← Search

Hai Lin

15 accepted papers

2026

FUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and Generation

AAAI 2026technical

Recent unified models have demonstrated that the reasoning capacity of Multimodal Large Language Models (MLLMs) can be leveraged to facilitate diffusion-based image generation with impressive flexibility and performance. However, approaches that rely heavily on MLLMs for high-level semantic encoding

Cited by 0SourcePDFScholar
2026

Token-Importance Guided Direct Preference Optimization

ICLR 2026oral

Aligning Large Language Models (LLMs) with human preferences is crucial for safe and effective AI interactions. While popular methods like Direct Preference Optimization (DPO) have simplified alignment, they remain sensitive to data noise and overlook the differential importance of individual tokens…

Cited by 0SourcecodeScholar
2025

Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models

CVPR 2025poster

We explore Generalizable Tumor Segmentation, aiming to train a single model for zero-shot tumor segmentation across diverse anatomical regions. Existing methods face limitations related to segmentation quality, scalability, and the range of applicable imaging modalities. In this paper, we uncover th…

2025

Efficient Visual Storytelling through Descriptive Words Distillation and Dynamic Decoding

ICASSP 2025accepted

Visual storytelling, a complex task in natural language generation, aims to create coherent and engaging narratives from a sequence of images, requiring more intricate and lengthy descriptions than typical image captioning. Current methods generally employ sophisticated modal interaction modules and…

Cited by 0SourceScholar
2025

Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers

AAAI 2025technical

Large language models (LLMs) have demonstrated remarkable performance in multimodal tasks even with frozen LLM Block and only a few trainable parameters. However, the underlying mechanisms of how LLMs enhance multimodal performance remains unclear. In this work, we focus on the phenomenon that ``Mer…

Cited by 0SourcePDFScholar
2025

SIGraph: Saliency Image-Graph Network for Retinal Disease Classification in Fundus Image

AAAI 2025technical

An efficient and precise diagnosis of retinal diseases is a fundamental goal for auxiliary diagnostic systems in ophthalmology. Inspired by the importance of scattered subtle lesions in manual retinal disease diagnosis, recent research has achieved state-of-the-art performance by mining information…

Cited by 0SourcePDFScholar
2024

AAT: Adapting Audio Transformer for Various Acoustics Recognition Tasks

ICASSP 2024accepted

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality——It fine-tunes easily to down-stream tasks and shows more robust p…

Cited by 0SourceScholar
2024

OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models

NAACL 2024findings

Object navigation (ObjectNav) requires an agent to navigate through unseen environments to find queried objects. Many previous methods attempted to solve this task by relying on supervised or reinforcement learning, where they are trained on limited household datasets with close-set objects. However…

2022

Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics

ICRA 2022poster

Seemingly in defiance of basic physics, cats consistently land on their feet after falling. In this paper, we design a controller that lands the Mini Cheetah quadruped robot on its feet as well. Specifically, we explore how trajectory optimization and machine learning can work together to enable hig…

Cited by 45SourceScholar
2022

SatFormer: Saliency-Guided Abnormality-Aware Transformer for Retinal Disease Classification in Fundus Image

IJCAI 2022poster

Automatic and accurate retinal disease diagnosis is critical to guide proper therapy and prevent potential vision loss. Previous works simply exploit the most discriminative features while ignoring the pathological visual clues of scattered subtle lesions. Therefore, without a comprehensive understa…

Cited by 11SourcePDFScholar