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753 results for “keyword:"fine tuning"” in ICLR 2027. 158 withdrawn or desk rejected listed apart.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]L-MoL: Mitigating Multilingual Interference via a Language-Guided Mixture of Low-Rank Experts▼5.9k2.50
[PDF]Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning▼1361.33
[PDF]Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression▼1361.33
[PDF]Adaptive Contrastive Self-Play for Regime-Aware Reinforcement Learning Fine-Tuning of Language Models▼4.3k2.00
[PDF]APERTURE: What to measure, how much to measure, and where to allocate in multimodal low-rank adaptation▼13k2.00
[PDF]SAE-Locked LoRA: Edit-Specific Sparse-Feature Gradient Routing for Low-Interference Knowledge Editing▼4.5k2.67
[PDF]RL Does Not Always Forget Less: Understanding Retention through Target Learning in LLM Post-Training▲3952.67
[PDF]Unanticipated Preference Drift: Training Data Outweighs Tasks and Defies Self-Prediction▼4.3k2.00
[PDF]Decoupling Capabilities via Sample-Level Geometric Routing for Parameter-Efficient Low-Resource Adaptation▲6.1k2.00
[PDF]MedRDSyn: Knowledge Graph-Based Rare Disease Data Synthesis for Supervised Fine-Tuning▼4.3k2.00
[PDF]What The Mask Still Buys: Measuring Which Decoding Constraints Small Language Models Internalize▲11.00
[PDF]Collapse, Repair, and Drift: Dissecting Fine Tuning Dynamics in Speech Language Models▼1.2k1.67
[PDF]Encoded but Unread: Locating and Recovering Within-Event Motion in Video Language Models▼12k1.67
[PDF]Diagnosing Harmful Continuation in Answer-Correct Mathematical Long-CoT Training Traces▼4.3k2.00
[PDF]DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data▼5.8k2.33
[PDF]ECR-LoRA: Evolving Core LoRA and Complementary Residual LoRAs for Class-Incremental Learning▲6.6k3.33
Withdrawn or desk rejected (158)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