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

Zhengzhong Tu

Zhengzhong Tu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visioneess.IVArtificial IntelligenceMachine LearningMultimediaGraphicsRobotics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
16works
0followers
7topics
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

16 published item(s)

preprint2026arXiv

AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving

Recent advancements in large vision language models (VLMs) tailored for autonomous driving (AD) have shown strong scene understanding and reasoning capabilities, making them undeniable candidates for end-to-end driving systems. However, limited work exists on studying the trustworthiness of DriveVLMs -- a critical factor that directly impacts public transportation safety. In this paper, we introduce AutoTrust, a comprehensive trustworthiness benchmark for large vision-language models in autonomous driving (DriveVLMs), considering diverse perspectives -- including trustfulness, safety, robustness, privacy, and fairness. We constructed the largest visual question-answering dataset for investigating trustworthiness issues in driving scenarios, comprising over 10k unique scenes and 18k queries. We evaluated six publicly available VLMs, spanning from generalist to specialist, from open-source to commercial models. Our exhaustive evaluations have unveiled previously undiscovered vulnerabilities of DriveVLMs to trustworthiness threats. Specifically, we found that the general VLMs like LLaVA-v1.6 and GPT-4o-mini surprisingly outperform specialized models fine-tuned for driving in terms of overall trustworthiness. DriveVLMs like DriveLM-Agent are particularly vulnerable to disclosing sensitive information. Additionally, both generalist and specialist VLMs remain susceptible to adversarial attacks and struggle to ensure unbiased decision-making across diverse environments and populations. Our findings call for immediate and decisive action to address the trustworthiness of DriveVLMs -- an issue of critical importance to public safety and the welfare of all citizens relying on autonomous transportation systems. We release all the codes and datasets in https://github.com/taco-group/AutoTrust.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search

Humanoid Visual Search (HVS) requires agents to actively explore immersive 360$^\circ$ environments. While prior methods treat this as a monolithic task relying on cumulative, multi-turn Chain-of-Thought (CoT) reasoning, they impose heavy cognitive burdens and require expensive trajectory-level annotations. In this paper, we propose Imagining in 360$^\circ$, a novel framework that decouples the exploration process into a specialized Imaginator and an Actor. The Imaginator functions as a probabilistic predictor of spatial priors; instead of maintaining a cumulative reasoning chain, it infers the semantic layout of both observed and unobserved regions in a single step. By sampling multiple hypotheses within this semantic space, we provide the Actor with a distribution of effective spatial information, offering robust guidance that hedges against uncertainty during active search. This decoupled architecture significantly lowers data engineering costs by eliminating the need for full-trajectory CoT annotations, enabling the generation of over 1.96 million curated training samples. Extensive experiments demonstrate that explicitly modeling semantic spatial priors drastically improves search efficiency and success rates in complex, in-the-wild environments.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning

Parallel reasoning, where a generator samples many candidate solutions and an aggregator selects the best, is one of the most effective forms of test-time scaling in large language models, and pairwise self-verification has become its strongest aggregation primitive. Yet pairwise verification carries a heavy cost: each judgment reads two complete solutions in full, and existing methods perform tens of such judgments per problem regardless of whether the comparison is informative. We introduce CAPS (Cascaded Adaptive Pairwise Selection), an inference-only framework that allocates verifier compute non-uniformly along two orthogonal axes: an evidence axis that adapts how much of each candidate the judge sees, and a distribution axis that adapts how comparisons are spread across the pool. CAPS instantiates these into a four-stage cascade with an optional rescue subroutine, and admits a closed-form verifier-token cost in which the per-candidate marginal cost is roughly halved relative to uniform full-evidence schedules. On four self-verifying models (Qwen3-14B, GPT-OSS-20B, Qwen3-4B-Instruct/Thinking) and five reasoning benchmarks spanning code (LiveCodeBench-v5/v6, CodeContests) and math (AIME 2025, HMMT 2025), CAPS outperforms the leading pairwise verifier on 14 of 20 suites while using 25.4% of its verifier-token budget on code, and outperforms pointwise self-verification on all 20. The trade-off suites admit an interpretable diagnostic in terms of the verifier's accuracy at partial versus full evidence, providing a concrete pre-deployment check for cascade suitability.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation

Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in balancing reactivity and stability: models must respond promptly to new events while maintaining temporal coherence over long horizons. Existing approaches distill bidirectional models into autoregressive generators and further adapt them via streaming long tuning, yet often exhibit persistent drift after condition changes. We identify the cause as conditional bias, where the teacher may provide condition-aligned but trajectory-agnostic guidance, biasing generation toward locally valid yet globally inconsistent modes. Inspired by Trust Region Policy Optimization, we propose Delta Forcing, a simple yet effective framework that constrains unreliable teacher supervision within an adaptive trust region. Specifically, Delta Forcing estimates transition consistency from the latent delta between teacher and generator trajectories, and uses it to balance teacher supervision with a monotonic continuity objective. This suppress unreliable teacher-induced shifts while preserving responsiveness to new events. Extensive experiments demonstrate that Delta Forcing significantly improves consistency while maintaining event reactivity.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models

Digital twins, as precise digital representations of physical systems, have evolved from passive simulation tools into intelligent and autonomous entities through the integration of artificial intelligence technologies. This paper presents a unified four-stage framework that systematically characterizes AI integration across the digital twin lifecycle, spanning modeling, mirroring, intervention, and autonomous management. By synthesizing existing technologies and practices, we distill a unified four-stage framework that systematically characterizes how AI methodologies are embedded across the digital twin lifecycle: (1) modeling the physical twin through physics-based and physics-informed AI approaches, (2) mirroring the physical system into a digital twin with real-time synchronization, (3) intervening in the physical twin through predictive modeling, anomaly detection, and optimization strategies, and (4) achieving autonomous management through large language models, foundation models, and intelligent agents. We analyze the synergy between physics-based modeling and data-driven learning, highlighting the shift from traditional numerical solvers to physics-informed and foundation models for physical systems. Furthermore, we examine how generative AI technologies, including large language models and generative world models, transform digital twins into proactive and self-improving cognitive systems capable of reasoning, communication, and creative scenario generation. Through a cross-domain review spanning eleven application domains, including healthcare, aerospace, smart manufacturing, robotics, and smart cities, we identify common challenges related to scalability, explainability, and trustworthiness, and outline directions for responsible AI-driven digital twin systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitation of question-level difficulty bias. We also identify a connection between GRPO and traditional discriminative methods in supervised learning. Motivated by these insights, we introduce a new Discriminative Constrained Optimization (DisCO) framework for reinforcing LRMs, grounded in the principle of discriminative learning. The main differences between DisCO and GRPO and its recent variants are: (1) it replaces the group relative objective with a discriminative objective defined by a scoring function; (2) it abandons clipping-based surrogates in favor of non-clipping RL surrogate objectives used as scoring functions; (3) it employs a simple yet effective constrained optimization approach to enforce the KL divergence constraint. As a result, DisCO offers notable advantages over GRPO and its variants: (i) it completely eliminates difficulty bias by adopting discriminative objectives; (ii) it addresses the entropy instability in GRPO and its variants through the use of non-clipping scoring functions and a constrained optimization approach, yielding long and stable training dynamics; (iii) it allows the incorporation of advanced discriminative learning techniques to address data imbalance, where a significant number of questions have more negative than positive generated answers during training. Our experiments on enhancing the mathematical reasoning capabilities of SFT-finetuned models show that DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7\% over GRPO and 6\% over DAPO across six benchmark tasks for a 1.5B model.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

FAVER: Blind Quality Prediction of Variable Frame Rate Videos

Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to capture, process, and share high resolution, high frame rate (HFR) videos across the Internet nearly instantaneously. Being able to monitor and control the quality of these streamed videos can enable the delivery of more enjoyable content and perceptually optimized rate control. Accordingly, there is a pressing need to develop VQA models that can be deployed at enormous scales. While some recent effects have been applied to full-reference (FR) analysis of variable frame rate and HFR video quality, the development of no-reference (NR) VQA algorithms targeting frame rate variations has been little studied. Here, we propose a first-of-a-kind blind VQA model for evaluating HFR videos, which we dub the Framerate-Aware Video Evaluator w/o Reference (FAVER). FAVER uses extended models of spatial natural scene statistics that encompass space-time wavelet-decomposed video signals, to conduct efficient frame rate sensitive quality prediction. Our extensive experiments on several HFR video quality datasets show that FAVER outperforms other blind VQA algorithms at a reasonable computational cost. To facilitate reproducible research and public evaluation, an implementation of FAVER is being made freely available online: \url{https://github.com/uniqzheng/HFR-BVQA}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MAXIM: Multi-Axis MLP for Image Processing

