paper-with-me

Program Synthesis

3개 벤치마크 · 논문 537편 · 이 태스크의 논문 보기 →

Benchmarks

SPoC TestP

결과 2개

SPoC TestW

결과 2개

AlgoLisp

결과 1개

Most implemented

Papers

CommerceVibe: Learning to Design E-Commerce Creatives as Executable Visual Code via Dual-Feedback Reinforcement Learning

2026-08-28 · Yajiao Xu, Jin Zhang, Jiangbo Ai, Tao Jiang 외 arxiv

High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent diffusion models enable scalable creative generation and produce visually compelling images, but their flat…

Reinforcement LearningProgram Synthesis

Narcissus: Program Synthesis Using Context-Aware LLM Approximations

2026-08-26 · Tilman Hinnerichs, Sebastijan Dumancic, Neil Yorke-Smith arxiv

Large language models (LLMs) excel at programming, but not when the task fixes the target language: prompted with a grammar rare in their training data, their programs usually break the grammar or fail the given specific…

Program Synthesis

Lossless Tensor Compression as Program Synthesis

2026-08-03 · Jieke Shi, Junda He, Wenjia Jiang, Weifeng Sun 외 hf

Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requirements but ignore tensor structure, whereas …

Program SynthesisImage Generation

Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

2026-08-03 · Gaytri Jena, Kapil Wanaskar, Vinija Jain, Aman Chadha 외 hf

Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey org…

Program Synthesis

Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models

2026-07-30 · Yang Li, Ping Hou, Nobuko Yoshida arxiv

Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlocks. In such settings, protocol refinement - the safe substi…

Program SynthesisCode Generation

SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch

2026-07-29 · Yihao Chen, Shi Chang, Feng Lin, Khaled Chawa 외 hf

LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this…

Program Synthesis

전체 537편 보기 →