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
1,970 results for “keyword:"text"” in ICLR 2027. 412 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond Position Bias: Shifting Context Compression from Position-Driven to Semantic-Driven▼4.5k2.67
[PDF]FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models▼1.1k3.25
[PDF]AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation▲3942.67
[PDF]GICAT: Goal-conditioned In-Context Action Translation for Generalizable Robot Manipulation▼4.3k2.00
[PDF]Quantize the Keys, Audit the Values: Retained-State Certificates for KV-Cache Compression▲3942.67
[PDF]Context Augmentation for Causal Foundation Models with Interventional Data and Domain Knowledge▼1.2k1.67
[PDF]RECAP-KV: Single-Prefill Approximation of Reconstruction Importance for Reusable KV Cache Eviction▲5.4k3.00
[PDF]Probabilistic Set Representations with Partial Optimal Transport for Image–Text Retrieval▼5.3k1.33
[PDF]Remembering What Changes the Future: Learning to Compress Agent Histories for Long-Horizon Tasks▼4.3k2.00
[PDF]TAME:Topology-Aware Text-Driven Motion Editing across Heterogeneous Humanoid Skeletons▼5.8k2.33
[PDF]Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation▼4.3k2.00
[PDF]Beyond Summarization: Semantic Context Handoff with On-Demand Evidence for Long-Horizon Agents▲9.2k2.67
[PDF]BCAR: Budgeted Concave Adaptive Retention for Query-Aware Context Compression in Long-Running Agents▲11.00
[PDF]SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection▼5.8k2.33
[PDF]Hidden Harm in Non-Atomic Demonstrations: Selective Counterfactual Component Intervention for Multimodal In-Context Learning▼5.8k2.33
[PDF]Better Conditioning, Better Motion: Generation-Oriented Text Representation Learning for Motion Generation▲5103.00
[PDF]CoStitch: Disentangled Color Style and Stitch Texture Generation for Controllable Embroidery Synthesis▼5.9k2.50
Withdrawn or desk rejected (412)
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Beyond Tokens: Read and Predict N-gram Spans with a Shared Dictionary for Genomic Foundation ModelsWithdrawn