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
11,752 results for “keyword:"models"” in ICLR 2027. 2,919 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Less Data, Better Timing: Student–Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding▲9.2k2.67
[PDF]LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation▼5.9k2.33
[PDF]Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text▼4.3k2.00
[PDF]Beyond Lip Sync: Reference-Grounded Oral Refinement for Audio-Driven Portrait Animation▼4.3k2.00
[PDF]Beyond the Best Available Cause: Calibrated Verification and Triage under Hypothesis-Space Inadequacy▲3.0k2.33
[PDF]Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers▲3812.67
[PDF]Rethinking Geometric Priors in Novel View Synthesis through Multi-Axis Reliability Fields▲9.2k2.67
[PDF]Learning to Zoom at the Right Difficulty: Dynamic Curricula for Visual Tool-Use Reinforcement Learning▲5093.00
[PDF]One Calibration, Many Requests: Amortized Black-Box Multimodal Jailbreaking via Cross-Model Refusal Coordinates▲14k3.00
[PDF]Global Relevance Is Not Enough: Representative Candidate Construction and Residual-Based Evidence Preservation for Efficient, Reliable Medical MLLM Inference▲9.2k2.67
[PDF]What Should a VLM Tell an Action Expert? Comparing Conditioning Interfaces for Long-Horizon Furniture Assembly▼1361.33
[PDF]Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning▼4.5k2.67
[PDF]Progressive Branch-Merge:Trainable Sequence Processing Across Frozen Transformer Depth▼1.2k1.67
[PDF]Act-on-Graph: Recoverability-Aware Multi-Hop Retrieval for Reliable Knowledge Graph-Grounded LLM Reasoning▲3.0k2.33
[PDF]HotPOT: Operator Transformer with Heterogeneous Physics Experts for Large-Scale PDE Pre-training▲6.1k2.00
[PDF]SEA-Boundary: A Diagnostic Benchmark for State Preparation, Information Access, and Evidence Use in Long-Context LLM Systems▲5.4k3.00
[PDF]EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL▼4.3k2.00
Withdrawn or desk rejected (2,919)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected