Related papers: RISE & Shine: Language-Oriented Compiler Design

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly,…

Data is stored in both structured and unstructured form. Querying both, to power natural language conversations, is a challenge. This paper introduces dIR, Discrete Information Retrieval, providing a unified interface to query both free…

Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performance for flexible hardware, or ASICs, which rapidly become…

The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…

There is a growing interest in enhancing compiler optimizations with ML models, yet interactions between compilers and ML frameworks remain challenging. Some optimizations require tightly coupled models and compiler internals,raising issues…

As Moore's Law continues to increase the complexity of electronic systems, Electronic Design Automation (EDA) must advance to meet global demand. An important example of an EDA technology is SKILL, a scripting language used to customize and…

This paper presents the design of Glow, a machine learning compiler for heterogeneous hardware. It is a pragmatic approach to compilation that enables the generation of highly optimized code for multiple targets. Glow lowers the traditional…

Composed Image Retrieval (CIR) facilitates image retrieval through a multimodal query consisting of a reference image and modification text. The reference image defines the retrieval context, while the modification text specifies desired…

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications…

Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly studied when to invoke tools, while overlooking how tools are applied. We identify two common…

Modern Language Models (LMs) are capable of following long and complex instructions that enable a large and diverse set of user requests. While Information Retrieval (IR) models use these LMs as the backbone of their architectures,…

Optimization modeling is fundamental to decision-making across diverse domains. Despite progress in automating optimization formulation from natural language descriptions, Large Language Models (LLMs) often struggle to generate formally…

A central piece in enabling intelligent agentic behavior in foundation models is to make them capable of introspecting upon their behavior, reasoning, and correcting their mistakes as more computation or interaction is available. Even the…

Modeling interoperability between programs in different languages is a key problem when modeling verified and secure compilation, which has been successfully addressed using multi-language semantics. Unfortunately, existing models of…

Existing large language model (LLM)-based embeddings typically adopt an encoder-only paradigm, treating LLMs as static feature extractors and overlooking their core generative strengths. We introduce GIRCSE (Generative Iterative Refinement…

Recent algorithmic advances have made equality saturation an appealing approach to program optimization because it avoids the phase-ordering problem. Existing work uses external equality saturation libraries, or custom implementations that…

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel…

While recent advancements in Neural Ranking Models have resulted in significant improvements over traditional statistical retrieval models, it is generally acknowledged that the use of large neural architectures and the application of…

This paper presents a meta-compilation framework, the MCompiler. The main idea is that different segments of a program can be compiled with different compilers/optimizers and combined into a single executable. The MCompiler can be used in a…

A C decompiler converts an executable into source code. The recovered C source code, once re-compiled, is expected to produce an executable with the same functionality as the original executable. With over twenty years of development, C…