BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yucheng Wang

Yucheng Wang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputation and Languagecond-mat.dis-nnMachine LearningComputer Visioncond-mat.str-elDiscrete MathematicsGraphicsInformation Theorymath.CTmath.ITquant-phRoboticsSocial and Information Networks

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
13works
0followers
14topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

13 published item(s)

preprint2026arXiv

A Unified Shape-Aware Foundation Model for Time Series Classification

Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting teammates induce non-stationarity, and rewards are often sparse and high-variance. Therefore, we introduce \textbf{Multi-Agent Test-Time Reinforcement Learning (MATTRL)}, a framework that injects structured textual experience into multi-agent deliberation at inference time. MATTRL forms a multi-expert team of specialists for multi-turn discussions, retrieves and integrates test-time experiences, and reaches consensus for final decision-making. We also study credit assignment for constructing a turn-level experience pool, then reinjecting it into the dialogue. Across challenging benchmarks in medicine, math, and education, MATTRL improves accuracy by an average of 3.67\% over a multi-agent baseline, and by 8.67\% over comparable single-agent baselines. Ablation studies examine different credit-assignment schemes and provide a detailed comparison of how they affect training outcomes. MATTRL offers a stable, effective and efficient path to distribution-shift-robust multi-agent reasoning without tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Controllable Video Generation: A Survey

With the rapid development of AI-generated content (AIGC), video generation has emerged as one of its most dynamic and impactful subfields. In particular, the advancement of video generation foundation models has led to growing demand for controllable video generation methods that can more accurately reflect user intent. Most existing foundation models are designed for text-to-video generation, where text prompts alone are often insufficient to express complex, multi-modal, and fine-grained user requirements. This limitation makes it challenging for users to generate videos with precise control using current models. To address this issue, recent research has explored the integration of additional non-textual conditions, such as camera motion, depth maps, and human pose, to extend pretrained video generation models and enable more controllable video synthesis. These approaches aim to enhance the flexibility and practical applicability of AIGC-driven video generation systems. In this survey, we provide a systematic review of controllable video generation, covering both theoretical foundations and recent advances in the field. We begin by introducing the key concepts and commonly used open-source video generation models. We then focus on control mechanisms in video diffusion models, analyzing how different types of conditions can be incorporated into the denoising process to guide generation. Finally, we categorize existing methods based on the types of control signals they leverage, including single-condition generation, multi-condition generation, and universal controllable generation. For a complete list of the literature on controllable video generation reviewed, please visit our curated repository at https://github.com/mayuelala/Awesome-Controllable-Video-Generation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

HoloMotion-1 Technical Report

In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1 is to scale control-policy training with a large-scale hybrid motion corpus, where video-reconstructed motions from in-the-wild videos provide the dominant source of motion diversity, while curated motion-capture and in-house motion data provide higher-fidelity supervision and deployment-oriented coverage. This data regime enables HoloMotion-1 to move beyond conventional MoCap-only training and exposes the policy to substantially broader behaviors, capture conditions, and motion styles. Learning from such heterogeneous data introduces new challenges, including reconstruction noise, source-domain mismatch, uneven motion quality, and the need for temporal modeling under large behavioral variation. To address these challenges, HoloMotion-1 integrates large-capacity temporal modeling, a sparsely activated Mixture-of-Experts Transformer with KV-cache inference for real-time control, and a sequence-level training strategy that improves learning efficiency on extended motion sequences. Extensive experiments on multiple unseen motion benchmarks show that HoloMotion-1 generalizes robustly across diverse motion types and capture conditions, significantly improves tracking accuracy over prior methods, and transfers directly to a real humanoid robot without task-specific fine-tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small set of dominant reasoning patterns, improving pass@1 while limiting rollout-level diversity and gains in pass@k. We argue that this failure stems from regularizing local token behavior rather than diversity over sets of solutions. To address this, we propose Uniqueness-Aware Reinforcement Learning, a rollout-level objective that explicitly rewards correct solutions that exhibit rare high-level strategies. Our method uses an LLM-based judge to cluster rollouts for the same problem according to their high-level solution strategies, ignoring superficial variations, and reweights policy advantages inversely with cluster size. As a result, correct but novel strategies receive higher rewards than redundant ones. Across mathematics, physics, and medical reasoning benchmarks, our approach consistently improves pass@$k$ across large sampling budgets and increases the area under the pass@$k$ curve (AUC@$K$) without sacrificing pass@1, while sustaining exploration and uncovering more diverse solution strategies at scale.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Document-Level Event Extraction via Human-Like Reading Process

Document-level Event Extraction (DEE) is particularly tricky due to the two challenges it poses: scattering-arguments and multi-events. The first challenge means that arguments of one event record could reside in different sentences in the document, while the second one reflects one document may simultaneously contain multiple such event records. Motivated by humans' reading cognitive to extract information of interests, in this paper, we propose a method called HRE (Human Reading inspired Extractor for Document Events), where DEE is decomposed into these two iterative stages, rough reading and elaborate reading. Specifically, the first stage browses the document to detect the occurrence of events, and the second stage serves to extract specific event arguments. For each concrete event role, elaborate reading hierarchically works from sentences to characters to locate arguments across sentences, thus the scattering-arguments problem is tackled. Meanwhile, rough reading is explored in a multi-round manner to discover undetected events, thus the multi-events problem is handled. Experiment results show the superiority of HRE over prior competitive methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ideal approximation in $n$-exangulated categories