Recent progress on Transformers and multi-layer perceptron (MLP) models provide new network architectural designs for computer vision tasks. Although these models proved to be effective in many vision tasks such as image recognition, there remain challenges in adapting them for low-level vision. The inflexibility to support high-resolution images and limitations of local attention are perhaps the main bottlenecks. In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks. MAXIM uses a UNet-shaped hierarchical structure and supports long-range interactions enabled by spatially-gated MLPs. Specifically, MAXIM contains two MLP-based building blocks: a multi-axis gated MLP that allows for efficient and scalable spatial mixing of local and global visual cues, and a cross-gating block, an alternative to cross-attention, which accounts for cross-feature conditioning. Both these modules are exclusively based on MLPs, but also benefit from being both global and `fully-convolutional', two properties that are desirable for image processing. Our extensive experimental results show that the proposed MAXIM model achieves state-of-the-art performance on more than ten benchmarks across a range of image processing tasks, including denoising, deblurring, deraining, dehazing, and enhancement while requiring fewer or comparable numbers of parameters and FLOPs than competitive models. The source code and trained models will be available at \url{https://github.com/google-research/maxim}.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MaxViT: Multi-Axis Vision Transformer

Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision backbones. In this paper we introduce an efficient and scalable attention model we call multi-axis attention, which consists of two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. We also present a new architectural element by effectively blending our proposed attention model with convolutions, and accordingly propose a simple hierarchical vision backbone, dubbed MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to ''see'' globally throughout the entire network, even in earlier, high-resolution stages. We demonstrate the effectiveness of our model on a broad spectrum of vision tasks. On image classification, MaxViT achieves state-of-the-art performance under various settings: without extra data, MaxViT attains 86.5% ImageNet-1K top-1 accuracy; with ImageNet-21K pre-training, our model achieves 88.7% top-1 accuracy. For downstream tasks, MaxViT as a backbone delivers favorable performance on object detection as well as visual aesthetic assessment. We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module. The source code and trained models will be available at https://github.com/google-research/maxvit.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Perceptual Quality Assessment of UGC Gaming Videos

In recent years, with the vigorous development of the video game industry, the proportion of gaming videos on major video websites like YouTube has dramatically increased. However, relatively little research has been done on the automatic quality prediction of gaming videos, especially on those that fall in the category of "User-Generated-Content" (UGC). Since current leading general-purpose Video Quality Assessment (VQA) models do not perform well on this type of gaming videos, we have created a new VQA model specifically designed to succeed on UGC gaming videos, which we call the Gaming Video Quality Predictor (GAME-VQP). GAME-VQP successfully predicts the unique statistical characteristics of gaming videos by drawing upon features designed under modified natural scene statistics models, combined with gaming specific features learned by a Convolution Neural Network. We study the performance of GAME-VQP on a very recent large UGC gaming video database called LIVE-YT-Gaming, and find that it both outperforms other mainstream general VQA models as well as VQA models specifically designed for gaming videos. The new model will be made public after paper being accepted.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

ROMNet: Renovate the Old Memories

Renovating the memories in old photos is an intriguing research topic in computer vision fields. These legacy images often suffer from severe and commingled degradations such as cracks, noise, and color-fading, while lack of large-scale paired old photo datasets makes this restoration task very challenging. In this work, we present a novel reference-based end-to-end learning framework that can jointly repair and colorize the degraded legacy pictures. Specifically, the proposed framework consists of three modules: a restoration sub-network for degradation restoration, a similarity sub-network for color histogram matching and transfer, and a colorization subnet that learns to predict the chroma elements of the images conditioned on chromatic reference signals. The whole system takes advantage of the color histogram priors in a given reference image, which vastly reduces the dependency on large-scale training data. Apart from the proposed method, we also create, to our knowledge, the first public and real-world old photo dataset with paired ground truth for evaluating old photo restoration models, wherein each old photo is paired with a manually restored pristine image by PhotoShop experts. Our extensive experiments conducted on both synthetic and real-world datasets demonstrate that our method significantly outperforms state-of-the-arts both quantitatively and qualitatively.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer

