Related papers: The Double Dilemma in Multi-Task Radiology Report …
Retrieval-Augmented Generation (RAG) systems are widely adopted in knowledge-intensive NLP tasks, but current evaluations often overlook the structural complexity and multi-step reasoning required in real-world scenarios. These benchmarks…
Scene graph generation (SGG) has gained tremendous progress in recent years. However, its underlying long-tailed distribution of predicate classes is a challenging problem. For extremely unbalanced predicate distributions, existing…
Radiology Report Generation (RRG) draws attention as a vision-and-language interaction of biomedical fields. Previous works inherited the ideology of traditional language generation tasks, aiming to generate paragraphs with high readability…
Accurate segmentation of cell nuclei in histopathology images is essential for numerous biomedical research and clinical applications. However, existing cell nucleus segmentation methods only consider a single dataset (i.e., primary…
The multi-grid reaction-diffusion master equation (mgRDME) provides a generalization of stochastic compartment-based reaction-diffusion modelling described by the standard reaction-diffusion master equation (RDME). By enabling different…
Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history. However,…
Reinforcement learning fine-tuning has become the dominant approach for aligning diffusion models with human preferences. However, assessing images is intrinsically a multi-dimensional task, and multiple evaluation criteria need to be…
Radiology report generation (RRG) aims to automatically generate free-text descriptions from clinical radiographs, e.g., chest X-Ray images. RRG plays an essential role in promoting clinical automation and presents significant help to…
The rapid adoption of synthetic data for training Large Language Models (LLMs) has introduced the technical challenge of "model collapse"-a degenerative process where recursive training on model-generated content leads to a contraction of…
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more…
Multi-behavior sequential recommendation aims to capture users' dynamic interests by modeling diverse types of user interactions over time. Although several studies have explored this setting, the recommendation performance remains…
Medical image segmentation plays a crucial role in computer-aided diagnosis. However, existing methods heavily rely on fully supervised training, which requires a large amount of labeled data with time-consuming pixel-wise annotations.…
There are many challenges in bimanual assembly, including high-level sequencing, multi-robot coordination, and low-level, contact-rich operations such as component mating. Task and motion planning (TAMP) methods, while effective in this…
Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implicit regularization…
Planning for sequential robotics tasks often requires integrated symbolic and geometric reasoning. TAMP algorithms typically solve these problems by performing a tree search over high-level task sequences while checking for kinematic and…
Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature. Functionally, SLAM is an operation that transforms raw sensor…
Knowledge Graph (KG) plays a crucial role in Medical Report Generation (MRG) because it reveals the relations among diseases and thus can be utilized to guide the generation process. However, constructing a comprehensive KG is…
Recent advances in deep learning have enabled researchers to explore tasks at the intersection of computer vision and natural language processing, such as image captioning, visual question answering, visual dialogue, and visual language…
Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or retrieval-augmented pipelines achieve progress in fluency but remain…
The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE)…