14 papers
CARE: Confidence-Aware Reasoning for Reliable Medical VQA
Yuetian Du, Yucheng Wang, Zhenyuan Chen +9
Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering, yet these mo…
HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference
Hui Dong, Yanzhao Li, Jie Gao +5
We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintainin…
Training-free sparse attention based on cumulative energy filtering
Chunlu Li, Yixuan Pan, Bai Du +5
Sparse attention accelerates Diffusion Transformers (DiTs) for video generation by computing only the important tokens while skipping the rest. The token selection strategy is key…
SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs
Bo Gu, Zhikang Zhang, Zizhuang Wei +3
Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered repres…
EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation Track
Zhenyuan Chen, Guanyuan Shen, Feng Zhang
Cross-modal image-to-image translation among Electro-Optical (EO), Infrared (IR), and Synthetic Aperture Radar (SAR) sensors is essential for comprehensive multi-modal aerial-view…
RSEdit: Text-Guided Image Editing for Remote Sensing
Chen Zhenyuan, Zhang Zechuan, Zhang Feng
In this paper, we explore text-guided image editing in the remote sensing domain using generative modeling. We propose \rsedit, a collection of models from U-Net to DiT with variou…
Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Models
Kwun Sy Lee, Jiawei Chen, Fuk Sheng Ford Chung +3
Reliable in silico molecular toxicity prediction is a cornerstone of modern drug discovery, offering a scalable alternative to experimental screening. However, the black-box nature…
Are Image-to-Video Models Good Zero-Shot Image Editors?
Zechuan Zhang, Zhenyuan Chen, Zongxin Yang +1
Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Ed…
RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
Zhenyuan Chen, Chenxi Wang, Ningyu Zhang +1
Remote sensing is critical for disaster monitoring, yet existing datasets lack temporal image pairs and detailed textual annotations. While single-snapshot imagery dominates curren…
NeuralDB: Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database
Weizhi Fei, Hao Shi, Jing Xu +7
Efficiently editing knowledge stored in large language models (LLMs) enables model updates without large-scale training. One possible solution is Locate-and-Edit (L\&E), allowing s…
Rethinking Inductive Bias in Geographically Neural Network Weighted Regression
Zhenyuan Chen
Inductive bias is a key factor in spatial regression models, determining how well a model can learn from limited data and capture spatial patterns. This work revisits the inductive…
Agent-based Video Trimming
Lingfeng Yang, Zhenyuan Chen, Xiang Li +3
As information becomes more accessible, user-generated videos are increasing in length, placing a burden on viewers to sift through vast content for valuable insights. This trend u…
Revisiting Prompt Pretraining of Vision-Language Models
Zhenyuan Chen, Lingfeng Yang, Shuo Chen +3
Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recentl…
HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes
Changfeng Feng, Zhenyuan Chen, Xiang Li +5
Object detection from aerial platforms under adverse atmospheric conditions, particularly haze, is paramount for robust drone autonomy. Yet, this domain remains largely underexplor…