Jin Wang

18

Papers

28

Total Citations

Papers (18)

Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models

MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer

Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent Detection

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

Vision-aware Multimodal Prompt Tuning for Uploadable Multi-source Few-shot Domain Adaptation

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

Data-Free Black-Box Federated Learning via Zeroth-Order Gradient Estimation

Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations

Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective

Personalized LoRA for Human-Centered Text Understanding

Event-assisted Low-Light Video Object Segmentation

Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation

Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

ISP2HRNet: Learning to Reconstruct High Resolution Image from Irregularly Sampled Pixels via Hierarchical Gradient Learning

INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception

Event-Enhanced Blurry Video Super-Resolution

Sample-aware Adaptive Structured Pruning for Large Language Models