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
753 results for “keyword:"fine tuning"” in ICLR 2027. 158 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reward Moves What It Measures: Anisotropic Program Anchoring for RL Fine-Tuning under Incomplete Objectives▼5.8k2.33
[PDF]Not All Conflicts Are Equal: Forecasting Token Learning Trajectories for Supervised Fine-Tuning▼11k1.75
[PDF]CoSelTune: Co-Designing Token Selection and Backward Computation for Efficient Long-Context Fine-Tuning▼4.3k2.00
[PDF]Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance▲432.75
[PDF]Pretrained Mamba-Based Vision Backbones Can Exhibit Collapsed Timescale Banks: Checkpoint-Aware State Expansion with SpanInit▼4.3k2.00
[PDF]When LoRA Rank Matters in RLVR: Saturation-Gated Scaling and Off-Principal Initialization▼1361.33
[PDF]SWORD: An Efficient Adaptation of Multi-Agent Policy with Sparse and Low Rank Decomposition for Heterogeneous Satellite Cluster▲3.0k2.33
[PDF]Learning Style, Forgetting Semantics: A case study of SFT and RFT on Classification Tasks▲5.4k3.00
[PDF]Representational Inertia: Activation Stitching Reverses Fine-Tuned Behavior in Large Language Models▼4.3k2.00
[PDF]Longer Answers, Heavier Questions: How Loss Weighting Shapes Comparisons of Synthetic Reasoning Data▼4.5k2.67
[PDF]What Should We Freeze? Guarded Freezing: Connectivity Shapes the Fine-Tuning of Pretrained Models▲6.1k2.00
[PDF]Routes Interfere, Representations Transfer: Parameter-Efficient Adaptation of Promptable Segmentation Models▼1.2k1.67
Withdrawn or desk rejected (158)
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67