Related papers: An Innovative Approach to Achieve Compositionality…
Object-centric learning aims to break down complex visual scenes into more manageable object representations, enhancing the understanding and reasoning abilities of machine learning systems toward the physical world. Recently, slot-based…
Computer vision applications such as visual relationship detection and human object interaction can be formulated as a composite (structured) set detection problem in which both the parts (subject, object, and predicate) and the sum…
Data fusion allows the elaboration and the evaluation of a situation synthesized from low level informations provided by different kinds of sensors. The fusion of the collected data will result in fewer and higher level informations more…
Smart contract (SC) platforms form blocks of transactions into a chain and execute them via user-defined smart contracts. In conventional platforms like Bitcoin and Ethereum, the transactions within a block are executed \emph{sequentially}…
Linear sequence modeling methods, such as linear attention, state space modeling, and linear RNNs, offer significant efficiency improvements by reducing the complexity of training and inference. However, these methods typically compress the…
Given the advances in reactive synthesis, it is a natural next step to consider more complex multi-process systems. Distributed synthesis, however, is not yet scalable. Compositional approaches can be a game changer. Here, the challenge is…
Symmetric tensor operations arise in a wide variety of computations. However, the benefits of exploiting symmetry in order to reduce storage and computation is in conflict with a desire to simplify memory access patterns. In this paper, we…
Multimodal classification is a core task in human-centric machine learning. We observe that information is highly complementary across modalities, thus unimodal information can be drastically sparsified prior to multimodal fusion without…
Multiparty session types are designed to abstractly capture the structure of communication protocols and verify behavioural properties. One important such property is progress, i.e., the absence of deadlock. Distributed algorithms often…
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost. In this paper, we present STTS, a token selection framework that dynamically selects a few…
Fast, byte-addressable non-volatile memory (NVM) embraces both near-DRAM latency and disk-like persistence, which has generated considerable interests to revolutionize system software stack and programming models. However, it is less…
The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application portability. Among the existing deep…
There is an ongoing effort to provide programming abstractions that ease the burden of exploiting multicore hardware. Many programming abstractions (e.g., concurrent objects, transactional memory, etc.) simplify matters, but still involve…
We introduce the DeTerministic Virtual Machine (DTVM) Stack, a next-generation smart contract execution framework designed to address critical performance, determinism, and ecosystem compatibility challenges in blockchain networks. Building…
Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new…
Predicting future states of dynamic agents is a fundamental task in autonomous driving. An expressive representation for this purpose is Occupancy Flow Fields, which provide a scalable and unified format for modeling motion, spatial extent,…
The drastic variation of motion in spatial and temporal dimensions makes the video prediction task extremely challenging. Existing RNN models obtain higher performance by deepening or widening the model. They obtain the multi-scale features…
Concurrent systems are often complex and difficult to design. Choreographic languages, such as Multiparty Session Types (MPST), allow the description of global protocols of interactions by capturing valid patterns of interactions between…
We present SSS, a scalable transactional key-value store deploying a novel distributed concurrency control that provides external consistency for all transactions, never aborts read-only transactions due to concurrency, all without…
In this paper, we present new optimization models for Support Vector Machine (SVM), with the aim of separating data points in two or more classes. The classification task is handled by means of nonlinear classifiers induced by kernel…