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
7,679 results for “keyword:"ai"” in ICLR 2027. 1,830 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation▼1.2k1.67
[PDF]Reusing Trainable States, Not Just Solutions: Policy-Archive Search at Test Time for Automated Discovery▲25k3.00
[PDF]What a Deepfake Score Does Not Tell You: Same-Source Controls for Face-Forgery and Generated-Video Detectors▲3.0k2.33
[PDF]Observation-Aligned Mask Priors for Learning Physical Fields from Authentic Occlusions▼5.8k2.33
[PDF]Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding▲3.0k2.33
[PDF]CRISP: Domain Generalization through Compositional Spatial Relations over Visual Primitives▲3952.67
[PDF]Where Grounding Accuracy Lives on the IoU Curve: Label-Free Inference-Time Boundary Refinement▼1361.33
[PDF]CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition▲3.0k2.33
[PDF]SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning▼4.3k2.00
[PDF]Proxyboros: Motion-Faithful Dynamic Self-Intersection Repair for Rigged Mesh Animations▲4.6k3.00
[PDF]See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space▼4.5k2.67
[PDF]AlloMIT: Boosting Allosteric Virtual Screening via Multi-Instance Parameter-Efficient Tuning▼5.8k2.33
[PDF]Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence▼4.3k2.00
Withdrawn or desk rejected (1,830)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected