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
351 results for “keyword:"parameter efficient"” in ICLR 2027. 97 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Chain of Evidence: Localizing Video Forgeries via Image Forensic Evidence in Space and Time▼5.8k2.33
[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]EnergyCA-LLM: Context-Guided Window-Adaptive Residual Learning for Unified Renewable Generation and Load Forecasting▼5.8k2.33
[PDF]Decoupling Capabilities via Sample-Level Geometric Routing for Parameter-Efficient Low-Resource Adaptation▲6.1k2.00
[PDF]Encoded but Unread: Locating and Recovering Within-Event Motion in Video Language Models▼12k1.67
[PDF]ECR-LoRA: Evolving Core LoRA and Complementary Residual LoRAs for Class-Incremental Learning▲6.6k3.33
[PDF]How Much Rank Does LoRA Need? Task-Dependent Rank-Error Bounds for Transformer Attention▼1.2k1.67
[PDF]Beyond the Current Observation: History-Informed Adaptation for Vision-Language-Action Models▼1351.33
[PDF]Beyond Non-Zero Initialization: Investigating Update Balance in Structured LoRA Initialization▼4.3k2.00
[PDF]Spectral Profiling for Complementary Dual-Branch Capacity Allocation in One-Step Diffusion Super-Resolution▲3.0k2.33
[PDF]From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning▲5.4k3.00
[PDF]CRITICAL-LAYER CONTEXT ALIGNMENT FOR LARGE LANGUAGE MODEL-BASED TIME-SERIES FORECASTING▼4.3k2.00
[PDF]Den2MoEE: Reconstructing Dense LLMs into Expert-Specialized Mixture-of-Experts for Efficient Embedding Models▲1.7k3.33
[PDF]RIDER: SUPPORT-AWARE ANALYTICAL EVIDENCE CONSTRUCTION FOR REHEARSAL-FREE CLASS- INCREMENTAL LEARNING▲4012.67
[PDF]AR-Retrofit: Retrofitting Pretrained Decoders with Attention Residuals for Adaptive Depth▲9.2k2.67
[PDF]Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing▼4.3k2.00
Withdrawn or desk rejected (97)
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67