Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks31 from public data
- T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation298
This work presents T2I-CompBench++, an enhanced benchmark for compositional text-to-image generation, and proposes enhanced evaluation metrics designed to assess these diverse compositional challenges.
- T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation212
It is found that compositional text-to-video generation is highly challenging for current models, and it is hoped the first systematic study on compositional text-to-video generation could shed light on future research in this direction.
- Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval177
Considering the enormous computational overhead of incorporating all historical context, the Memory Retrieval module is proposed to select truly relevant context frames by determining FOV overlap between camera poses, which significantly reduces the number of candidate frames without substantial information loss.
- Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association152
This paper proposes to exploit natural language description as additional training supervisions for effective visual features for person re-identification and achieves state-of-the-art performance without utilizing any auxiliary information during testing and shows better performance than other joint embedding methods for the image-language association.
- Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data147
This work proposes an image captioning framework with a self-retrieval module as training guidance, which encourages generating discriminative captions and demonstrates the effectiveness of the proposed retrieval-guided method on COCO and Flickr30k captioning datasets, and shows its superior captioning performance with more discriminating captions.
- A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook142
This article introduces seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks, and delves into the potential future directions behind the emergence of reasoning abilities within foundation models.
- HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting127
An efficient yet effective framework that generates high-quality 3D humans with fine-grained geometry and realistic appearance, based on the insight that 3D Gaussian Splatting is an efficient renderer with peri-odic Gaussian shrinkage or growing, where such adaptive density control can be naturally guided by intrinsic human structures.
- EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning79
EgoPlan-Bench is introduced, a comprehensive benchmark to evaluate the planning abilities of MLLMs in real-world scenarios from an egocentric perspective, mirroring human perception, and EgoPlan-IT, a specialized instruction-tuning dataset that effectively enhances model performance on EgoPlan-Bench.
- OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion69
OmniPart is introduced, a novel framework for part-aware 3D object generation designed to achieve high semantic decoupling among components while maintaining robust structural cohesion.
- Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding69
A training-free probabilistic parallel decoding algorithm, Speculative Jacobi Decoding (SJD), is proposed, to accelerate auto-regressive text-to-image generation and facilitates the model to predict multiple tokens at each step and accepts tokens based on the probabilistic criterion, enabling the model to generate images with fewer steps than the conventional next-token-prediction paradigm.
- MBQ: Modality-Balanced Quantization for Large Vision-Language Models51
Modality-Balanced Quantization (MBQ), a simple yet effective method that incorporates the different sensitivities across modalities during the calibration process to minimize the reconstruction loss for better quantization parameters for large VLMs.
- World Guidance: World Modeling in Condition Space for Action Generation44
WoG (World Guidance), a framework that maps future observations into compact conditions by injecting them into the action inference pipeline, and demonstrates that modeling and predicting this condition space not only facilitates fine-grained action generation but also exhibits superior generalization capabilities.
- Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions42
This work proposes a novel algorithm, named Open-Edit, which is the first attempt on open-domain image manipulation with open-vocabulary instructions, which takes advantage of the unified visual-semantic embedding space pretrained on a general image-caption dataset, and manipulates the embedded visual features by applying text-guided vector arithmetic on the image feature maps.
- Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation32
This work introduces a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism that efficiently model the resulting large token space.
- Learning Transferable Spatiotemporal Representations from Natural Script Knowledge9
A new pre-text task, Turning to Video for Transcript Sorting (TVTS), which sorts shuffled ASR scripts by attending to learned video representations, and demonstrates strong out-of-the-box spatiotemporal representations on diverse benchmarks, e.g., +13.6% gains over VideoMAE on SSV2 via linear probing.
- CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation8
The key innovation is a novel context conditioning mechanism that injects 3D-aware features in an implicit way into a pretrained text-to-video generation model by additional context concatenation, enabling camera-controlled video synthesis with consistent scenes and dynamic subjects.
- 8
- GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing7
Generation Chain-of-Thought (GoT) is presented, a novel paradigm that em-powers a Multimodal Large Language Model (MLLM) to first generate an explicit, structured reasoning chain in natural language—detailing semantic relationships.
- A cutting-edge deep learning-and-radiomics-based ultrasound nomogram for precise prediction of axillary lymph node metastasis in breast cancer patients ≥ 75 years7
The DL and radiomics-based model exhibited remarkable accuracy and reliability in predicting ALN status among breast cancer patients ≥ 75 years, thereby contributing to the enhancement of personalized treatment strategies’ efficacy and improvement of patients’ quality of life.
- 5
- 4
- Adaptive 1D Video Diffusion Autoencoder3
This work proposes One-Dimensional Diffusion Video Autoencoder (One-DVA), a transformer-based framework for adaptive 1D encoding and diffusion-based decoding that supports adaptive compression and thus can achieve higher compression ratios.
- DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation2
Experimental results demonstrate that DreamComposer++ seamlessly integrates with cutting-edge view-aware diffusion models and enhances their abilities to generate controllable novel views from multi-view conditions, facilitates controllable 3D object reconstruction and enables a wide range of applications.
- 1
- 1
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; 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.