Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks37 from public data
- Neural Style Transfer: A Review895
A taxonomy of current algorithms in the field of NST is proposed and several evaluation methods are presented and compared to compare different NST algorithms both qualitatively and quantitatively.
- Dynamic Instance Normalization for Arbitrary Style Transfer222
The proposed Dynamic Instance Normalization (DIN) provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.
- Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields124
This paper presents a stroke controllable style transfer network that incorporates different stroke sizes into one single model and demonstrates that with almost the same number of parameters as the previous Fast Style Transfer algorithm, this network can transfer an artistic style in a stroke controlled manner.
- 123
- 108
- 70
- Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks55
This work proposes two evaluation metrics, termed as "consistency score" and "stability score", to evaluate the explanation consistency across images and the explanation robustness against perturbations, respectively, both of which are essential for explanations taken into practice.
- 52
- Deep Graph Reprogramming50
A novel model reusing task tailored for graph neural networks (GNNs) is explored, termed as “deep graph reprogramming”, which aims to reprogram a pretrained GNN, without amending raw node features nor model parameters, to handle a bunch of cross-level downstream tasks in various domains.
- 50
- Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks48
Two dedicated forms of meta neighborhood aggregators are proposed, an exclusive meta aggregator termed as Greedy Gumbel Neighborhood Aggregator (GNA), and a diffused meta aggregators termed as Adaptable Hybrid Neighborhood AggRegator (ANA), which learn to exclusively pick one single optimal aggregator from a pool of candidates.
- 39
- Interpretable Partitioned Embedding for Customized Multi-item Fashion Outfit Composition35
A partitioned embedding network to learn interpretable embeddings from clothing items and outfits recommended by the model are more desirable in comparison with the existing methods are demonstrated.
- 33
- Benchmarking Reasoning Robustness in Large Language Models30
A novel benchmark is introduced, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps, achieved by an instruction-based approach to generate diverse datasets that closely resemble training distributions, facilitating a holistic robustness assessment and advancing the development of more robust reasoning frameworks.
- 29
- Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG28
Retrieval-Augmented Perception is proposed, a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout and dynamically selects the optimal number of crops based on model confidence and retrieval scores.
- 27
- Segment Anything in Non-Euclidean Domains: Challenges and Opportunities22
This paper explores a novel Segment Non-Euclidean Anything (SNA) paradigm that strives to develop foundation models that can handle the diverse range of graph data within the non-E Euclidean domain, seeking to expand the scope of SA and lay the groundwork for future research in this direction.
- Interpretable Partitioned Embedding for Intelligent Multi-item Fashion Outfit Composition19
A partitioned embedding network to learn interpretable embeddings from clothing items and outfits recommended by the model are more desirable in comparison with the existing methods are demonstrated.
- 14
- 13
- Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning11
KG-RAR is proposed, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model (PRP-RM) that refines retrieved information and evaluates each reasoning step.
- ClusIR: Towards Cluster-Guided All-in-One Image Restoration6
ClusIR is proposed, a Cluster-Guided Image Restoration framework that explicitly models degradation semantics through learnable clustering and propagates cluster-aware cues across spatial and frequency domains for adaptive restoration.
- Towards Deeper Insights into Deep Learning from Imbalanced Data5
It is found that imbalanced data is a neither sufficient nor necessary condition for im balanced performance in deep neural networks, and another important factor for imbalanced performance is the distance between the majority class instances and the decision boundary.
- MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation3
This paper proposes MedCoG, a Medical Meta-Cognition Agent with Knowledge Graph, where the meta-cognitive assessments of task complexity, familiarity, and knowledge density dynamically regulate utilization of procedural, episodic, and factual knowledge.
- 3
- 3
- 3
- Disentangled Representation Learning via Flow Matching2
This work proposes a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space and introduces a non-overlap (orthogonality) regularizer that suppresses cross-factor interference and reduces information leakage between factors.
- 2
- CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction1
A novel model-free decoding strategy in the conformal prediction framework that simultaneously maintains a compact search space and ensures high coverage probability over desirable trajectories is proposed.
- 1
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.