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
2,482 results for “keyword:"sta"” in ICLR 2027. 730 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Stored Action Does Not Identify the Sampled Latent: Finite-Precision Likelihood Replay in Squashed Policies▼1.2k1.67
[PDF]An Infinite Information Exponent that Gradient Descent Still Learns at the Optimal Rate: The Value Catalyst in Softmax Attention▼71.25
[PDF]Recurrent Refinement Moves Candidate-Quality Readability Earlier and Stabilizes Its Coordinates▼1.2k1.67
[PDF]FineRich: Towards Holistic Fine-Grained Text-Rich Image Understanding via Versatile HTML-Based Synthesis▲14k3.00
[PDF]Frames Don't Add Up: A Factorial Causal Audit of Contextual Evidence Utility in Video-Language Models▼1361.33
[PDF]Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams▲2623.67
[PDF]StreamWeave: Curating Multi-Timescale Visual Evidence for Streaming Video Understanding▲3952.67
[PDF]The Statistical Origins of Model Collapse: Resampling, Retention, and Exact Variance Recursions▲3.0k2.33
[PDF]Decoding Beyond Hemodynamic Delay: Delay-Coupled Graph Dynamics for fMRI-to-Image Reconstruction▼4.3k2.00
[PDF]Where You Put Attention Matters More Than How Much You Use: Attention Placement in Hybrid Sequence Models▲11.00
[PDF]Towards Efficient and Effective Scene Visual Representation for 3D Spatial Scene Understanding▼4.5k2.67
[PDF]One Lesion, Many Views: Disentangled Vision-Language Pretraining for Multi-Dimensional Lesion Understanding▲9.2k2.67
[PDF]Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory▼4.3k2.00
[PDF]ICM-bench: A Benchmark for Evaluating the In-context Modification Ability of Large Language Models▼4.3k2.00
[PDF]What Should a Streaming Coach Remember? Motion Evidence Across Repetitions and Transitions▲3952.67
[PDF]LayerBridge: Unifying Understanding, Generation and Editing with Adaptive Attention over Frozen VLM Layers
[PDF]IMUG-Bench: Benchmarking Unified Multimodal Models on Interleaved Understanding and Generation▲3952.67
[PDF]AlloMIT: Boosting Allosteric Virtual Screening via Multi-Instance Parameter-Efficient Tuning▼5.8k2.33
[PDF]CPGN: A Coordination Polyhedron Graph Network for Multi-Scale Crystal Property Prediction Using Dual-Level Atomic and Geometric Representations▼1361.33
Withdrawn or desk rejected (730)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00