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

Yuyao Zhang

Yuyao Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionArtificial Intelligenceeess.IVGraphicsMachine Learning

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
9works
0followers
5topics
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

9 published item(s)

preprint2026arXiv

AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling

Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (UHR) long videos remains prohibitively expensive. The difficulty is especially pronounced for long single-shot generation where a continuous scene must preserve global temporal coherence, and fine-grained spatial details without relying on clip transitions or autoregressive shot stitching. In this work, we revisit this challenge from the perspective of decoupled modeling. We argue that existing video diffusion models already encode strong local visual priors, while the main bottleneck lies in efficiently extending global spatiotemporal modeling as resolution and duration increase. Based on this insight, we propose AtlaVid, a decoupled global-local framework for efficient UHR long video generation. AtlaVid first generates a low-resolution and low-FPS global semantic proxy via temporally scaled RoPE, thereby extending the temporal horizon without increasing the training token count. Guided by this proxy, a high-resolution detail branch performs joint denoising with hierarchical locality-preserving attention. Reordered spatiotemporal windows preserve geometric locality and asymmetric global-local attention injects aligned semantic guidance and preserves the model's pretrained ability. This design enables resolution-agnostic training: the model is trained only at 720P with lightweight LoRA adaptation, yet generalizes directly to 4K and beyond for longer (>10s) video synthesis. Experiments show that AtlaVid substantially improves the efficiency of ultra-high-resolution long video generation, achieving high-quality UHR long video generation with 60.9x speed up and significantly less training cost and even better performance than native 4K video generators.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction

Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient training and suboptimal imaging quality. Recent initialization-based approaches attempt to inject population priors into pre-trained networks, yet they rely on high-quality images and often suffer from catastrophic forgetting during fine-tuning. We present DisINR, a novel INR framework that explicitly disentangles shared and subject-specific representations. DisINR introduces a shared encoder-decoder pair and subject-specific encoders, whose features are jointly decoded for image reconstruction. By integrating differentiable forward models, it pre-trains the shared modules directly from limited raw measurements, removing the need for pre-acquired high-quality images. During test-time adaptation, only the subject-specific encoder is optimized, while the shared pair remains frozen, effectively preserving learned priors. Extensive evaluations on three representative medical imaging tasks show that DisINR significantly outperforms state-of-the-art INRs in both reconstruction accuracy and efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Efficient Reinforcement Learning with Semantic and Token Entropy for LLM Reasoning

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy collapse, which reduces policy exploration and limits reasoning capabilities. To address this challenge, we propose an efficient reinforcement learning framework that leverages entropy signals at both the semantic and token levels to improve reasoning. From the data perspective, we introduce semantic entropy-guided curriculum learning, organizing training data from low to high semantic entropy to guide progressive optimization from easier to more challenging tasks. For the algorithmic design, we adopt non-uniform token treatment by imposing KL regularization on low-entropy tokens that critically impact policy exploration and applying stronger constraints on high-covariance portions within these tokens. By jointly optimizing data organization and algorithmic design, our method effectively mitigates entropy collapse and enhances LLM reasoning. Experimental results across 6 benchmarks with 3 different parameter-scale base models demonstrate that our method outperforms other entropy-based approaches in improving reasoning.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce HierEdit, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (\textbf{Local-Window MMDiT}) that refines only edited regions within the original high-res image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (\textbf{Inference Acceleration}) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without any specialized high-resolution training data. Extensive experiments demonstrate that HierEdit achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing. Please check our {\href{https://peteryyzhang.github.io/HierEdit-page/}{\textbf{Project Page}}}.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning

Large Reasoning Models (LRMs) often suffer from overthinking, generating verbose reasoning traces that compromise both computational efficiency and interpretability. Unlike prior efforts that rely on global length-based rewards, we propose a semantic-aware decomposition of redundancy into two distinct forms: internal redundancy (informational stagnation within the reasoning process) and external redundancy (superfluous continuation after the final answer). We introduce a dual-penalty reinforcement learning framework that surgically targets these inefficiencies: a sliding-window semantic analysis is employed to penalize low-gain steps within the reasoning trajectory, while a normalized metric suppresses the post-answer tail. Extensive experiments demonstrate that our method significantly compresses Chain-of-Thought traces with minimal accuracy degradation, while maintaining strong generalization to out-of-domain tasks. Crucially, we reveal an asymmetry in redundancy: external redundancy can be safely eliminated without performance loss, whereas internal redundancy removal requires a calibrated trade-off to maintain reasoning fidelity. Our framework enables fine-grained, implicit control over reasoning length, paving the way for more concise and interpretable LRMs.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning

Large reasoning models (LRMs) have attracted much attention due to their exceptional performance. However, their performance mainly stems from thinking, a long Chain of Thought (CoT), which significantly increase computational overhead. To address this overthinking problem, existing work focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. Unfortunately, using RL will suffer the the reward hacking problem, e.g., the model engages in thinking but is judged as not doing so, resulting in incorrect rewards. To mitigate this problem, existing works either employ supervised fine-tuning (SFT), which incurs high computational costs, or enforce uniform token limits on non-thinking responses, which yields limited mitigation of the problem. In this paper, we propose Thinking-Based Non-Thinking (TNT). It does not employ SFT, and sets different maximum token usage for responses not using thinking across various queries by leveraging information from the solution component of the responses using thinking. Experiments on five mathematical benchmarks demonstrate that TNT reduces token usage by around 50% compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5B, while significantly improving accuracy. In fact, TNT achieves the optimal trade-off between accuracy and efficiency among all tested methods. Additionally, the probability of reward hacking problem in TNT's responses, which are classified as not using thinking, remains below 10% across all tested datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Continuous longitudinal fetus brain atlas construction via implicit neural representation

Longitudinal fetal brain atlas is a powerful tool for understanding and characterizing the complex process of fetus brain development. Existing fetus brain atlases are typically constructed by averaged brain images on discrete time points independently over time. Due to the differences in onto-genetic trends among samples at different time points, the resulting atlases suffer from temporal inconsistency, which may lead to estimating error of the brain developmental characteristic parameters along the timeline. To this end, we proposed a multi-stage deep-learning framework to tackle the time inconsistency issue as a 4D (3D brain volume + 1D age) image data denoising task. Using implicit neural representation, we construct a continuous and noise-free longitudinal fetus brain atlas as a function of the 4D spatial-temporal coordinate. Experimental results on two public fetal brain atlases (CRL and FBA-Chinese atlases) show that the proposed method can significantly improve the atlas temporal consistency while maintaining good fetus brain structure representation. In addition, the continuous longitudinal fetus brain atlases can also be extensively applied to generate finer 4D atlases in both spatial and temporal resolution.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NIMBLE: A Non-rigid Hand Model with Bones and Muscles

Emerging Metaverse applications demand reliable, accurate, and photorealistic reproductions of human hands to perform sophisticated operations as if in the physical world. While real human hand represents one of the most intricate coordination between bones, muscle, tendon, and skin, state-of-the-art techniques unanimously focus on modeling only the skeleton of the hand. In this paper, we present NIMBLE, a novel parametric hand model that includes the missing key components, bringing 3D hand model to a new level of realism. We first annotate muscles, bones and skins on the recent Magnetic Resonance Imaging hand (MRI-Hand) dataset and then register a volumetric template hand onto individual poses and subjects within the dataset. NIMBLE consists of 20 bones as triangular meshes, 7 muscle groups as tetrahedral meshes, and a skin mesh. Via iterative shape registration and parameter learning, it further produces shape blend shapes, pose blend shapes, and a joint regressor. We demonstrate applying NIMBLE to modeling, rendering, and visual inference tasks. By enforcing the inner bones and muscles to match anatomic and kinematic rules, NIMBLE can animate 3D hands to new poses at unprecedented realism. To model the appearance of skin, we further construct a photometric HandStage to acquire high-quality textures and normal maps to model wrinkles and palm print. Finally, NIMBLE also benefits learning-based hand pose and shape estimation by either synthesizing rich data or acting directly as a differentiable layer in the inference network.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Noise2SR: Learning to Denoise from Super-Resolved Single Noisy Fluorescence Image

Fluorescence microscopy is a key driver to promote discoveries of biomedical research. However, with the limitation of microscope hardware and characteristics of the observed samples, the fluorescence microscopy images are susceptible to noise. Recently, a few self-supervised deep learning (DL) denoising methods have been proposed. However, the training efficiency and denoising performance of existing methods are relatively low in real scene noise removal. To address this issue, this paper proposed self-supervised image denoising method Noise2SR (N2SR) to train a simple and effective image denoising model based on single noisy observation. Our Noise2SR denoising model is designed for training with paired noisy images of different dimensions. Benefiting from this training strategy, Noise2SR is more efficiently self-supervised and able to restore more image details from a single noisy observation. Experimental results of simulated noise and real microscopy noise removal show that Noise2SR outperforms two blind-spot based self-supervised deep learning image denoising methods. We envision that Noise2SR has the potential to improve more other kind of scientific imaging quality.

0 citations0 reviewsNo code linkedOpen access