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
19 results for “keyword:"contrastive decoding"” in ICLR 2027. 3 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TAVCD: TARGET-AWARE VISUAL CONTRASTIVE DECODING FOR HALLUCINATION MITIGATION IN VISION- LANGUAGE MODELS▼4.3k2.00
[PDF]Mitigating Scene Transition Misunderstanding in Video LLMs via Semantic-Shift-Aware Contrastive Decoding▼4.3k2.00
[PDF]Attention-Entropy Decoding with Visual Grounding for Hallucination Mitigation in Multimodal Large Language Models▲5.4k3.00
[PDF]CPD: Contrastive Perspective Decoding for First-Order False-Belief Answer Selection in Language Models▼1351.33
[PDF]DCLED: Dynamic Confidence-Aware Layer-wise Evolution Decoding for Factuality-Oriented Candidate Scoring▼4.3k2.00
[PDF]Rethinking Contrastive Decoding: Evidence Guided Branch Assignment for Multimodal Hallucination Mitigation▼1.2k1.67
[PDF]ACTIV: Reducing Spatiotemporal Hallucinations in Video Language Models through Token Interventions▲9.2k2.67
[PDF]TAKE THE HINT OR PUSH BACK? DECIDING WHEN A VISION-LANGUAGE MODEL SHOULD ACCEPT THE USER’S ANSWER▼1.2k3.00
[PDF]DeCoS: Decoding by Contrasting Steered Features Reduces Hallucinations in Large Language Models▼4.5k2.67
[PDF]DASH: Mitigating LLM Hallucinations via Dynamic Attention Steering in Hidden-Space for Contextual Faithfulness▲14k3.00
[PDF]BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA▼4.3k2.00
[PDF]HT-SCD: Self-Contrastive Decoding via Hallucination Trajectories for Mitigating Object Hallucinations in LVLMs▼1351.33