In this paper, we study the ideal approximation theory associated to almost $n$-exact structures in the $n$-exangulated category. The notions of $n$-ideal cotorsion pairs and $n$-$\mathbb{F}$-phantom morphisms are introduced and studied. In particular, let $\mathscr{C}$ be an extriangulated category which satisfies the condition (WIC) and $\mathcal{T}$ be a nicely embedded $n$-cluster tilting subcategory of $\mathscr{C}$, we prove Salce's Lemma in $\mathcal{T}$.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Many-body critical phase: extended and nonthermal

The transition between ergodic phase and many-body localization (MBL) phase lies at the heart in understanding quantum thermalization of many-body systems. Here we predict a many-body critical phase in the one-dimensional extended Aubry-André-Harper-Hubbard model, which is different from both the ergodic phase and MBL phase, implying that the quantum system hosts three different fundamental phases. It is shown that the level statistics in the many-body critical phase are well characterized by the so-called critical statistics, and the wave functions in this phase generally exhibit a multifractal behavior. We further study the half-chain entanglement entropy (EE) and thermalization properties by exact diagonalization, which show that the EE in this critical phase manifest a volume law EE scaling while the many-body states violate the eigenstate thermalization hypothesis. This work unveils a novel many-body phase which is extended but non-ergodic.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Edge corona product as an approach to modeling complex simplical networks

Many graph products have been applied to generate complex networks with striking properties observed in real-world systems. In this paper, we propose a simple generative model for simplicial networks by iteratively using edge corona product. We present a comprehensive analysis of the structural properties of the network model, including degree distribution, diameter, clustering coefficient, as well as distribution of clique sizes, obtaining explicit expressions for these relevant quantities, which agree with the behaviors found in diverse real networks. Moreover, we obtain exact expressions for all the eigenvalues and their associated multiplicities of the normalized Laplacian matrix, based on which we derive explicit formulas for mixing time, mean hitting time and the number of spanning trees. Thus, as previous models generated by other graph products, our model is also an exactly solvable one, whose structural properties can be analytically treated. More interestingly, the expressions for the spectra of our model are also exactly determined, which is sharp contrast to previous models whose spectra can only be given recursively at most. This advantage makes our model a good test-bed and an ideal substrate network for studying dynamical processes, especially those closely related to the spectra of normalized Laplacian matrix, in order to uncover the influences of simplicial structure on these processes.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Exact mobility edges, $\mathcal{PT}$-symmetry breaking and skin effect in one-dimensional non-Hermitian quasicrystals

We propose a general analytic method to study the localization transition in one-dimensional quasicrystals with parity-time ($\mathcal{PT}$) symmetry, described by complex quasiperiodic mosaic lattice models. By applying Avila's global theory of quasiperiodic Schrödinger operators, we obtain exact mobility edges and prove that the mobility edge is identical to the boundary of $\mathcal{PT}$-symmetry breaking, which also proves the existence of correspondence between extended (localized) states and $\mathcal{PT}$-symmetry ($\mathcal{PT}$-symmetry-broken) states. Furthermore, we generalize the models to more general cases with non-reciprocal hopping, which breaks $\mathcal{PT}$ symmetry and generally induces skin effect, and obtain a general and analytical expression of mobility edges. While the localized states are not sensitive to the boundary conditions, the extended states become skin states when the periodic boundary condition is changed to open boundary condition. This indicates that the skin states and localized states can coexist with their boundary determined by the mobility edges.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On Uplink Performance of Multiuser Massive MIMO Relay Network With Limited RF Chains

This paper considers a multiuser massive multiple-input multiple-output uplink with the help of an analog amplify-and-forward relay. The base station equips a large array of $N_d$ antennas but is supported by a far smaller number of radio-frequency chains. By first deriving new results for a cascaded phase-aligned two-hop channel, we obtain a tight bound for the ergodic rate in closed form for both perfect and quantized channel phase information. The rate is characterized as a function of a scaled equivalent signal-to-noise ratio of the two-hop channel. It implies that the source and relay powers can be respectively scaled down as $1/N_d^a$ and $1/N_d^{1-a}~ (0\!\leq\!a\!\leq\!1)$ for an asymptotically unchanged sum rate. Then for the rate maximization, the problem of power allocation is optimized with closed-form solutions. Simulation results verified the observations of our derived results.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Realization and detection of non-ergodic critical phases in optical Raman lattice

The critical phases, being delocalized but non-ergodic, are fundamental phases which are different from both the many-body localization and ergodic extended quantum phases, and have so far not been realized in experiment. Here we propose to realize such critical phases with and without interaction based on a topological optical Raman lattice scheme, which possesses one-dimensional spin-orbit coupling and an incommensurate Zeeman potential. We demonstrate the existence of both the noninteracting and many-body critical phases, which can coexist with the topological phase, and show that the critical-localization transition coincides with the topological phase boundary in noninteracting regime. The dynamical detection of the critical phases is proposed and studied in detail. Finally, we demonstrate how the proposed critical phases can be achieved based on the current cold atom experiments. This work paves the way to observe the novel critical phases.

0 citations0 reviewsNo code linkedOpen access