Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks107 from public data
- DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes151
DeVRF, a novel representation to accelerate learning dynamic radiance fields via utilizing the 3D volumetric canonical space learnt from multi-view static images to ease the learning of 4D voxel deformation field with only few-view dynamic sequences is presented.
- HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation138
This work presents HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm through a novel heterogeneous low-rank adaptation technique and a tailored hierarchical visual perception approach.
- BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation138
A novel semi-supervised learning framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models and the experimental results verify the framework's effectiveness with a significant improvement over various state-of-the-art methods.
- VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM93
The VideoRefer Suite is introduced to empower Video LLM for finer-level spatial-temporal video understanding, i.e., enabling perception and reasoning on any objects throughout the video, and comprehensively assess the spatial-temporal understanding capability of a Video LLM.
- DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization72
It is argued that the computational cost brought by fine-tuning can be rather unnecessary, and a novel perspective to improving DMG without increasing computational cost is presented, i.e., device-specific parameter generation which directly maps data distribution to parameters.
- Consensus Graph Representation Learning for Better Grounded Image Captioning64
The Consensus Rraph Representation Learning framework (CGRL) is proposed for GIC that incorporates a consensus representation into the grounded captioning pipeline that can capture both the correct linguistic characteristics and visual relevance, and then grounding appropriate image regions further.
- 63
- Intelligent Model Update Strategy for Sequential Recommendation55
IntellectReq is a novel learning task, aimed at the detection of out-of-distribution data, thereby fine-tuning adaptive communication strategies and evidencing a marked improvement in the efficiency and generalizability of edge-cloud collaborative and dynamic recommendation systems.
- MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning52
This work proposes the Multimodal relAtional Graph adversarIal InferenCe (MAGIC) framework, a framework that can adaptively construct multiple multimodal relational graphs of images and model complex relationships among graphs to represent descriptive diversity and validate the effectiveness of MAGIC in generating diverse captions from different relational information items of an image.
- 50
- Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models41
A novel Gradient-RegulAted Meta-prompt learning (GRAM) framework that jointly meta-learns an efficient soft prompt initialization for better adaptation and a lightweight gradient regulating function for strong cross-domain generalizability in a meta-learning paradigm using only the unlabeled image-text pre-training data.
- Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels40
This work introduces a novel task, Partial labeling and Long-Tailed Multi-Label Classification (PLT-MLC), and proposes an end-to-end learning framework, COMIC, which significantly outperforms general MLC, LT-MLC and PL-MLC methods in terms of effectiveness and robustness on newly created PLT-MLC datasets.
- 39
- 37
- 36
- Deep Learning Model for Classifying Metastatic Epidural Spinal Cord Compression on MRI36
A DL model showed comparable agreement to a subspecialist radiologist and clinical specialists for the classification of malignant epidural spinal cord compression and could optimize earlier diagnosis and surgical referral.
- Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation35
The Device-Cloud LLM-SRM Collaborative Recommendation Framework (LSC4Rec) is designed under a device-cloud collaboration setting and aims to integrate the advantages of both LLMs and SRMs, as well as the benefits of cloud and edge computing, achieving a complementary synergy.
- HERO: HiErarchical spatio-tempoRal reasOning with Contrastive Action Correspondence for End-to-End Video Object Grounding35
This paper introduces the weakly-supervised contrastive learning that classifies the video as action-consistent and action-independent frames relying on the video-caption action semantic correspondence and designs the hierarchical reasoning layers to decouple fully connected multi-head attention and remove the redundant interfering correlations.
- 34
- 32
- EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model30
The Eyecare Kit is proposed, which systematically tackles three key challenges of intelligent ophthalmic diagnosis with the tailored dataset, benchmark and model, and develops the EyecareGPT, optimized for fine-grained ophthalmic visual understanding thoroughly.
- 30
- METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection30
METER is introduced, a novel dynamic concept adaptation framework that introduces a new paradigm for OAD that significantly outperforms existing OAD approaches in various application scenarios and employs a novel dynamic concept adaptation technique that leverages a hypernetwork to dynamically generate the parameter shift of the base detection model.
- Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding28
A variational cross-graph reasoning framework is proposed that explicitly decomposes video and language into hierarchical semantic graphs, respectively, and learns fine-grained semantic correspondence between the two graphs, and introduces a novel adaptive structured semantics learning approach to derive the structure-informed and domain-generalizable graph representations.
- 27
- 26
- Tell and guess: cooperative learning for natural image caption generation with hierarchical refined attention26
This paper designed the “Tell and Guess” Cooperative Learning model with a Hierarchical Refined Attention mechanism (CL-HRA) that bidirectionally improves the performance to generate more informative captions.
- 23
- HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models22
HyperLLaVA is introduced, which involves adaptive tuning of the projector and LLM parameters, in conjunction with a dynamic visual expert and language expert, respectively, derived from HyperNetworks, enabling dynamic projector and LLM modeling in two-stage training.
- 22
- Multi-modal Action Chain Abductive Reasoning17
The proposed model significantly outperforms existing video-language models in terms of effectiveness on the newly created MAR dataset and design a novel symbolic module that can complete strict derivation of the progressive action chain layer by layer.
- Deep Learning Model for Grading Metastatic Epidural Spinal Cord Compression on Staging CT17
Deep learning models for automatic MESCC classification on staging CT studies showed comparable to superior interobserver agreement to radiologists and could be used to aid earlier diagnosis.
- 17
- Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos17
A cross-modal consensus learning paradigm is introduced, which leverages the inherent semantic consensus between the aligned video and subtitle to achieve weakly-supervised learning on temporal emotion localization.
- 16
- Semantic Codebook Learning for Dynamic Recommendation Models16
The semantic metacode and semantic codebook, which stores disentangled item representations, ensures robust and accurate parameter generation and demonstrates that SOLID consistently outperforms existing DSR, delivering more accurate, stable, and robust recommendations.
- De-fine: De composing and Re fin ing Visual Programs with Auto-Feedback14
Inspired by benders decomposition, this work introduces De-fine, a training-free framework that automatically decomposes complex tasks into simpler subtasks and refines programs through auto-feedback, which can improve logical reasoning performance by integrating the strengths of multiple models.
- Diagnostic Accuracy of CT for Metastatic Epidural Spinal Cord Compression13
Dedicated radiologist review for MESCC on CT showed high interobserver agreement and sensitivity compared to the current standard of care, which is vital to expedite therapy and prevent paralysis.
- Mastering Collaborative Multi-Modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness12
A collaborative framework, DataTailor, is proposed, which leverages three key principles,formativeness, uniqueness, and representativeness, for effective data selection and achieves 101.3% of the performance of full-data fine-tuning with only 15% of the data, significantly reducing computational costs while maintaining superior results.
- Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales12
Fact is introduced, a novel paradigm designed to generate multimodal rationales that are faithful, concise, and transferable for teaching MLLMs and filter rationales that can be transferred to end-to-end paradigms from programming paradigms to guarantee transferability.
- Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT12
Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.
- Leveraging Invariant Principle for Heterophilic Graph Structure Distribution Shifts11
HEI is proposed, a framework capable of generating invariant node representations through incorporating Heterophily information, the node's estimated neighbor pattern, to infer latent Environments without augmentation, which are then used for Invariant prediction.
- 10
- Unsupervised Domain Adaptation for Video Object Grounding with Cascaded Debiasing Learning9
This paper addresses the Unsupervised Domain Adaptation (UDA) for the dense frame prediction task - Video Object Grounding and measures Grounding Coordinate Offset based on the semantic distance of the model's prediction across domains, based on which it alleviate source-domain bias in the target model through adversarial learning.
- A Novel 2-DOF Lorentz Force Actuator for the Modular Magnetic Suspension Platform9
A novel 2- (two degrees-of-freedom) DOF Lorentz force actuator is developed by designing the pose of the windings and permanent magnets (PMs) to achieve the integration of vertical driving force and horizontal driving force.
- Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining8
Iris is introduced, a foundational visual agent that addresses challenges in visual perception through two key innovations: Information-Sensitive Cropping (ISC) and Self-Refining Dual Learning (SRDL).
- Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration8
A universal on-device Multi-modal Model Adaptation framework is introduced, revolutionizing on-device model adaptation by striking a balance between efficiency and effectiveness, and represents a pioneering solution for on-Device Multi-modal Model Adaptation (DMMA).
- Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning6
A novel Dual Self-Consistency Reinforcement Learning optimization paradigm is introduced, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency in TikZ code.
- 6
- 6
- BOSS: Bottom-up Cross-modal Semantic Composition with Hybrid Counterfactual Training for Robust Content-based Image Retrieval6
A novel Bottom-up crOss-modal Semantic compoSition (BOSS) with Hybrid Counterfactual Training framework, which sheds new light on the CIR task by studying it from two previously overlooked perspectives.
- Photo Stream Question Answer6
This paper presents a new visual question answering (VQA) task -- Photo Stream QA, which aims to answer the open-ended questions about a narrative photo stream, and proposes an end-to-end baseline (E-TAA), which provides promising results outperforming all the other baseline methods.
- 5
- 5
- Insight into Tetrabromobisphenol A‐Associated Liver Transcriptional Landscape via Single Cell RNA Sequencing5
TBBPA-induced dysfunction of hepatocytes and endothelial cells may then activate and recruit other immune cells such as Kuffer cells, and T/NK cells into the liver, further increasing inflammatory response and liver injury, providing novel insight into undesiring environmental pollutant-induced liver injury.
- Weakly-supervised Disentanglement Network for Video Fingerspelling Detection5
This paper proposes the Weakly-supervised Disentanglement Network, namely WED, that requires no additional knowledge, and better exploits the video-sentence weak supervisions, contributing to the state-of-the-art performance for fingerspelling detection and recognition.
- Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with Benchmark4
RADAR, a robust two-stage Robust modAlity-instructive fusing & Detecting frAmewoRk, is proposed, which integrates a Modality-Incomplete Instruction mechanism-guiding the multimodal Transformer to focus more on available modal info, and a Double-Pseudo Hybrid Module to highlight unique modality combinations and reduce overfitting.
- 4
- 4
- 4
- Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning4
An innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i.e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL.
- Fast Simulation Method for Ocean Wave Base on Ocean Wave Spectrum and Improved Gerstner Model with GPU4
The experimental results show that the method is vivid and it conforms with randomness and complexity of ocean wave, it effectively improves the simulation speed of the wave and is satisfied with the real-time ability and fidelity in simulation system of ocean.
- 3
- LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation3
This paper introduces LASER, a tuning-free LLM-driven attention control framework that follows a progressive process: LLM planning, feature-attention injection, and stable animation generation, and proposes a Text-conditioned Image-to-Animation Benchmark to validate the effectiveness and efficacy of LASER.
- Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework3
This paper focuses on the efficient adaptation of EMLLMs to private domains, specifically in two areas: how to reduce data requirements, and how to avoid parameter fine-tuning.
- 3
- Identification of CXCL8 as a potential gene associated with lymph node metastasis in papillary thyroid carcinoma through bioinformatics analysis2
The data revealed a significantly elevated expression of CXCL8 in PTC tissues compared to Paired non-cancerous thyroid tissues(PNTs), with CXCL8 expression showing a strong positive correlation with lymph node metastasis, suggesting that CXCL8 may function as a key molecular contributor to lymph node metastasis in PTC.
- 2
- Fast Thinking for Large Language Models2
GainRouter is proposed, a lightweight routing mechanism that adaptively switches between fast codebook guided inference and slow explicit reasoning, thereby suppressing overthinking and reducing unnecessary token generation in large language models.
- Align2LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation2
A novel instruction curation algorithm, derived from two unique perspectives, human and LLM preference alignment, to compress this vast corpus of machine-generated multimodal instructions to a compact and high-quality form.
- Toward Cohort Intelligence: A Universal Cohort Representation Learning Framework for Electronic Health Record Analysis2
A universal COhort Representation lEarning (CORE) framework to augment EHR utilization by leveraging the fine-grained cohort information among patients, serving as a universal plug-in framework to infuse cohort information into healthcare methods for boosted performance.
