ICLR 2025PastOther
ICLR 2025 Third Workshop on Deep Learning for Code
DL4C @ ICLR 2025
- Submission deadline
- Feb 13, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (46)
Fetched from OpenReview (v2) on 2026-06-10.
Adaptive Self-improvement LLM Agentic System for ML Library Development
Arctic-SnowCoder: Demystifying High-Quality Data in Code Pretraining
AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions
Automated Benchmark Generation for Repository-Level Coding Tasks
BaxBench: Can LLMs Generate Correct and Secure Backends?
Black-Box Adversarial Attacks on LLM-Based Code Completion
CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification
Code2JSON: Can a Zero-Shot LLM Extract Code Features for Code RAG?
CodeEditorBench: Evaluating Code Editing Capability of LLMs
CodeTransEngine: Ready-to-use Backend for LLM-based Code Translation
Contextual Augmented Multi-Model Programming (CAMP): A Local-Cloud Copilot Solution
Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning
Diagnosing Robotics Systems Issues with Large Language Models – A Case Study
DISC: Dynamic Decomposition Improves LLM Inference Scaling
Do LLMs Understand Code Preference? Training Code Preference Models via Synthetic Code Evolution
EnvBench: A Benchmark for Automated Environment Setup
Evaluating the Diversity and Quality of LLM Generated Content
Evolving RL: Discovering New Activation Functions using LLMs
Feather-SQL: A Lightweight NL2SQL Framework with Dual-Model Collaboration Paradigm for Small Language Models
From Pseudo-Code to Source Code: A Self-Supervised Search Approach
GenePrune : Automated Pruning of Large Language Models for Code using Genetic Algorithm
Generate-Feedback-Refine: How Much Does Model Quality in Each Role Matter?
Generating Code to Verify Cryptic Crossword Reasoning
GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code
Improving Automated Issue Resolution via Comprehensive Repository Exploration
InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation
KernelBench: Can LLMs Write Efficient GPU Kernels?
LLM Program Optimization via Retrieval Augmented Search
LoRACode: LoRA Adapters for Code Embeddings
ML-BENCH: EVALUATING LARGE LANGUAGE MODELS AND AGENTS FOR MACHINE LEARNING TASKS ON REPOSITORY-LEVEL CODE
ML-Dev-Bench: Comparative Analysis of AI Agents on ML development workflows
NextCoder: Robust Adaptation of Code LMs to Diverse Code Edits
On Pretraining For Project-Level Code Completion
One Model to Train Them All: Hierarchical Self-Distillation for Enhanced Early Layer Embeddings
Parameter-Efficient Instruction Tuning Code Large Language Models: An Empirical Study
Programming with Pixels: Towards Generalist Software Engineering Agents
Shedding Light on Task Decomposition in Program Synthesis: The Driving Force of the Synthesizer Model
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
Tasks, Challenges, and Paths Towards AI for Software Engineering
Teaching Language Models to Critique via Reinforcement Learning
Themisto: Jupyter-Based Runtime Benchmark
Toward Trustworthy Neural Program Synthesis
Training Software Engineering Agents and Verifiers with SWE-Gym
Type-Constrained Code Generation with Language Models
TypyBench: Evaluating LLM Type Inference for Untyped Python Repositories
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation