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
11,744 results for “keyword:"models"” in ICLR 2027. 2,927 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]SEFIR: Safety Detection in Frozen Multimodal Large Language Models via Internal Evidence Fusion▲3352.67
[PDF]Decoupling Outcome-Observation and Actor-Update Horizons in Reinforcement Learning with Verifiable Rewards▼4.5k2.67
[PDF]Coordinates Are Labels, Not Physics: Breaking the Coordinate Shortcut in Neural Surrogates▲1.9k3.67
[PDF]Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions▲3.1k2.33
[PDF]SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs▲3.1k2.33
[PDF]TriPoD: Triadic 3D CT Representation Learning via Physically Anchored Pretraining and Polarity-Debiased Text Alignment▼4.3k2.00
[PDF]MolToken: Scaling a Molecular Foundation Model with Unified Graph Tokenization across Chemical and Biological Space▲3.1k2.33
[PDF]The Doctor’s Casebook: When LLMs Reason by Patient Analogy via Information Gain–Guided Graph Search▼1.2k3.00
[PDF]Prune Once, Route per Turn: Constructing Persistent Visual Memory for Multi-Turn VLM Inference▼4.3k2.00
[PDF]CellBridge: Biologically Faithful Cell Morphology Prediction via Source-Conditioned Schrodinger Bridges▼4.3k2.00
[PDF]Learning Where and What to Optimize: From Diffusion Distillation to Reinforcement Learning▲1462.75
[PDF]DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch▼4.3k2.00
[PDF]Mixture of Outputs: Dynamic Decoding-Time Expertise Integration Between Large Language Models▼5.9k2.33
[PDF]FreeID: Calibrating Attention for Identity Preservation in Image-conditioned T2I Models▲4753.00
[PDF]The Model is Its Own Curriculum: Internal Difficulty Assessment for Self-Adaptive RL in Reasoning▲4753.00
[PDF]EviTime: Evidence-Guided Vision-Language Learning for Multimodal Time Series Forecasting▼1.2k1.67
[PDF]H-MPO: Hierarchical Multi-Response Preference Optimization with Modality-Guided Decoding for Omni Large Language Models▼5.9k2.33
[PDF]LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforcement Learning▲3352.67
Withdrawn or desk rejected (2,927)
[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