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
56 results for “keyword:"hallucination mitigation"” in ICLR 2027. 29 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CAVCD: Candidate-Aware Visual Counterfactual Decoding for Mitigating Object Hallucinations in Large Vision-Language Models▼1611.50
[PDF]Not All Tokens Contribute Equally: Token-Level Reinforcement Learning for Multimodal Hallucination Mitigation▲9.2k2.67
[PDF]Attention at Rest Stays at Rest: Breaking Visual Inertia to Mitigate Relation Hallucinations▲3952.67
Withdrawn or desk rejected (29)
[PDF]Reliable Memory Injection into Core Visual Attention Heads for Object Hallucination Mitigation in Large Vision-Language ModelsWithdrawn2.00
[PDF]TRAINING-FREE POSITIVE SPATIOTEMPORAL ENHANCEMENT FOR MITIGATING TEMPORAL HALLUCINATIONS IN VIDEO-LLMSWithdrawn2.00
[PDF]LIFE: LOCAL INTRINSIC DIMENSION-GUIDED FEATURE EDITING FOR ONE-TOKEN, ONE-LAYER HALLUCINATION REPAIR IN VISION-LANGUAGE MODELSWithdrawn1.67
[PDF]Risk Is Not Reward: Action-Relative Process Rewards for VLM Hallucination MitigationDesk rejected
[PDF]-VLM: Detecting and Correcting Vision-Language Hallucination via Active Representational Perturbation and Residual Spectral GroundingWithdrawn1.33