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
842 results for “keyword:"code"” in ICLR 2027. 190 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A Linear Name-Origin Prior in the Recall Heads: How Language Models Fabricate and Misrecall Facts About People▲5103.00
[PDF]The Half-Life of Repairs: Why Fixes Fail under Continued Training and How to Make Them Last▲11.00
[PDF]From Noise Beliefs to Logical Decisions: Surface-Code Decoding with Temporal Side Information▲3.0k2.33
[PDF]Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates▲13k2.33
[PDF]Auditing the Auditor: Ground-Truth Controls for Natural-Language Explanations of LLM Activations▼4.3k2.00
[PDF]Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders▲5103.00
[PDF]How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts▼5.8k2.33
[PDF]Exact and Inexact Marginal Penalties: When Does the Wasserstein Autoencoder Recover the Wasserstein Distance?▼11k1.75
[PDF]PROSE: Enhancing Sample Efficiency in Code Generation via Plan-Aware Rollout Reorganization▼5.8k2.33
[PDF]Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation▼1.2k1.67
[PDF]Asymptotically Optimal Quantizer-Guided Sinkhorn Alignment for Mitigating Codebook Collapse▲4012.67
[PDF]Cross-Architecture Universal SAEs: A Shared Sparse Dictionary for Vision and Diffusion Transformers▼1351.33
[PDF]Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery▲3.0k2.33
[PDF]CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits▼4.5k2.67
Withdrawn or desk rejected (190)
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67