Tao Lin

Unified Continuous Generative Models for Denoising-based Diffusion

APEX: One-Step High-Resolution Image Synthesis

Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems

Safeguarding Visual Privacy in Dataset Distillation: Robust Initialization via Augmentation

Don't Just Fine-tune the Agent, Tune the Environment

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration

Generative Modeling with Explicit Memory

Beyond Model-Centric: Collaborative Data Optimization for Reusing and Sharing

Efficient Generative Model Training via Embedded Representation Warmup

IOMM: Fast Pre-training of Unified Multimodal Models without Text-Image Pairs

Toward Editable Vector Graphics: Layered SVG Synthesis from Multimodal Prompts

Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty

Atomos: Hierarchical Reasoning From Atomic Steps

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

ELICIT: LLM Augmentation Via External In-context Capability

Structured-Initialization Learning

GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost

CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic

Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Switch EMA: A Free Lunch for Better Flatness and Sharpness

MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration

Equally Critical: Samples, Targets, and Their Mappings in Datasets

Privacy as a Free Lunch: Crafting Initial Distilled Datasets through the Kaleidoscope

Cognitive Insights and Stable Coalition Matching for Fostering Multi-Agent Cooperation

Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing

Improving Group Connectivity for Generalization of Federated Deep Learning

Collaborative Data Optimization

Co-Evolution Learning

Data-Evolution Learning