The "2nd Frontiers in Graph Machine Learning for the Large Model Era (GMLLM'26)" workshop focuses on advancing graph machine learning (GML) techniques in the context of large-scale foundation models. Graphs offer a principled way to represent structured and relational data, making them essential for capturing complex dependencies in knowledge, systems, and behaviors. As the scale and influence of foundation models grow, graph learning is well positioned to enhance model robustness, improve interpretability, and integrate domain-specific relational priors. This workshop explores how graph learning can support emerging challenges in knowledge reasoning, temporal and multi-hop inference, and AI systems. It also investigates how advances in representation learning, structure-aware generalization, and efficient graph processing can contribute to trustworthy and scalable AI systems. By convening experts in graph learning, knowledge management, and LLMs, the workshop aims to identify core challenges and opportunities of GML in the large model era.
Qingyun Sun, Ziwei Zhang, Xingcheng Fu et al.· Proceedings of the 32nd ACM...· 0 citations
Visual retrieval-augmented generation (RAG) commonly expands the retrieved evidence set to improve answer-page coverage, implicitly assuming that all available evidence should be passed to the generator. We show that this assumption does not hold for diffusion language models (DLMs): retrieving more pages increases answer-page recall, whereas unconditionally passing all retrieved pages to the generator often reduces answer accuracy, primarily because of semantic conflict. A latent-source analysis explains this mismatch through source-coherence loss in parallel denoising, where position-wise proposals can combine incompatible visual sources into unsupported answers. We further find that such interference is already visible in the first-step answer-block distribution, making it possible to assess evidence before decoding. To preserve retrieval coverage while limiting harmful visual exposure, we propose the Entropy-Based Candidate Filter (ECF), a training-free evidence-admission framework. To reduce irrelevant content within individual candidates, ECF constructs multi-granularity evidence units; to identify beneficial additional evidence, it uses blank-controlled block confidence and retrieval rank to determine whether and which candidate should enter the final context. Across three multimodal DLMs and five visual QA benchmarks, ECF improves answer accuracy by 2.62 percentage points on average over the strongest fixed top-$k$ input and, with LLaDA2.0-Uni, by 2.37 percentage points on average over the best competing training-free result for each dataset. These results show that broader retrieval benefits visual DLM-RAG through selective evidence admission rather than unconditional evidence expansion. Code is publicly available at https://github.com/wjkuser/ECF.
Jiankun Wang, Yi-Sen Gao, Ziwei Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
