Related papers: Learning to Combine Instructions in LLVM Compiler
With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model's capabilities from the perspective of…
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…
The Deep Learning (DL) community sees many novel topologies published each year. Achieving high performance on each new topology remains challenging, as each requires some level of manual effort. This issue is compounded by the…
Large-scale neural language models exhibit a remarkable capacity for in-context learning (ICL): they can infer novel functions from datasets provided as input. Most of our current understanding of when and how ICL arises comes from LMs…
Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications. The primary challenge is effectively fusing this visual and textual information.…
Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…
We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs. NPI has three learnable components: a task-agnostic recurrent core, a persistent key-value…
With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototyping and automated…
Low bit-width Quantized Neural Networks (QNNs) enable deployment of complex machine learning models on constrained devices such as microcontrollers (MCUs) by reducing their memory footprint. Fine-grained asymmetric quantization (i.e.,…
Imitation learning (IL) provides a data-driven framework for approximating policies for large-scale combinatorial optimisation problems formulated as sequential decision problems (SDPs), where exact solution methods are computationally…
Robust and adaptive control strategies are needed when robots or automated systems are introduced to unknown and dynamic environments where they are required to cope with disturbances, unmodeled dynamics, and parametric uncertainties. In…
Various processing-in-memory (PIM) accelerators based on various devices, micro-architectures, and interfaces have been proposed to accelerate deep neural networks (DNNs). How to deploy DNNs onto PIM-based accelerators is the key to explore…
Multi-level intermediate representations (MLIR) show great promise for reducing the cost of building domain-specific compilers by providing a reusable and extensible compiler infrastructure. This work presents TPU-MLIR, an end-to-end…
Error-Correcting Output Codes (ECOCs) offer a principled approach for combining simple binary classifiers into multiclass classifiers. In this paper, we investigate the problem of designing optimal ECOCs to achieve both nominal and…
Simulators for the RISC-V instruction set architecture (ISA) are useful for teaching assembly language and modern CPU architecture concepts. The Assembly/Simulation Platform for Illustration of RISC-V in Education (ASPIRE) is an integrated…
Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…
During early optimization passes, compilers must make predictions for machine-dependent characteristics such as execution unit utilization, number of register spills, latency, throughput etc. to generate better code. Often a hand-written…
Machine learning based on neural networks has advanced rapidly, but the high energy consumption required for training and inference remains a major challenge. Hyperdimensional Computing (HDC) offers a lightweight, brain-inspired alternative…
High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU…
To overcome the limitations of Neural Programmer-Interpreters (NPI) in its universality and learnability, we propose the incorporation of combinator abstraction into neural programing and a new NPI architecture to support this abstraction,…