- ART: rule bAsed futuRe-inference deducTion2
This work introduces rule b A sed futu R e-inference deduc T ion ( ART), which aims at de-ducing the correct future event based on the visual phenomenon and the rule-based premises, along with an explanation of the reasoning process.
- 2
- Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs1
The proposed MIND (Meta-cognitive INtegrated Dynamic Knowledge Editing), a framework that constructs a meta-knowledge memory for self-awareness, employs game-theoretic interactions to monitor knowledge activation, and incorporates label refinement for noise-robust updates, significantly outperforms existing cognitive editing approaches.
- 1
- Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing1
Persona is a novel personalized method using a prototype-based, backpropagation-free parameter editing framework to enhance model generalization without post-deployment retraining to tackle the generalization of lightweight on-device models.
- 1
- DuetRAG: Collaborative Retrieval-Augmented Generation1
This work proposes a novel Collaborative Retrieval-Augmented Generation framework, DuetRAG, to simultaneously integrate the domain fintuning and RAG models to improve the knowledge retrieval quality, thereby enhancing generation quality.
- 1
- MART: Learning Hierarchical Music Audio Representations with Part-Whole Transformer1
This work introduces MART, a hierarchical music representation learning approach that facilitates feature interactions among cropped music clips while considering their part-whole hierarchies, and proposes a hierarchical part-whole transformer to capture the structural relationships between music clips in a part-whole hierarchy.
- 1
- Denoising Multi-modal Sequential Recommenders with Contrastive Learning1
A weakly-supervised framework based on contrastive learning for denoising multi-modal recommenders (dubbed Demure) is proposed, which circumvents the requirement of users' explicit feedback and identifies the noises by analyzing the modalities of all interacted items from a given user.
- CAusal and collaborative proxy-tasKs lEarning for Semi-Supervised Domain Adaptation1
This paper proposes a collaboratively debiasing learning framework that utilizes two complementary semi-supervised learning (SSL) classifiers to mutually exchange their unbiased knowledge, which helps unleash the potential of source and target domain training data, thereby producing more convincing pseudo-labels.
- Modeling and Simulation Based on Improved Particle System1
In-depth study for particle system is taken, introducing the idea of genetic algorithm, made the improvement of traditional simulation model, and results show that the simulation of improved model is vivid under the complex environment, its real-time characteristics and fidelity is satisfied the requirements.
- Anti-Excessive Filtering Model Based on Sliding Window1
An improved model basing on the traditional sliding window model, combining with optimized rules on determining standard elevation value, tolerance of elevation difference and dynamic thresholds is proposed.
- The Intelligent Arithmetic of Scheme Design of NC Vertical Lathe Based on the Modularization1
The intelligent arithmetic model of the scheme design of NC vertical lathe in modularization is established and the order, the reasoning and the intelligent arithmetic of the selection and integration on the modules of the NC Vertical lathe are studied.
- 1
- –
- –
- –
- –
- –
- Effect of single-bundle autologous hamstring tendon reconstruction combined with braided thread on joint stability and clinical efficacy in patients with posterior cruciate ligament rupture–
The single-bundle reconstruction combined with braided thread has good clinical efficacy in patients with PCL rupture and more effectively improves the patient’s joint stability.
- –
- –
- –
- An Formation and Characteristic Analysis of Intangible Manpower Capital on the Sports Stars in China–
- –
- –
- Research on Environmental Influence Factors of Physical Exercise Adherence of Community Residents–
The main purpose is to find out the key factors which influence the physical exercise adherence of community residents in order to set up the theoretical foundation for the persist and health development of the physical Exercise adherence ofcommunity residents.
- –
- Research on Self-Influence Factors on Physical Exercise Adherence of Community Residents–
This paper analyzed self-influence factor from the demography, self-physiological condition and the self-mental condition in order to find out the main factors influencing the physical exercise adherence of community residents and laid the theoretical foundation for sustainable development of physical Exercise adherence ofcommunity residents.
- –
- –
- –
- –
- Network Economy and Network Shanghai–
The content of the Network Shanghai is studied, pointing out that network Shanghai is a rudiment of network society and the strategy of constructing the network is analyzed.
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 2026-10-12. 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.