Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks42 from public data
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models1,936
InternVL3 incorporates variable visual position encoding (V2PE) to support extended multimodal contexts, employs advanced post-training techniques such as supervised fine-tuning (SFT) and mixed preference optimization (MPO), and adopts test-time scaling strategies alongside an optimized training infrastructure.
- VideoLLM: Modeling Video Sequence with Large Language Models134
This work proposes a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence understanding and demonstrates that the understanding and Reasoning capabilities of LLMs can be effectively transferred to video understanding tasks.
- ViLT-CLIP: Video and Language Tuning CLIP with Multimodal Prompt Learning and Scenario-Guided Optimization64
Extensive validation of fully supervised, zero-shot, few-shot, base-to-novel generalization settings for video recognition indicates that the proposed approach achieves competitive performance with less commute cost.
- InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges62
In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and the champions of CVPR2022, demonstrating the powerful representation ability of Intern video as a video foundation model.
- Universal Segmentation at Arbitrary Granularity with Language Instruction47
Unified segmentation model UniLSeg is presented, a universal segmentation model that can perform segmentation at any semantic level with the guidance of language instructions, surpassing both specialist and unified segmentation models.
- 35
- RIFormer: Keep Your Vision Backbone Effective But Removing Token Mixer33
This paper develops an RepIdentityFormer base on the re-parameterizing idea, and explores the improved learning paradigm to break the limitation of simple token mixer free backbone, and summarizes the empirical practice into 5 guidelines.
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models31
This work extends each image into a "static" video and introduces a unified token compression strategy called Progressive Visual Token Compression (PVC), where the tokens of each frame are progressively encoded and adaptively compressed to supplement the information not extracted from previous frames.
- 19
- 18
- Will You Ever Become Popular? Learning to Predict Virality of Dance Clips18
A novel multi-modal framework that integrates skeletal, holistic appearance, facial and scenic cues is proposed for comprehensive dance virality prediction and it is shown that short video applications such as multi-dimensional recommendation and action feedback can be derived from this model.
- 17
- Chinese Character Inpainting with Contextual Semantic Constraints16
A semantics enhanced generative framework for Chinese character inpainting is proposed, where a global semantic supervising module (GSSM) is introduced to constrain contextual semantics and sentence embedding is used to guide the encoding of continuous contextual characters.
- 13
- 13
- ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding12
ELV-Halluc is introduced, the first benchmark dedicated to long-video hallucination, enabling a systematic investigation of Semantic Aggregation Hallucination (SAH), and it is demonstrated that positional encoding strategy contributes to alleviating SAH, and the model's ability to distinguish semantics within and across events is enhanced.
- LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation11
The proposed Linear Diffusion Transformer (LiT), which serves as a safe and efficient alternative baseline for DiT with pure linear attention, can be quickly adapted from DiT using only 20 % and 33 % of DiT's training steps, respectively, while achieving comparable performance.
- Collaborative Filtering Model of Graph Neural Network Based on Random Walk11
Results show that the proposed graph neural network recommendation method can improve the accuracy of recommendation results, tap the association information between users and items more effectively, and significantly alleviate the user cold-start problem.
- Improving SSVEP-BCI System Interaction Efficiency: Design Recommendations for Shape of Visual Stimuli and Number of Auxiliary Stimuli9
This research provides significant evidence for the design of visual stimulation for SSVEP-BCI systems, and provides new directions and ideas for the interface design of BCI systems, visual stimulation design, and application of advanced interaction technology.
- Adapting LLaMA Decoder to Vision Transformer6
The tailored model, dubbed as image LLaMA (iLLaMA), is akin to LLaMA in architecture and enables direct supervised learning, and boosts computational efficiency and learns complex representation by elevating attention map ranks.
- Passive vibration isolation of flexure jointed hexapod: A geometry design method6
A new design algorithm for geometry structure of the FJH and coefficients of the parallel spring-damping mechanism in struts is proposed and numerical simulation results are provided to demonstrate effectiveness of the proposed design algorithm.
- Dual-level graph contrastive collaborative filtering5
This work proposes an innovative dual-level graph contrastive collaborative filtering method (DL-GCL) that combines both graph and node-level views and employs a multi-task learning strategy to optimize local-global views and BPR (Bayesian Personalized Ranking) loss functions.
- 4
- 3
- LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model3
This paper proposes a Language Collaboration and Glyph Perception Model, termed LOGO, an innovative framework designed to enhance the performance of conventional text spotters, and designs a language synergy classifier (LSC) to explicitly discern text instances from background noise in the recognition stage.
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.