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

Chang Chen

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

ResearcherUnclaimed source record
Computer Visioneess.IVMachine LearningArtificial Intelligenceastro-ph.COBiological Physicscond-mat.otherDistributed, Parallel, and Cluster Computinghep-phmath.DSmath.PRnucl-thPerformance

Catalog footprint

What is connected

10works
13topics
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

10 published item(s)

preprint2026arXiv

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration

LLM-based evolution has emerged as a promising way to improve agents by refining non-parametric artifacts, but its wall-clock cost remains a major bottleneck. We identify that this cost comes from synchronized stage execution and imbalance inside each LLM-heavy stage. We present FlashEvolve, an efficient framework that replaces synchronized execution with asynchronous workers and queues, allowing different stages and steps to overlap. To handle data staleness introduced by asynchrony, FlashEvolve tracks artifact versions and applies different policies to update, discard, or patch stale artifacts. Unlike weight-space staleness in asynchronous RL, language-space staleness is inspectable and repairable: a stale artifact is not just delayed work, but readable evidence that the LLM can reflect on, revise, and turn into useful evolution signal. FlashEvolve further improves throughput and token efficiency with speculative stage completion and adaptive workflow control. On GEPA workloads, FlashEvolve improves proposal throughput by $3.5\times$ on local vLLM and $4.9\times$ on API serving over synchronous GEPA. The same design also applies to ACE and Meta-Harness.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

Simple Hierarchical Planning with Diffusion

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long-horizon tasks. To overcome this, we introduce the Hierarchical Diffuser, a simple, fast, yet surprisingly effective planning method combining the advantages of hierarchical and diffusion-based planning. Our model adopts a "jumpy" planning strategy at the higher level, which allows it to have a larger receptive field but at a lower computational cost -- a crucial factor for diffusion-based planning methods, as we have empirically verified. Additionally, the jumpy sub-goals guide our low-level planner, facilitating a fine-tuning stage and further improving our approach's effectiveness. We conducted empirical evaluations on standard offline reinforcement learning benchmarks, demonstrating our method's superior performance and efficiency in terms of training and planning speed compared to the non-hierarchical Diffuser as well as other hierarchical planning methods. Moreover, we explore our model's generalization capability, particularly on how our method improves generalization capabilities on compositional out-of-distribution tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Advanced Deep Networks for 3D Mitochondria Instance Segmentation

Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods. In this paper, we propose two advanced deep networks, named Res-UNet-R and Res-UNet-H, for 3D mitochondria instance segmentation from Rat and Human samples. Specifically, we design a simple yet effective anisotropic convolution block and deploy a multi-scale training strategy, which together boost the segmentation performance. Moreover, we enhance the generalizability of the trained models on the test set by adding a denoising operation as pre-processing. In the Large-scale 3D Mitochondria Instance Segmentation Challenge at ISBI 2021, our method ranks the 1st place. Code is available at https://github.com/Limingxing00/MitoEM2021-Challenge.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation

Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands. However, this modeling strategy ignores the continuous nature of spectral signature. In this paper, we propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation. To this end, we embrace the concept of implicit function and implement a parameterized embodiment with a neural network. Specifically, we first adopt a backbone network to extract spatial features of RGB inputs. Based on it, we devise Spectral Profile Interpolation (SPI) module and Neural Attention Mapping (NAM) module to enrich deep features, where the spatial-spectral correlation is involved for a better representation. Then, we view the number of sampled spectral bands as the coordinate of continuous implicit function, so as to learn the projection from deep features to spectral intensities. Extensive experiments demonstrate the distinct advantage of NeSR in reconstruction accuracy over baseline methods. Moreover, NeSR extends the flexibility of spectral reconstruction by enabling an arbitrary number of spectral bands as the target output.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On Lowest Lying $\frac{1}{2}^-$ Octet Baryons

The recently proposed $N^*(890)$ $1/2^-$ baryon is studied in a flavor $SU(3)$ scheme with $K$ matrix unitarization, by fitting to low energy cross section and phase shift data. It is found that $N^*(890)$ co-exists with low lying poles in other channels, which have been extensively discussed in the literature, though they belong to different octets, in the $SU(3)$ limit. Hence the existence of $N^*(890)$ is further verified.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Retinal Vessel Segmentation with Pixel-wise Adaptive Filters

Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast. Previous methods generally refine segmentation results by cascading multiple deep networks, which are time-consuming and inefficient. In this paper, we propose two novel methods to address these challenges. First, we devise a light-weight module, named multi-scale residual similarity gathering (MRSG), to generate pixel-wise adaptive filters (PA-Filters). Different from cascading multiple deep networks, only one PA-Filter layer can improve the segmentation results. Second, we introduce a response cue erasing (RCE) strategy to enhance the segmentation accuracy. Experimental results on the DRIVE, CHASE_DB1, and STARE datasets demonstrate that our proposed method outperforms state-of-the-art methods while maintaining a compact structure. Code is available at https://github.com/Limingxing00/Retinal-Vessel-Segmentation-ISBI20222.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Removing Interlopers From Intensity Mapping Probes Of Primordial Non-Gaussianity

Line intensity mapping (LIM) has the potential to produce highly precise measurements of scale-dependence bias from primordial non-Gaussianity (PNG) due to its ability to map much larger volumes than are available from galaxy surveys. PNG parameterized by $f_{NL}$ leads to a scale-dependent correction to the bias, and therefore a correction to the line intensity power spectrum. However, LIM experiences contamination from foreground emission, including interloping emission lines from other redshifts which alter the power spectra of the maps at these scales, potentially biasing measurements of $f_{NL}$. Here we model the effect of line interlopers on upcoming line intensity mapping probes of primordial non-Gaussianity (PNG) from inflation. As an example, we consider the $[\rm CII]$ line at target redshift $z_t = 3.6$ to probe PNG, with the important systematic concern being foreground contamination from CO lines residing at redshifts different from the target redshift. We find interloper lines can lead to a significant bias and an increase in errors for our PNG constraints, leading to a false positive for non-standard inflation models. We model how well the cross-correlation technique could reduce this interloper contamination. We find the uncertainty of $f_{NL}$ reduces by factors of two and six for local and orthogonal shape PNG respectively, and by a factor of five for local shape if we consider seven interloper lines, almost eliminating the effect of interlopers. This work shows that using cross-power and auto-power spectra of line intensity maps jointly could potentially remove the effects of interlopers when measuring non-Gaussianity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Camera Trace Erasing

Camera trace is a unique noise produced in digital imaging process. Most existing forensic methods analyze camera trace to identify image origins. In this paper, we address a new low-level vision problem, camera trace erasing, to reveal the weakness of trace-based forensic methods. A comprehensive investigation on existing anti-forensic methods reveals that it is non-trivial to effectively erase camera trace while avoiding the destruction of content signal. To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siamese architecture for network training. Specifically, we propose embedded similarity, truncated fidelity, and cross identity to form the hybrid loss. Compared with existing anti-forensic methods, SiamTE has a clear advantage for camera trace erasing, which is demonstrated in three representative tasks. Code and dataset are available at https://github.com/ngchc/CameraTE.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Queueing Analysis of a Large-Scale Bike Sharing System through Mean-Field Theory

The bike sharing systems are fast increasing as a public transport mode in urban short trips, and have been developed in many major cities around the world. A major challenge in the study of bike sharing systems is that large-scale and complex queueing networks have to be applied through multi-dimensional Markov processes, while their discussion always suffers a common difficulty: State space explosion. For this reason, this paper provides a mean-field computational method to study such a large-scale bike sharing steps: Firstly, a multi-dimensional Markov process is set up for expressing the states of the bike sharing system, and the empirical process of the multi-dimensional Markov process is given to partly overcome the difficulty of state space explosion. Based on this, the mean-field equations are derived by means of a virtual time-inhomogeneous M(t)/M(t)/1/K queue whose arrival and service rates are determined by the mean-field computation. Secondly, the martingale limit is employed to investigate the limiting behavior of the empirical process, the fixed point is proved to be unique so that it can be computed by means of a nonlinear birth-death process, the asymptotic independence of this system is discussed simply, and specifically, these lead to numerical computation of the steady-state probability of the problematic (empty or full) stations. Finally, some numerical examples are given for valuable observation on how the steady-state probability of the problematic stations depends on some crucial parameters of the bike sharing system.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Local solid-state modification of nanopore surface charges

The last decade, nanopores have emerged as a new and interesting tool for the study of biological macromolecules like proteins and DNA. While biological pores, especially alpha-hemolysin, have been promising for the detection of DNA, their poor chemical stability limits their use. For this reason, researchers are trying to mimic their behaviour using more stable, solid-state nanopores. The most successful tools to fabricate such nanopores use high energy electron or ions beams to drill or reshape holes in very thin membranes. While the resolution of these methods can be very good, they require tools that are not commonly available and tend to damage and charge the nanopore surface. In this work, we show nanopores that have been fabricated using standard micromachning techniques together with EBID, and present a simple model that is used to estimate the surface charge. The results show that EBID with a silicon oxide precursor can be used to tune the nanopore surface and that the surface charge is stable over a wide range of concentrations.

0 citations0 reviewsNo code linkedOpen access