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3,104 results for “keyword:"ual"” in ICLR 2027. 948 withdrawn or desk rejected listed apart.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]Evidence-Aligned Multimodal On-Policy Self-Distillation for Fine-Grained Visual Understanding▼4.3k2.00
[PDF]EchoGhost: A Frequency-Structural Backdoor Attack and Spectral-Counterfactual Defense for Graph Neural Networks▼1361.33
[PDF]Beyond Image-Wide Color Shifts: Scene-Compatible Semantic-Region Triggers for Backdoor Attacks▼1361.33
[PDF]Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals▲3922.67
[PDF]TouchAnything: A Dataset and Framework for Bimanual Tactile Estimation from Egocentric Video▼11k2.33
[PDF]Benign Tasks, Unsafe Orders: The Local-to-Global Safety Gap in Continual LLM Fine-Tuning▼5.8k2.33
[PDF]Detect the Forgery, Not the Visual Disturbances: MLLM-Guided Representation and Selective Modulation for ID Document Images▲3922.67
[PDF]ANCHOR: Cross-Lingual Reasoning with Anchored Reinforcement Learning Under Accuracy-Language Trade-off▼4.3k2.00
[PDF]How Foundation Skills Boost Continual Vision-Language Learning: A Skill-Evolution Perspective▲3.0k2.33
[PDF]PixStain: Pixel-Space Diffusion with Cross-View Representation Alignment for Virtual Staining▲3.0k2.33
[PDF]Viscot-steer: Disentangling and Transferring Visual Chain-of-Thought via Activation Steering▲3.0k2.33
[PDF]Diagno-SV: Decoupling Perception, Reasoning, and Knowledge for Trustworthy Medical VLMs▲3922.67
[PDF]IBEC-MVC:INFORMATION BOTTLENECK EHANCED CONTRASTIVE MULTI-VIEW CLUSTERING VIA PROGRESSIVE MATRIX FACTORIZATION▼4.5k2.25
[PDF]D-BISR: Multi-Prototype Diffusion Residual Scoring for Target-Data-Free Harmful Prompt Detection▼1361.33
[PDF]RSCB: REGIONAL SEMANTIC CONTEXTUAL BANDIT FOR OPTIMAL SELECTION OVER LLM-GENERATED DYNAMIC CANDIDATES▼1361.33
[PDF]Which Internal Neural Representations Should Become Spikes? Task-Relevant Spatiotemporal Threshold Adaptation for Audio-Visual Spiking Neural Networks▼5.8k2.33
[PDF]S2AR: Dual-Axis Routing for Continuous Attribute Control in Visual Autoregressive Models▼5.8k2.33
[PDF]Not Just a Matter of Scale: Recovering Forensic Traces to Build a Forensic-Enhanced Vision Backbone▼4.3k2.00
[PDF]EgoExo-ViewCL: View-Labeled Continual Action Learning with Stable Analytic Anchors and View-Factorized Adaptation▲5103.00
[PDF]Learning When Cellular Responses Transfer: A Factorized Memory-Guided Agent for Perturbation Prediction▼4.3k2.00
[PDF]Re-Attending to the Missing Pieces: Test-Time Visual Evidence Refinement for High-Resolution Reasoning▲3922.67
[PDF]Adaptation Is Not Retention: Reframing Continual Low-Rank Adaptation through Response Coordinates▼5.8k2.33
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