ANCHOR: Agentic Noise Creation Framework for Human Simulation and Denoising Recommendation

Distilling accurate user preferences from noisy implicit feedback remains a fundamental bottleneck in recommendation systems, highlighting the need for recommendation denoising. However, real-world data lack explicit noise annotations, forcing existing methods to rely on unsupervised side information or handcrafted heuristics. These approaches often incur high external costs, generalize poorly, or depend on unreliable priors, causing noise misidentification and corrupting true user preference representations. To address these limitations, we propose a paradigm-level reformulation of recommendation denoising. Instead of indirectly inferring noisy interactions through heuristics, our Creation-Recognition paradigm proactively creates labeled noisy interactions and trains a dedicated recognizer to identify them, transforming denoising from heuristic filtering into supervised learning. Based on this paradigm, we present ANCHOR, an agent-based framework inspired by recent LLM-as-User research. ANCHOR simulates user behaviors to generate realistic noise labels and enables supervised denoising through two stages: noise creation and noise recognition. In the noise creation stage, ANCHOR adopts a recommender-in-the-loop agentic architecture to synthesize both diverse out-of-preference noise and informative boundary-adjacent noise. For out-of-preference noise, it implements five extensible simulation mechanisms to approximate major sources of noisy implicit feedback. For boundary-adjacent noise, an adversarial boundary refinement mechanism generates ambiguous interactions that challenge the recognizer and target the decision boundary. In the noise recognition stage, ANCHOR leverages the generated labels to train a reusable parametric recognizer that integrates collaborative signals and semantic representations to detect noise patterns in real interaction data.

Scene-based Factored Attention for Image Captioning

Image captioning has attracted ever-increasing research attention in the multimedia community. To this end, most cutting-edge works rely on an encoder-decoder framework with attention mechanisms, which have achieved remarkable progress. However, such a framework does not consider scene concepts to attend visual information, which leads to sentence bias in caption generation and defects the performance correspondingly. We argue that such scene concepts capture higher-level visual semantics and serve as an important cue in describing images. In this paper, we propose a novel scene-based factored attention module for image captioning. Specifically, the proposed module first embeds the scene concepts into factored weights explicitly and attends the visual information extracted from the input image. Then, an adaptive LSTM is used to generate captions for specific scene types. Experimental results on Microsoft COCO benchmark show that the proposed scene-based attention module improves model performance a lot, which outperforms the state-of-the-art approaches under various evaluation metrics.