SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution Paper • 2502.18449 • Published 28 days ago • 71
Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning Paper • 2410.03103 • Published Oct 4, 2024 • 7
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents Paper • 2401.00812 • Published Jan 1, 2024 • 9
What is the Visual Cognition Gap between Humans and Multimodal LLMs? Paper • 2406.10424 • Published Jun 14, 2024
Mitigating Transformer Overconfidence via Lipschitz Regularization Paper • 2306.06849 • Published Jun 12, 2023
MACP: Efficient Model Adaptation for Cooperative Perception Paper • 2310.16870 • Published Oct 25, 2023
LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs Paper • 2312.04372 • Published Dec 7, 2023
Agentless: Demystifying LLM-based Software Engineering Agents Paper • 2407.01489 • Published Jul 1, 2024 • 62
XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts Paper • 2404.15247 • Published Apr 23, 2024 • 3
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair Paper • 2309.00608 • Published Sep 1, 2023 • 2
NeuRI: Diversifying DNN Generation via Inductive Rule Inference Paper • 2302.02261 • Published Feb 4, 2023 • 3
Enable Language Models to Implicitly Learn Self-Improvement From Data Paper • 2310.00898 • Published Oct 2, 2023 • 23
LM-Infinite: Simple On-the-Fly Length Generalization for Large Language Models Paper • 2308.16137 • Published Aug 30, 2023 • 40