL benchmark, and in Natural Flickering Atari Games, a new, more challenging POMDP RL benchmark introduced in this paper. Further, DPFRL performs well for visual navigation with real-world data in the Habitat environment.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Greedy Convex Ensemble

We consider learning a convex combination of basis models, and present some new theoretical and empirical results that demonstrate the effectiveness of a greedy approach. Theoretically, we first consider whether we can use linear, instead of convex, combinations, and obtain generalization results similar to existing ones for learning from a convex hull. We obtain a negative result that even the linear hull of very simple basis functions can have unbounded capacity, and is thus prone to overfitting; on the other hand, convex hulls are still rich but have bounded capacities. Secondly, we obtain a generalization bound for a general class of Lipschitz loss functions. Empirically, we first discuss how a convex combination can be greedily learned with early stopping, and how a convex combination can be non-greedily learned when the number of basis models is known a priori. Our experiments suggest that the greedy scheme is competitive with or better than several baselines, including boosting and random forests. The greedy algorithm requires little effort in hyper-parameter tuning, and also seems able to adapt to the underlying complexity of the problem. Our code is available at https://github.com/tan1889/gce.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Risk Fluctuation Characteristics of Internet Finance: Combining Industry Characteristics with Ecological Value

The Internet plays a key role in society and is vital to economic development. Due to the pressure of competition, most technology companies, including Internet finance companies, continue to explore new markets and new business. Funding subsidies and resource inputs have led to significant business income tendencies in financial statements. This tendency of business income is often manifested as part of the business loss or long-term unprofitability. We propose a risk change indicator (RFR) and compare the risk indicator of fourteen representative companies. This model combines extreme risk value with slope, and the combination method is simple and effective. The results of experiment show the potential of this model. The risk volatility of technology enterprises including Internet finance enterprises is highly cyclical, and the risk volatility of emerging Internet fintech companies is much higher than that of other technology companies.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Closed strong spacelike curves, Fenchel theorem and Plateau problem in the 3-dimensional Minkowski space

We generalize the Fenchel theorem for strong spacelike closed curves of index $1$ in the 3-dimensional Minkowski space, showing that the total curvature must be less than or equal to $2π$. Here strong spacelike means that the tangent vector and the curvature vector span a spacelike 2-plane at each point of the curve $γ$ under consideration. The assumption of index 1 is equivalent to saying that $γ$ winds around some timelike axis with winding number 1. We prove this reversed Fenchel-type inequality by constructing a ruled spacelike surface with the given curve as boundary and applying the Gauss-Bonnet formula. As a by-product, this shows the existence of a maximal surface with $γ$ as boundary.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Robustness of Bayesian Pool-based Active Learning Against Prior Misspecification

We study the robustness of active learning (AL) algorithms against prior misspecification: whether an algorithm achieves similar performance using a perturbed prior as compared to using the true prior. In both the average and worst cases of the maximum coverage setting, we prove that all $α$-approximate algorithms are robust (i.e., near $α$-approximate) if the utility is Lipschitz continuous in the prior. We further show that robustness may not be achieved if the utility is non-Lipschitz. This suggests we should use a Lipschitz utility for AL if robustness is required. For the minimum cost setting, we can also obtain a robustness result for approximate AL algorithms. Our results imply that many commonly used AL algorithms are robust against perturbed priors. We then propose the use of a mixture prior to alleviate the problem of prior misspecification. We analyze the robustness of the uniform mixture prior and show experimentally that it performs reasonably well in practice.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

The Fenchel-type inequality in the 3-dimensional Lorentz space and a Crofton formula

We generalize the Fenchel theorem to strong spacelike (which means that the tangent vector and the curvature vector span a spacelike 2-plane at each point) closed curves with index 1 in the 3-dimensional Lorentz space, showing that the total curvatures must be less than or equal to $2π$. A similar generalization of the Fary-Milnor theorem is also obtained. We establish the Crofton formula on the de Sitter 2-sphere which implies the above results.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A Poincaré-type inequality and a related eigenvalue problem

Given a smooth positive function $f$ defined on the unit circle satisfying a simple condition, we obtain a Poincaré-type inequality for an arbitrary function $u$ whose weighted average with respect to $f$ is zero. The proof uses Fenchel's theorem about the total curvature of closed space curves in an essential way. Next we consider the generalization of this result to higher dimensional closed Riemannian manifold and reduce it to an eigenvalue problem. Finally, we point out that even though such Poincaré-type inequality still holds, the best constant $λ_1(f)$ might be different from the first eigenvalue $λ_1$ by constructing explicit examples on the standard spheres and flat tori.

0 citations0 reviewsNo code linkedOpen access