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
21 results for “keyword:"token selection"” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DART-VLA: Dynamic Action-Relevance Token Pruning for Efficient Vision-Language-Action Models▲3.0k2.33
[PDF]GRAIN: Gradient-Referenced Alignment of Informative Tokens for LLM Supervised Fine-Tuning▲3.0k2.33
[PDF]CoSelTune: Co-Designing Token Selection and Backward Computation for Efficient Long-Context Fine-Tuning▼4.3k2.00
[PDF]Keys Decide Attention, Values Decide Contribution: Value-Gated KV Cache Eviction at 20× Compression▼1351.33
[PDF]When Selective On-Policy Dstillation Rules Conflict: From Supervision Collapse to Minimal Repair▼1.2k1.67
[PDF]ASIR: An Agent-Structure-Aware Indexer with Block-Local Reuse for Native Sparse Attention▼4.3k2.00
[PDF]Seeing Action-Critical Evidence: Token Pruning with Internal Action Priors for Vision-Language-Action Models▲153.33
[PDF]Where to Look, What to Keep: Two-Phase Learning for Grounding-Aware Visual Token Selection▲4012.67
[PDF]Fund Regions, Not Tokens: Query-Conditioned Budget Allocation for Extreme KV-Cache Eviction in Vision-Language Models▲5103.00
[PDF]READ: Query-Relevant Evidence Retrieval for Visual Token Compression in Edge–Cloud VLM Inference▲5103.00
Withdrawn or desk rejected (11)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]GeoKV: Geometry-Aware KV Cache Compression via Global Structural Contribution and Key RectificationWithdrawn1.67
[PDF]SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language ModelsDesk rejected2.33