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
412 results for “keyword:"uci"” in ICLR 2027. 140 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision▼1.2k1.67
[PDF]When Answers Stray from Questions: Hallucination Detection via Question-Answer Orthogonal Decomposition▲5.4k3.00
[PDF]Erase It Where You Found It: Matched-Position Erasure Lowers Demographic Dependence at a Measured Cost▼4.3k2.00
[PDF]Certify Before You Intervene: Pathwise Intervention-Certified Decoding for Multimodal Generation▼5.8k2.33
[PDF]Better Fixed-State Fidelity Need Not Improve Closed-Loop Performance in Quantized Neural Policies▼1361.33
[PDF]Grounded-R1: Reinforcement Learning for Preemptive Hallucination Intervention and Grounded Generation▲3.0k2.33
[PDF]REIN: Bridging the Gap Between Reasoning and Reliability via Reflection and Abstention Alignment▲3952.67
[PDF]A Free Knob: Decoupling Calibration and Predictive Skill in Threshold-Based Evaluation▼4.3k2.00
[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs▼12k1.67
[PDF]HSS-DR: From Hidden-State Spectral Signatures to Object Hallucination Detection and Repair in LVLMs▲3.0k2.33
[PDF]Spot the Difference: Detecting Hallucinations through Context-Head Intervention and Sparse Autoencoder Feature Contrasts▲9.2k2.67
[PDF]Works Where Calibrated, Fails Where Misused: Auditing Small-Scale Pretraining's Seed-Noise Instruments▼4.3k2.00
[PDF]Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs▼1361.33
[PDF]DLIPS: Detecting Hallucinations in Large Language Models via Temporal Lipschitz Dynamics▼4.3k2.00
[PDF]Temperature and Truncation Do Not Commute: Exact Conditions for Order-Independent Decoding▼4.3k2.00
[PDF]When is seeing enough? Cross-granularity evidence search with Sufficiency verification for High-resolution understanding▼4.5k2.67
[PDF]Beyond Relevance: State-Conditioned Consequence Modeling for Adaptive Retrieval-Augmented Generation▼1.2k1.67
[PDF]NMR-CRAFT: Structure Elucidation through Bidirectional Modeling and Fragment Recombination▲4.6k3.00
[PDF]Distilling Answers, Discarding Uncertainty: Uncertainty Collapse in Sequence-Level Knowledge Distillation▼1.2k1.67
[PDF]GROUNDING BEFORE SPEAKING: CROSS-MODAL REFLECTIVE ROUTING FOR HALLUCINATION-RESILIENT MULTIMODAL LARGE LANGUAGE MODELS▲3.9k1.67
[PDF]BRIDGE: Bi-subspace Residual Guidance for Spectral Representation Editing towards Truthful LLMs▲6.1k2.00
[PDF]When More Seeing Does Not Help: Understanding and Mitigating Hallucinations in Think-with-Images Models▲5103.00
Withdrawn or desk rejected (140)
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33
[PDF]Contrastive Trajectory-Guided Visual Evidence Reinforcement for Hallucination MitigationWithdrawn2.00
[PDF]GRA: Grounding Ratio Analysis for Prompt-Anchored Update Trajectories in Hallucination DetectionWithdrawn1.67