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
141 results for “keyword:"supervised fine tuning"” in ICLR 2027. 26 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning What vs. Learning How: Decomposing Task and Interface Competence in Agentic Training▲5103.00
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise▼1.2k1.67
[PDF]Synth-Ethics: Synthetic Training Data for LLM Constitutions Grounded in Ethical Traditions▼5.8k2.33
[PDF]BIND BEFORE YOU BUYCANDIDATE-CONSISTENT CONSTRAINT LEARNINGFOR INTERACTIVE SHOPPING AGENTS▼1.3k1.75
[PDF]GRAIN: Gradient-Referenced Alignment of Informative Tokens for LLM Supervised Fine-Tuning▲3.0k2.33
[PDF]From Hallucinated Targets to Runaway Repetition: Termination Control in Long Structured Generation▼5.9k2.50
[PDF]Not All Conflicts Are Equal: Forecasting Token Learning Trajectories for Supervised Fine-Tuning▼11k1.75
[PDF]Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance▲432.75
[PDF]Learning Style, Forgetting Semantics: A case study of SFT and RFT on Classification Tasks▲5.4k3.00
[PDF]Longer Answers, Heavier Questions: How Loss Weighting Shapes Comparisons of Synthetic Reasoning Data▼4.5k2.67
[PDF]Beyond Rejection Sampling: Learning from Guided Rollouts to Improve LLMs for Software Engineering▼4.3k2.00
[PDF]LEMMA: Learned Model Merging for Text-to-Image Generation via Multi-Objective Optimization▼5.8k2.33
[PDF]The Protocol Is the Agent: Decomposing RL, SFT, and Scaffold Effects in Tool-Use Agents from 0.8B to 27B▼1.2k1.67
[PDF]Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation▲9.2k2.67
[PDF]Can Post-Training on Agentic Chain-of-Thought Autonomously Screen Protein Binders For Experimental Success?▼1.2k1.67
Withdrawn or desk rejected (26)
[PDF]When Does DPO Add Value over Continued SFT? Evidence from Correction-Preservation FrontiersWithdrawn1.50
[PDF]TraceBridge: Interaction-Aware Trajectory Rewriting across Harnesses for Coding Agent TrainingWithdrawn1.67
[PDF]Prior-Guided Importance Weighting for Supervised Fine-Tuning of Multimodal Large Language ModelsDesk rejected2.00