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
2,436 results for “keyword:"optimization"” in ICLR 2027. 454 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Support Selection Beyond Smooth DAG Exactness: Completion Geometry, Score Margins, and Selective Certificates▼5.8k2.33
[PDF]HeteroLoRA-MoE: Heterogeneous Low-Rank Experts with Diverse Projection Patterns and Efficient GPU Kernels▼4.3k2.00
[PDF]BeTAR: Belief-Guided Trajectory Learning with Agentic Reinforcement Learning for Multi-Degradation Surgical Image Restoration▲11.00
[PDF]Normalize the Update, Not the Weights: Efficient Loss Weighting for Multi-Objective Pretraining▲3.0k2.33
[PDF]Breaking the Black Box: An Architecture-Specialized Preconditioning Optimizer for Attention Mechanism▼4.3k2.00
[PDF]Learning What to Reject: Counterfactual Preference Alignment for Emotion–Cause Pair Extraction▼1.3k1.80
[PDF]Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes▲5103.00
[PDF]Protect Before Evicting: Lagrangian-Guided Encoder Caching for Disaggregated Multimodal LLM Serving▼1361.33
[PDF]A Decentralized Lens on Centralized Federated Learning: Unifying FL via Inexact Douglas–Rachford Splitting▼4.3k2.00
[PDF]H-OSIRIS: Hierarchical Layout-Aware Analog Circuit Sizing and Footprint Optimization using Deep Reinforcement Learning▼4.3k2.00
[PDF]Same Groups, Different Values: Decomposing Step-Level Credit Assignment for LLM Agents▲6.1k2.00
[PDF]TraceStencil: Signed Temporal Neighborhoods for Token-Level Policy Optimization in RLVR▼1.2k1.67
[PDF]Bringing Order to Asynchronous SGD: Towards Optimality under Data-Dependent Delays with Momentum▼5.9k2.50
[PDF]SARC: Interpretable State-Adaptive Reward Composition for Sparse Reward Reinforcement Learning▲3.0k2.33
[PDF]Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution▲3.0k2.33
[PDF]From Experience to Knowledge: Algorithm Design for Black-Box Optimization with Large Language Models▼4.3k2.00
[PDF]Gradient Descent on Tokens Is Sparse: Understanding the Computational Structure of Differentiable Token Optimization▼4.3k2.00
Withdrawn or desk rejected (454)
[PDF]Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction TuningDesk rejected1.67