In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust cooperative perception framework with V2X communication using a novel vision Transformer. Specifically, we build a holistic attention model, namely V2X-ViT, to effectively fuse information across on-road agents (i.e., vehicles and infrastructure). V2X-ViT consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spatial relationships. These key modules are designed in a unified Transformer architecture to handle common V2X challenges, including asynchronous information sharing, pose errors, and heterogeneity of V2X components. To validate our approach, we create a large-scale V2X perception dataset using CARLA and OpenCDA. Extensive experimental results demonstrate that V2X-ViT sets new state-of-the-art performance for 3D object detection and achieves robust performance even under harsh, noisy environments. The code is available at https://github.com/DerrickXuNu/v2x-vit.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Predicting Eye Fixations Under Distortion Using Bayesian Observers

Visual attention is very an essential factor that affects how human perceives visual signals. This report investigates how distortions in an image could distract human's visual attention using Bayesian visual search models, specifically, Maximum-a-posteriori (MAP) \cite{findlay1982global}\cite{eckstein2001quantifying} and Entropy Limit Minimization (ELM) \cite{najemnik2009simple}, which predict eye fixation movements based on a Bayesian probabilistic framework. Experiments on modified MAP and ELM models on JPEG-compressed images containing blocking or ringing artifacts were conducted and we observed that compression artifacts can affect visual attention. We hope this work sheds light on the interactions between visual attention and perceptual quality.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality Models

Video and image quality assessment has long been projected as a regression problem, which requires predicting a continuous quality score given an input stimulus. However, recent efforts have shown that accurate quality score regression on real-world user-generated content (UGC) is a very challenging task. To make the problem more tractable, we propose two new methods - binary, and ordinal classification - as alternatives to evaluate and compare no-reference quality models at coarser levels. Moreover, the proposed new tasks convey more practical meaning on perceptually optimized UGC transcoding, or for preprocessing on media processing platforms. We conduct a comprehensive benchmark experiment of popular no-reference quality models on recent in-the-wild picture and video quality datasets, providing reliable baselines for both evaluation methods to support further studies. We hope this work promotes coarse-grained perceptual modeling and its applications to efficient UGC processing.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Comparative Evaluation of Temporal Pooling Methods for Blind Video Quality Assessment

Many objective video quality assessment (VQA) algorithms include a key step of temporal pooling of frame-level quality scores. However, less attention has been paid to studying the relative efficiencies of different pooling methods on no-reference (blind) VQA. Here we conduct a large-scale comparative evaluation to assess the capabilities and limitations of multiple temporal pooling strategies on blind VQA of user-generated videos. The study yields insights and general guidance regarding the application and selection of temporal pooling models. In addition, we also propose an ensemble pooling model built on top of high-performing temporal pooling models. Our experimental results demonstrate the relative efficacies of the evaluated temporal pooling models, using several popular VQA algorithms, and evaluated on two recent large-scale natural video quality databases. In addition to the new ensemble model, we provide a general recipe for applying temporal pooling of frame-based quality predictions.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

BBAND Index: A No-Reference Banding Artifact Predictor

Banding artifact, or false contouring, is a common video compression impairment that tends to appear on large flat regions in encoded videos. These staircase-shaped color bands can be very noticeable in high-definition videos. Here we study this artifact, and propose a new distortion-specific no-reference video quality model for predicting banding artifacts, called the Blind BANding Detector (BBAND index). BBAND is inspired by human visual models. The proposed detector can generate a pixel-wise banding visibility map and output a banding severity score at both the frame and video levels. Experimental results show that our proposed method outperforms state-of-the-art banding detection algorithms and delivers better consistency with subjective evaluations.

0 citations0 reviewsNo code linkedOpen access