Yang Li

38

Papers

381

Total Citations

Papers (38)

On Scaling Up a Multilingual Vision and Language Model

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

Active Evaluation Acquisition for Efficient LLM Benchmarking

An Efficient Knowledge Transfer Strategy for Spiking Neural Networks from Static to Event Domain

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings

H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfer

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring

Population Aware Diffusion for Time Series Generation

One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis

GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors

Perceptual Group Tokenizer: Building Perception with Iterative Grouping

GLOMA: Global Video Text Spotting with Morphological Association

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning

EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision

Motion-Zero: A Zero-Shot Trajectory Control Framework of Moving Object for Diffusion-Based Video Generation

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion

Open Ad Hoc Teamwork with Cooperative Game Theory

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning

Rich Human Feedback for Text-to-Image Generation

Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios

Enhancing Implicit Shape Generators Using Topological Regularizations

ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation

Language Models as Semantic Indexers

Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoising

LiON: Learning Point-Wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data

Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models

Enhancing Sequential Recommendation with Global Diffusion

pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

Phoneme Hallucinator: One-Shot Voice Conversion via Set Expansion

Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation

Multi-Prototype Space Learning for Commonsense-Based Scene Graph Generation

A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction