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
300 results for “keyword:"attribution"” in ICLR 2027. 80 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]JailbreakProfiler: Fine-Grained Attack Pattern Recognition and Open-Set Attribution for LLM Safety▼5.8k2.33
[PDF]Which output absorbs the conflict? Gauge-aware attribution for feed-forward 3D reconstruction▼1.2k1.67
[PDF]What Does It Mean to Remove an Edge? Intervention-Aware Fidelity for Graph Neural Network Explanations▲3.9k1.75
[PDF]Yours or Mine? Misleading Latent Diffusion Model Attribution via Cross-Model Reconstruction▲5.4k3.00
[PDF]Disentangling Agent Contribution in LLM Multi-Agent Systems through Controlled Interventions▲5.4k3.00
[PDF]JACE: Judge with Attribution, Calibration, and Evaluation for Multimodal Audio-Video Generation▲3952.67
[PDF]Training-Free Failure Attribution in Multi-Agent Systems via Structured Trajectory Diagnosis▼1361.33
[PDF]Learning to Repair the Learner: Evaluating Recursive Improvement in Neuro-Symbolic World Models▼4.5k2.67
[PDF]Iterative distillation of Matryoshka sparse autoencoders improves hierarchical feature organization in ESMFold2▲11.00
[PDF]Which Updates Erase What the Base Model Knew? Optimizer-Conditioned Attribution of Reasoning-Support Loss in RLVR▼5.8k2.33
[PDF]Does My LLM Obey Me? Falsification-Based Attribution Tests for Prompt-Based Behavioral Conditioning▼1361.33
[PDF]Mary Had a Little [What?]: Decoding Can Matter More Than the Model Itself in Zero-Shot Detection▼5.8k2.33
[PDF]Testing Attribution Claims in Diffusion-LM Remasking: A Localized Effect Without a Demonstrated Benefit▼5.3k1.33
[PDF]Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents▼5.9k2.50
[PDF]Path-Space: Estimating Transformer Component Effects and Their Interactions from Shared Backward Passes▼5.8k2.33
Withdrawn or desk rejected (80)
[PDF]Frequency Attribution Mask: Toward Detector-Adaptive Robustness in AI-Generated Image DetectionWithdrawn2.00
[PDF]When Language Gains Are Not Semantic: Rethinking Attribution in Language-Supervised Representation LearningWithdrawn1.00
[PDF]Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level LabelsDesk rejected