Related papers: Revisiting DRUP-based Interpolants with CaDiCaL 2.…
Due to the presence of metallic implants, the imaging quality of computed tomography (CT) would be heavily degraded. With the rapid development of deep learning, several network models have been proposed for metal artifact reduction (MAR).…
Masked image modeling (MIM) has become a prevalent pre-training setup for vision foundation models and attains promising performance. Despite its success, existing MIM methods discard the decoder network during downstream applications,…
Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial optimization problems (COPs). The learning-to-rank techniques have been studied in the field of information retrieval. While several COPs can be…
Audio-Visual Speaker Detection (AVSD) hinges on modeling both individual temporal continuity and inter-personal social context. Existing coupled architectures struggle to reconcile these tasks in shared representation spaces due to…
We present the design and implementation of a RAG-based AI system benchmarking (RAGPerf) framework for characterizing the system behaviors of RAG pipelines. To facilitate detailed profiling and fine-grained performance analysis, RAGPerf…
OneAPI is an open standard that supports cross-architecture software development with minimal effort from developers. It brings DPC++ and C++ compilers which need to be thoroughly tested to verify their correctness, reliability, and…
Adversarial training significantly improves adversarial robustness, but superior performance is primarily attained with large models. This substantial performance gap for smaller models has spurred active research into adversarial…
In the present study we demonstrate for the first time how Astigmatism Particle Tracking Velocimetry (APTV) can be utilized to measure suspensions dynamics. Measurements were successfully performed in monodisperse, refractive index matched…
Diffusion- and flow-based models have emerged as state-of-the-art generative modeling approaches, but they require many sampling steps. Consistency models can distill these models into efficient one-step generators; however, unlike flow-…
Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this paradigm and was…
Complex Verilog Design Problems (CVDP) challenge hardware LLM agents because solving them requires localizing verifier-relevant RTL, testbenches, include paths, and build dependencies inside large repository snapshots, making precise edits,…
As blockchain technology continues to evolve and mature, smart contracts have become a key driving force behind the digitization and automation of transactions. Smart contracts greatly simplify and refine the traditional business…
Deploying a deep learning model on mobile/IoT devices is a challenging task. The difficulty lies in the trade-off between computation speed and accuracy. A complex deep learning model with high accuracy runs slowly on resource-limited…
Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to…
Offline Reinforcement Learning (RL) relies on policy constraints to mitigate extrapolation error, where both the constraint form and constraint strength critically shape performance. However, most existing methods commit to a single…
Recent works in cross-modal understanding and generation, notably through models like CLAP (Contrastive Language-Audio Pretraining) and CAVP (Contrastive Audio-Visual Pretraining), have significantly enhanced the alignment of text, video,…
The burgeoning field of camouflaged object detection (COD) seeks to identify objects that blend into their surroundings. Despite the impressive performance of recent models, we have identified a limitation in their robustness, where…
The past three decades have witnessed notable success in designing efficient SAT solvers, with modern solvers capable of solving industrial benchmarks containing millions of variables in just a few seconds. The success of modern SAT solvers…
We develop an all-in-one computer vision toolbox named EasyCV to facilitate the use of various SOTA computer vision methods. Recently, we add YOLOX-PAI, an improved version of YOLOX, into EasyCV. We conduct ablation studies to investigate…
Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts…