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
645 results for “keyword:"robustness"” in ICLR 2027. 171 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Escaping the Texture Trap: Intervention-Guided Adaptive RGB–Geometry Fusion for Indoor 3D Segmentation▲3.0k2.33
[PDF]PhysMark: Population-Guided Carrier Learning for Generalizable Physical-Channel Watermarking in 3D Gaussian Splatting▼1.2k1.67
[PDF]TS-AgentBench: Disentangling Feature Necessity from Robustness in Agentic Time-Series Forecasting▼1.2k1.67
[PDF]Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models▼4.3k2.00
[PDF]Counterfactual Fragility Certificates for Tabular Classifications: Guarantees and Limits▼1.2k1.67
[PDF]Same Requirements, Different Decisions: How Presentation Changes Which Requests LLM Agents Allow▼4.5k2.67
[PDF]Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning▼4.3k2.00
[PDF]Image Robustness Does Not Imply Video Robustness: The Limits of Single-Frame Evaluation▼5.8k2.33
[PDF]All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable … Attacks▲13k2.33
[PDF]Fine-tuning Disrupts Edit Readout: A Mechanistic Perspective on Model Editing Robustness▲143.33
[PDF]Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models▲5103.00
[PDF]OCG: Orthogonal Consensus Graph Learning for Robust Heterogeneous Graph Representations▼4.3k2.00
Withdrawn or desk rejected (171)
[PDF]Auditing Reward-Model Selection on Tool Trajectories: Identification, Policy Utility, and Natural TransferWithdrawn1.67
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected
[PDF]The Knowability Gap: Auditing When Better Models Cannot Replace Missing InformationDesk rejected