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
156 results for “keyword:"causal intervention"” in ICLR 2027. 47 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Why Do Language Models Take Shortcuts? A Mechanistic Account of Heuristic–Constraint Competition
[PDF]Present Action Is Not Persistent Write: Causal Rights of Optimizer History in Replay-Free Continual Learning▼71.25
[PDF]When Are Spectral Modes Causal? Identification Before Intervention in Learning Dynamics▼4.3k2.00
[PDF]Faithful Rules Are Not Enough: Boolean Surrogates for Deep RL and an Audit of Their Concepts▼4.5k2.67
[PDF]The Model Already Has a Dictionary: Cumulative SVD Features as a Training-Free Alternative to Sparse Autoencoders▲3952.67
[PDF]Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures▼4.3k2.00
[PDF]Who Grades the Edit? Frozen and Re-fit Readouts for Position Interventions in RoPE Models▼1361.33
[PDF]Disentangling Safety and Capability in Large Language Models via Causal Interventional Decomposition▼1361.33
[PDF]PRISM: Causal Counterfactual Minimization of Agent Tool Privileges via Information Bottleneck Role Induction▼4.3k2.00
[PDF]Helpful When Right, Controlling When Wrong: Causal Dependence on External Intermediate States in Small Language Models▼1361.33
[PDF]The Memorization Cost of Generalization: A Quantitative Causal Law in Noisy-Trained Deep Networks▲11.00
[PDF]WHAT DOES FFN COMPRESSION CHANGE DOWNSTREAM? SAME-STATE CAUSAL RESTORATION IN DIFFUSION LANGUAGE MODELS▼1361.33
[PDF]SightLine: What a Vision-Language Model Reads From an Image Is Not What It Answers From▲5.4k3.00
[PDF]When Is Component Sensitivity Compositional? A Causal Study of Neural Resource Allocation▼4.3k2.00
[PDF]When Worlds Outlive Scars: How Persistent Environments Carry History Across Agent Resets▼1.2k1.67
Withdrawn or desk rejected (47)
[PDF]Misplaced, Not Forgotten: Compressed Codes Map Unseen Attribute Combinations to Seen OnesWithdrawn1.67
[PDF]Phase Geometry of Reasoning: Predicting and Controlling Evidence Integration in Large Language ModelsWithdrawn1.33
[PDF]Believing Is Seeing: How VLMs Assemble Trust in an Image, and Where It Can Be ReadDesk rejected