Bin Wang

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…

Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are often very incomplete. To perform zero-shot knowledge graph completion…

Based on $(10087\pm44)\times10^{6}$ $J/\psi$ events collected with the BESIII detector, the $J/\psi\rightarrow\gamma K^{0}_{S}K^{0}_{S}\pi^{0}$ and $J/\psi\rightarrow\gamma \pi^{0}\pi^{0}\eta$ processes are studied. The $X(2370)$ is…

Using $(10\,087 \pm 44) \times 10^6$ $J/\psi$ events collected with the BESIII detector, we perform the first amplitude analysis of the process $J/\psi\to\gamma\eta\pi^0$. The decay is dominated by the intermediate processes $J/\psi\to\pi^0…

Generative sequence models have shown strong results in recommendation. Applying them to search ranking is more challenging. Search behavior is inherently query-driven. Each query switch introduces a sharp topic shift in the user's…

Reinforcement learning offers a promising approach for scan-order optimisation in laser additive manufacturing, where sequential scan decisions critically influence thermal accumulation, residual stress, distortion, and final part quality.…

VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together with their bounding boxes and textual content. However,…

Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP…

Using 44.55 fb$^{-1}$ of $e^+e^-$ collision data collected by the BESIII detector at the BEPCII collider, we report the first measurement of the Born cross sections for the $e^+e^- \to K^+\Xi^0\bar\Sigma^-$ reaction at fifty-six…

Using $(2712.4 \pm 14.3) \times 10^6~\psi(3686)$ events collected by the BESIII detector operating at the BEPCII collider, the hadronic decay $\eta_{c}\to\Sigma^{0}\bar{\Sigma^{0}}$ is observed for the first time via the radiative…

Based on a novel method for producing antineutrons via $J/\psi$ decays, we report a study of $\bar{n}p$ inelastic scattering into final states containing kaons. The analysis uses $(10087\pm44)\times 10^6$ $J/\psi$ events collected at the…

Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting evidence unchecked. This answer-only approach masks a critical…

Recent knowledge graph (KG)-enhanced large language models (LLMs) move beyond purely textual knowledge augmentation by encoding retrieved subgraphs into continuous soft prompts via graph neural networks, introducing a graph-conditioned…

We present the first amplitude analysis and branching fraction measurement of $D^{+} \rightarrow K_{S}^{0}K_{L}^{0}\pi^{+}$ decay. The analysis uses a dataset corresponding to an integrated luminosity of 20.3~$\rm fb^{-1}$, which was…

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests…

Short-term air traffic flow prediction in terminal airspace is essential for proactive air traffic management. Existing approaches predominantly model traffic flow as aggregated time series, despite traffic dynamics being governed by…

Sparse-view satellite image surface reconstruction remains highly challenging, fundamentally because the reliability of multi-view matching under satellite imaging conditions is strongly spatially heterogeneous. Affected by large…

Based on (2712.4+-14.3)*10^{6} psi(3686) events collected with the BESIII detector, the decays Xi(1530)^{-} to Xi^{0} pi^{-} and Xi(1530)^{-} to Xi^{-} pi^{0} are investigated jointly via the process psi(3686) to anti-Xi^{+} Xi(1530)^{-} +…

Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies predominantly concentrate on adversarial attacks or inherent…

Optical Chemical Structure Recognition (OCSR) aims to translate molecular diagrams in scientific literature into machine-readable formats, but current systems remain unreliable on real-world images due to substantial visual and chemical…