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
792 results for “keyword:"latent"” in ICLR 2027. 183 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Pretrained Features as Teachers, Not States: Compact Latent World Models for Visual Planning▲3.0k2.33
[PDF]The Rank Bottleneck in Diffusion Transformers: Why and When Width Must Track Token Dimension▲432.75
[PDF]Graph-Parameterized Capacity for Latent Multi-Hop Recall: Usage, Compression, and Composition▼13k2.00
[PDF]Safe to Omit, Worth Omitting? Keeping the Answer and Cutting Latency When an LLM Agent Skips Another's Message▲13k2.33
[PDF]Learning World Models with Joint-Embedding Prediction for Single- and Multi-Agent Reinforcement Learning▼1361.33
[PDF]Auditing Individual Specificity in EEG Foundation Models with Occupancy-Preserving Temporal Nulls▼1.2k1.67
[PDF]Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?▼4.3k2.00
[PDF]What Is Identified in Causal Representation Learning? Exact Answers for the Normalized iVAE from Realized Symmetries▼4.3k2.00
[PDF]Universal Mixup Loss: Training Audio Autoencoders to Decode the Positive-Weight Mixing Cone▲3952.67
Withdrawn or desk rejected (183)
[PDF]Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous DrivingWithdrawn1.67
[PDF]Learning What to Share: Latent Representations for FedRL with Observation DistractorsDesk rejected1.67