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

Yue Ding

Yue Ding contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
cond-mat.mtrl-sciMachine Learningphysics.app-phArtificial IntelligenceComputer Visionhep-th

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
6works
0followers
6topics
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

6 published item(s)

preprint2026arXiv

Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

CS-GBA: A Critical Sample-based Gradient-guided Backdoor Attack for Offline Reinforcement Learning

Offline Reinforcement Learning (RL) enables policy optimization from static datasets but is inherently vulnerable to backdoor attacks. Existing attack strategies typically struggle against safety-constrained algorithms (e.g., CQL) due to inefficient random poisoning and the use of easily detectable Out-of-Distribution (OOD) triggers. In this paper, we propose CS-GBA (Critical Sample-based Gradient-guided Backdoor Attack), a novel framework designed to achieve high stealthiness and destructiveness under a strict budget. Leveraging the theoretical insight that samples with high Temporal Difference (TD) errors are pivotal for value function convergence, we introduce an adaptive Critical Sample Selection strategy that concentrates the attack budget on the most influential transitions. To evade OOD detection, we propose a Correlation-Breaking Trigger mechanism that exploits the physical mutual exclusivity of state features (e.g., 95th percentile boundaries) to remain statistically concealed. Furthermore, we replace the conventional label inversion with a Gradient-Guided Action Generation mechanism, which searches for worst-case actions within the data manifold using the victim Q-network's gradient. Empirical results on D4RL benchmarks demonstrate that our method significantly outperforms state-of-the-art baselines, achieving high attack success rates against representative safety-constrained algorithms with a minimal 5% poisoning budget, while maintaining the agent's performance in clean environments.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach

Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations. GCL can generate graph-level embeddings by maximizing the Mutual Information (MI) between different augmented views of the same graph (positive pairs). However, the GCL is limited by dimensional collapse, i.e., embedding vectors only occupy a low-dimensional subspace. In this paper, we show that the smoothing effect of the graph pooling and the implicit regularization of the graph convolution are two causes of the dimensional collapse in GCL. To mitigate the above issue, we propose a non-maximum removal graph contrastive learning approach (nmrGCL), which removes "prominent'' dimensions (i.e., contribute most in similarity measurement) for positive pair in the pre-text task. Comprehensive experiments on various benchmark datasets are conducted to demonstrate the effectiveness of nmrGCL, and the results show that our model outperforms the state-of-the-art methods. Source code will be made publicly available.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Holographic Schwinger effect in a soft wall AdS/QCD model

We perform the potential analysis for the holographic Schwinger effect in a deformed $AdS_5$ model with conformal invariance broken by a background dilaton. We evaluate the static potential by analyzing the classical action of a string attaching the rectangular Wilson loop on a probe D3 brane sitting at an intermediate position in the bulk AdS space. We observe that the inclusion of chemical potential tends to enhance the production rate, reverse to the effect of confining scale. Also, we calculate the critical electric field by Dirac-Born-Infeld (DBI) action.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The three-dimensional statistical characterization of plain grinding surfaces

In tribology, it is of importance to properly characterize the topography of rough surfaces. In this work, the three-dimensional topographies of plain grinding surfaces are measured through a white light interferometer, and their geometrical statistical features are analyzed. It is noticed that only when the total measured area is larger than a threshold value, is the statistical characterization reasonable and stable, which should be kept in mind in actual measurements. For various plain grinding surfaces, the height of asperity-summit obeys a Gaussian distribution, and the equivalent curvature radius follows a modified F-distribution. These statistical characteristics are helpful to analyze the contact and friction behaviors of rough surfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Size dependent yield hardness induced by surface energy

Size dependent hardness has long been reported in nanosized indentations, however the corresponding explanation is still in exploration. In this paper, we examine the influence of surface energy on the hardness of materials under spherical indentation. To evaluate the ability of materials to resist indentation, a yield hardness is defined here as the contact pressure at the inception of material yield. It is found that this defined hardness is an intrinsic material property depending only on the yield strength and Poisson ratio in conventional continuum mechanics. Then, the impact of surface energy on the yield hardness is analyzed through finite element simulations. By using the dimensional analysis, the dependences of the yield hardness and critical indent depth at yield initiation on surface energy have been achieved. When the yield strength is comparable to the ratio of surface energy density to indenter radius, surface energy will alter the yield hardness and the critical indent depth. As the size of indenter decreases to nanoscale, both the yield hardness and the indent depth will increase significantly. This study provides a possible clarification to the size dependence of hardness and a potential approach to measure the yield strength and surface energy of solids through nanosized indentations.

0 citations0 reviewsNo code linkedOpen access