15 accepted papers
With the rapid advancement of generative models, high-fidelity AI-generated images have become increasingly indistinguishable from real images, posing significant challenges to traditional detection methods that rely on explicit artifacts or uniform feature learning. We hypothesize that detection am
Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than expected, thereby yielding both positive and negative signals for t
Recent progress in Multimodal Large Language Models (MLLMs) has enabled mobile GUI agents capable of visual perception, cross-modal reasoning, and interactive control. However, existing benchmarks are largely English-centric and fail to capture the linguistic and interaction characteristics of the C
Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging paradigm of proactive intelligence, where agents autonomously
4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world models and physical AI. However, maintaining long-chain consistency across both frames and viewpoints through the uniqu…
Large Reasoning Models (LRMs) have achieved impressive performance on challenging tasks, yet their deep reasoning often incurs substantial computational costs. To achieve efficient reasoning, existing reinforcement learning methods still struggle to construct short reasoning path during the rollout…
The advancements in large language models (LLMs) have propelled the improvement of video understanding tasks by incorporating LLMs with visual models. However, most existing LLM-based models (e.g., VideoLLaMA, VideoChat) are constrained to processing short-duration videos. Recent attempts to underst…
In the field of AI-driven human-GUI interaction automation, while rapid advances in multimodal large language models and reinforcement fine-tuning techniques have yielded remarkable progress, a fundamental challenge persists: their interaction logic significantly deviates from natural human-GUI comm…
Weakly supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent subtle feature differences between nodule and background regions and confused incorrect infor…
Recently, significant progress has been made in 2D human pose estimation. While some research has focused on enhancing the accuracy of keypoint detection, others have aimed at reducing model size. However, most models excel in either one aspect or the other, but rarely both simultaneously. In this p…
Prompt learning was proposed to solve the problem of inconsistency between the upstream and downstream tasks and has achieved State-Of-The-Art (SOTA) results in various Natural Language Processing (NLP) tasks. However, Relation Extraction (RE) is more complex than other text classification tasks, wh…
Root cause analysis is crucial for cloud-native systems. However, existing supervised approaches ignore the potential of unlabeled data, which is frequent in the cloud-native root cause analysis scenarios. Moreover, the class-imbalanced distribution of faults presents obstacles to applying semi-supe…
Existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. One promising technique to obtain an accurate yet lightweight pose estimator is knowledge distillation, which distills the pose knowledge from a powerful teacher model to a less-pa…
Researches using margin based comparison loss demonstrate the effectiveness of penalizing the distance between face feature and their corresponding class centers. Despite their popularity and excellent performance, they do not explicitly encourage the generic embedding learning for an open set recog…
Many successful systems for scene recognition transform low-level descriptors into complex representations. This process consists of the two steps: 1) feature coding, which performs a pointwise transformation of the descriptors into a representation adapted to the task, and 2) image pooling, which s…