NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
172 results for “keyword:"code generation"” in ICLR 2027. 32 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]What The Mask Still Buys: Measuring Which Decoding Constraints Small Language Models Internalize▲11.00
[PDF]RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning▼1.2k1.67
[PDF]Layout Beyond Format: Internalizing Spatial Execution in LLMs via Element-Level Geometric Rewards▼4.3k2.00
[PDF]SketchFactory: A Unified Framework for Learning and Evaluating Sketch-to-Code Generation▼5.8k2.33
[PDF]KernelAudit: Can LLM-Generated GPU Kernels Be Both Reliable and Competitive on Real-World Workloads?▼4.5k2.67
[PDF]VISTA: Looking Right Is Not Working Right — Benchmarking Coding Agents from Design Handoffs to Full-Stack Web and Mobile Apps▼4.5k2.67
[PDF]How Far Can Reasoning Alone Take You? Graph-Based Candidate Selection for Test-Time Scaling on Code▲4012.67
[PDF]DitronGen: Compiler–LLM Coordination for Adaptive Kernel Generation and Computation–Communication Overlap▼4.3k2.00
[PDF]CreativeBench2.0: Benchmarking Creative Method Discovery and Foresight Toward Recursive Self-Improvement▼4.5k2.67
[PDF]REALMS-CG: Resilient Ensemble of Autonomous LLM Multi-agent with Spectral clustering for Code Generation▲3.0k2.33
[PDF]Small but Mighty: Quality–Diversity Evolutionary Search for Size-Optimized Unit Test Generation▲4012.67
[PDF]Where and When: Structure-Grounded Credit Assignment for Cross-Modal Reinforcement Learning▼4.5k2.67
[PDF]GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets▼5.8k2.33
[PDF]Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution▼5.8k2.33
Withdrawn or desk rejected (32)
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67
[PDF]EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution FeedbackWithdrawn1.67