Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks79 from public data
- 668
- OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation628
OPERA is presented, a novel MLLM decoding method grounded in an Over-trust Penalty and a Retrospection-Allocation strategy, serving as a nearly free lunch to alleviate the hallucination issue without additional data, knowledge, or training.
- InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model397
Experimental results demonstrate the superiority of InternLM-XComposer2 based on InternLM2-7B in producing high-quality long-text multi-modal content and its exceptional vision-language understanding performance across various benchmarks, where it not only significantly outperforms existing multimodal models but also matches or even surpasses GPT-4V and Gemini Pro in certain assessments.
- Dense Distinct Query for End-to-End Object Detection335
Dense Distinct Queries (DDQ) blends the advantages of traditional and recent end-to-end detectors and significantly improves the performance of various detectors including FCN, R-CNN, and DETRs.
- InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output216
A versatile large-vision language model that supports long-contextual input and output, InternLM-XComposer-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend.
- 175
- Deep-learning-based in-field citrus fruit detection and tracking125
A deep-learning-based orange counting algorithm using video sequences to help overcome inconsistent fruit detection accuracy and double-counting of the same fruit.
- Towards Natural Language-Based Visualization Authoring106
This paper introduces a structured representation of users' visualization editing intents, called editing actions, based on a formative study and an extensive survey on visualization construction tools, and implements a deep learning-based NL interpreter to translate NL utterances into editing actions.
- V3Det: Vast Vocabulary Visual Detection Dataset104
V3Det, a vast vocabulary visual detection dataset with precisely annotated bounding boxes on massive images, has the potential to serve as a cornerstone dataset for developing more general visual perception systems.
- Self-Supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences75
This work proposes a Partial Spatio-Temporal Learning (PSTL) framework to exploit the local relationship from a partial skeleton sequences built by a unique spatio-temporal masking strategy, and achieves state-of-the-art performance on NTURGB+D 60, NTUR GB+D 120 and PKU-MMD under various downstream tasks.
- VideoRoPE: What Makes for Good Video Rotary Position Embedding?71
VideoRoPE is introduced, with a 3D structure designed to preserve spatio-temporal relationships, which consistently surpasses previous RoPE variants, across diverse downstream tasks such as long video retrieval, video understanding, and video hallucination.
- DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition71
A new framework for skeleton-based action recognition, namely Dynamic Group Spatio-Temporal GCN (DG-STGCN), which consists of two modules, DG-GCN and DG-TCN, respectively, for spatial and temporal modeling.
- Easy domain adaptation method for filling the species gap in deep learning-based fruit detection45
A domain adaptation method that can transfer an existing model trained from one domain to a new domain without extra manual labeling is proposed and shows that the proposed method can potentially fill the species gap in deep learning-based fruit detection.
- Tag-informed collaborative topic modeling for cross domain recommendations38
A TagCDCTR (Tag-informed Cross Domain Collaborative Topic Regression) model, which exploits shared tags as bridges to link related domains through an extended collaborative topic modeling framework, and outperforms state-of-the-art collaborative-topic-based models and cross-domain- based models.
- 30
- BUOL: A Bottom-Up Framework with Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image27
BUOL, a Bottom-Up framework with Occupancy-aware Lifting to address the two issues for panoptic 3D scene reconstruction from a single image of instance-channel ambiguity and voxel-reconstruction ambiguity is proposed.
- Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate22
This paper presents the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs), and proposes evaluating the pre-training quality from the inter-modal distribution distance perspective.
- A survey on emotional visualization and visual analysis19
A survey of 75 approaches of emotional visualization from four different categories: data source type, emotional computing, visual coding and visualization and visual analysis tasks, and 15 subcategories, including visual works mentioned in published paper and interactive visual works published on the Internet is discussed.
- 18
- SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition16
SongComposer is a music-specialized large language model (LLM) that integrates the capability of simultaneously composing lyrics and melodies into LLMs by leveraging three key innovations: a flexible tuple format for word-level alignment of lyrics and melodies, an extended tokenizer vocabulary for song notes, and a multi-stage pipeline that captures musical structure.
- ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing14
ScaleCap is presented, an inference-time scalable image captioning strategy that generates comprehensive and detailed image captions that continuously enriches and calibrates the caption with increased inference budget and employs sentence-level offline contrastive decoding to effectively identify and eliminate hallucinations caused by linguistic biases.
- Adaptive Adjacent Layer Feature Fusion for Object Detection in Remote Sensing Images13
The proposed AALFF method incorporates an adjacent layer feature fusion enhancement (ALFFE) module, designed to capture high-level semantic information and accurately locate object spatial positions, which achieves mean average precision values of 77.1%, 88.9%, and 95.7% on the DIOR, HRRSD, and NWPU VHR-10 datasets, respectively.
- 13
- SS-GEN: A Social Story Generation Framework with Large Language Models11
This work develops a constraint-driven sophisticated strategy named StarSow to hierarchically prompt LLMs to generate Social Stories at scale, followed by rigorous human filtering to build a high-quality dataset, and introduces quality assessment criteria to evaluate the effectiveness of these generated stories.
- SPARK: Synergistic Policy And Reward Co-Evolving Framework10
The Synergistic Policy And Reward Co-Evolving Framework (SPARK), an efficient, on-policy, and stable method that builds on RLVR, is introduced, an efficient, on-policy, and stable method that eliminates the need for a separate reward model and costly human preference data.
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 2026-10-16. 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.