Related papers: BEhavioral Leakage and IntEr-cycle Variability Emu…
This paper introduces recurrent equilibrium networks (RENs), a new class of nonlinear dynamical models} for applications in machine learning, system identification and control. The new model class admits ``built in'' behavioural guarantees…
Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due…
Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause…
As conventional memory technologies are challenged by their technological physical limits, emerging technologies driven by novel materials are becoming an attractive option for future memory architectures. Among these technologies,…
Cognitive modeling commonly relies on asking participants to complete a battery of varied tests in order to estimate attention, working memory, and other latent variables. In many cases, these tests result in highly variable observation…
This paper proposes a novel methodology for addressing the simulation-reality gap for multi-robot swarm systems. Rather than immediately try to shrink or `bridge the gap' anytime a real-world experiment failed that worked in simulation, we…
In this paper, we build a general modelling framework for memristors, suitable for the simulation of event-based systems such as hardware spiking neural networks, and more generally, neuromorphic computing systems composed of three…
With the rapid surge in the number of on-road Electric Vehicles (EVs), the amount of spent lithium-ion (Li-ion) batteries is also expected to explosively grow. The spent battery packs contain valuable metal and materials that should be…
Reactive and safe agent modelings are important for nowadays traffic simulator designs and safe planning applications. In this work, we proposed a reactive agent model which can ensure safety without comprising the original purposes, by…
This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components -- to…
How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared…
We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…
Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…
A large number of simulation models have been proposed over the years to mimic the electrical behaviour of memristive devices. The models are based either on sophisticated mathematical formulations that do not account for physical and…
Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often violate this assumption, as non-speakers frequently lack…
Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…
We successfully model the behavior of two-spin systems using neural networks known as conditional Restricted Boltzmann Machines (cRBMs) which encode physical information in the properties of a thermal ensemble akin to an Ising model. The…
Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…
Sub/Near-threshold static random-access memory (SRAM) design is crucial for addressing the memory bottleneck in energy-constrained applications. However, the high integration density and reliability under process variations demand an…
In order to shed more light on how RowHammer affects modern and future devices at the circuit-level, we first present an experimental characterization of RowHammer on 1580 DRAM chips (408x DDR3, 652x DDR4, and 520x LPDDR4) from 300 DRAM…