Related papers: Deterministic Fully-Static Whole-Binary Translatio…

Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large Language Models (LLMs) have recently shown promise, they often suffer from "logical…

The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify…

Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them without grounding in observable evidence leads to compounding…

DSLs and hardware accelerators have proven to be very effective in optimizing computationally expensive workloads. In this paper, we propose a solution to the challenge of manually rewriting legacy or unoptimized code in domain-specific…

WebAssembly (Wasm), as a compact, fast, and isolation-guaranteed binary format, can be compiled from more than 40 high-level programming languages. However, vulnerabilities in Wasm binaries could lead to sensitive data leakage and even…

Transformers have become keystone models in natural language processing over the past decade. They have achieved great popularity in deep learning applications, but the increasing sizes of the parameter spaces required by transformer models…

Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latency. Inspired by recent refinement-based approaches, we…

Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation. This language-dependent design leads to large-scale network…

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is…

Knowledge of the input format of binary executables is important for finding bugs and vulnerabilities, such as generating data for fuzzing or manual reverse engineering. This paper presents an algorithm to recover the structure and semantic…

The semantics and the recursive execution model of Prolog make it very natural to express language interpreters in form of AST (Abstract Syntax Tree) interpreters where the execution follows the tree representation of a program. An…

Mutation analysis is an effective technique to evaluate a test suite adequacy in terms of revealing unforeseen bugs in software. Traditional source- or IR-level mutation analysis is not applicable to the software only available in binary…

Document exchange and error correcting codes are two fundamental problems regarding communications. In the first problem, Alice and Bob each holds a string, and the goal is for Alice to send a short sketch to Bob, so that Bob can recover…

This paper describes design of a low-complexity algorithm for adaptive encoding/ decoding of binary sequences produced by memoryless sources. The algorithm implements universal block codes constructed for a set of contexts identified by the…

Non-autoregressive machine translation (NAT) models have lower translation quality than autoregressive translation (AT) models because NAT decoders do not depend on previous target tokens in the decoder input. We propose a novel and general…

Deep learning needs high-precision handling of forwarding signals, backpropagating errors, and updating weights. This is inherently required by the learning algorithm since the gradient descent learning rule relies on the chain product of…

Many nonlinear optimal control and optimization problems involve constraints that combine continuous dynamics with discrete logic conditions. Standard approaches typically rely on mixed-integer programming, which introduces scalability…

Error correcting codes play a central role in digital communication, ensuring that transmitted information can be accurately reconstructed despite channel impairments. Recently, autoencoder (AE) based approaches have gained attention for…

State-of-the-art neural machine translation methods employ massive amounts of parameters. Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful. To this end, we propose…

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the…