← Search

Jianyu Qi

2 accepted papers

2026

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View

AAAI 2026technical

Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms based on reinforcement learning (RL), focusing predominantly

Cited by 0SourcePDFScholar
2025

AIDC: Benchmark for Analytical Learning in Incremental Disease Classification

ICASSP 2025accepted

Class Incremental Learning (CIL) aims to enable models to continuously learn new categories while retaining previous classification abilities. In medical scenarios, where new disease categories frequently emerge, CIL becomes crucial. Traditional CIL approaches often face "catastrophic forgetting". A…

Cited by 0SourceScholar