Liang Lin

29

Papers

129

Total Citations

Papers (29)

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis

Cross-modal Causal Relation Alignment for Video Question Grounding

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach

PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention

Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation

Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference

Sim-DETR: Unlock DETR for Temporal Sentence Grounding

Stripe Observation Guided Inference Cost-free Attention Mechanism

SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks

Monitoring Primitive Interactions During the Training of DNNs

FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System

Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios

Reproducible Vision-Language Models Meet Concepts Out of Pre-Training

Kepler codebook

VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction

No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition

DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh

DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering

Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method

Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering

RoboPearls: Editable Video Simulation for Robot Manipulation

Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions

RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy