Yanfeng Wang

Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling

Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning

Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs

MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Users

Selecting Auxiliary Data via Neural Tangent Kernels for Low-Resource Domains

MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection

Fine-tuning with Reserved Majority for Noise Reduction

Universal Video Temporal Grounding with Generative Multi-modal Large Language Models

Learning to Instruct for Visual Instruction Tuning

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

ConText: Driving In-context Learning for Text Removal and Segmentation

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation

Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models

MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

G4Seg: Generation for Online Segmentation Refinement with Diffusion Models

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal

Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation

Protecting Minorities in Diffusion Models via Capacity Allocation