Related papers: Forward-only learning in memristor arrays with mon…

The success of large-scale pre-trained models has established fine-tuning as a standard method for achieving significant improvements in downstream tasks. However, fine-tuning the entire parameter set of a pre-trained model is costly.…

Recent work applies Large Language Models (LLMs) to source-code vulnerability detection, but most evaluations still rely on random train-test splits that ignore time and overestimate real-world performance. In practice, detectors are…

We present a systematic study of memristor based neural networks trained with the hardware-friendly Manhattan update rule, focusing on the trade offs between learning performance and energy consumption. Using realistic models of…

We use telemetry data from the Gemini North ALTAIR adaptive optics system to investigate how well the commands for wavefront correction (both Tip/Tilt and high-order turbulence) can be forecasted in order to reduce lag error (due to…

For neuromorphic engineering to emulate the human brain, improving memory density with low power consumption is an indispensable but challenging goal. In this regard, emerging RRAMs have attracted considerable interest for their unique…

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart training for each new hyperparameter choice, at considerable…

Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…

Fine-tuning large pre-trained models on downstream tasks has been adopted in a variety of domains recently. However, it is costly to update the entire parameter set of large pre-trained models. Although recently proposed parameter-efficient…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Validating the safety of autonomous systems generally requires the use of high-fidelity simulators that adequately capture the variability of real-world scenarios. However, it is generally not feasible to exhaustively search the space of…

The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this…

We introduce Error Forward-Propagation, a biologically plausible mechanism to propagate error feedback forward through the network. Architectural constraints on connectivity are virtually eliminated for error feedback in the brain;…

In this work, we report a novel design, one-transistor-one-inverter (1T1I), to satisfy high speed and low power on-chip training requirements. By leveraging doped HfO2 with ferroelectricity, a non-volatile inverter is successfully…

Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…

The superior density of passive analog-grade memristive crossbars may enable storing large synaptic weight matrices directly on specialized neuromorphic chips, thus avoiding costly off-chip communication. To ensure efficient use of such…

Transformer models have achieved state-of-the-art performance across a wide range of machine learning tasks. There is growing interest in training transformers on resource-constrained edge devices due to considerations such as privacy,…

Spectral analysis provides one of the most effective paradigms for information-preserving dimensionality reduction, as simple descriptions of naturally occurring signals are often obtained via few terms of periodic basis functions. In this…

Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end…

In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the…