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
3,104 results for “keyword:"ual"” in ICLR 2027. 948 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning▲6.8k3.67
[PDF]How to Crack the Black Box of Emotion Generation? Interpretable Dual-Path Function Vectors for Token-Level Control▲6.1k2.00
[PDF]DoMA: Geometry-Aware Aggregation for Stable Continual Federated Fine-Tuning on the Heterogeneous Edge▼1.2k3.00
[PDF]Exploring and Mitigating Object Hallucination with Non-Autoregressive Vision-Language Models▼4.3k2.00
[PDF]Fidelity Where You Look, Realism Everywhere: Attention-Guided Additive Fidelity Allocation for Generative Image Compression▲3912.67
[PDF]Residual-Aware Neural Spectral Capacity: Allocating Capacity across the Network from Architecture Specification Alone▲2843.00
[PDF]Identifying Bias Directions from Population Residuals in Reference-shifted Deconvolution▼4.5k2.67
[PDF]Pairwise-Safe, Jointly-Unsafe: Higher-Order Residual Risk in Parallel Decoding of Diffusion Language Models▼1361.33
[PDF]CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs▼5.8k2.33
[PDF]Where to Refine and What to Recover: Disentangled Cross-modal Semantic Alignment for CT-to-PET Generation▼1.2k1.67
[PDF]Where to Apply Privilege: On-Policy Self-Distillation with Textual Privilege for Multimodal LLMs▼5.8k2.33
[PDF]HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data▼1.2k1.67
[PDF]VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining▼5.8k2.33
[PDF]Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training▲6.1k2.00
[PDF]RIDER: SUPPORT-AWARE ANALYTICAL EVIDENCE CONSTRUCTION FOR REHEARSAL-FREE CLASS- INCREMENTAL LEARNING▲3912.67
Withdrawn or desk rejected (948)
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Matched Counterfactual Attribution: A Controlled Evaluation of Data Selection for Video Instruction TuningDesk rejected2.00
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Curvature Controlled Mixing on the Interpolation Manifold: Sharp Cutoffs in Late-Phase Training DynamicsDesk rejected
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33