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
11,173 results for “keyword:"ct"” in ICLR 2027. 3,081 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]WHY SUBLIMINAL LEARNING NEEDS SO MUCH DATA: A NOISY INVERSE VIEW THROUGH STEERING VECTOR RECOVERY▲3342.67
[PDF]Graph Convolutional Networks Achieve Information-Theoretic Limits under Stochastic Block Models with Non-Informative Node Features▲14k3.00
[PDF]Compression-Aware Fine-Tuning: Adapting Language Model Weights to a Frozen Cache Bottleneck▼4.3k2.00
[PDF]SEED: Subject-to-Edge Exploration and Distillation for Unsupervised Camouflaged Object Detection▼5.9k2.33
[PDF]HOW MUCH SCHEMA CAN A READER USE? CAPACITY-ADAPTIVE TEST-TIME EXPOSURE FOR OUT-OF-DOMAIN MULTI-INTENT DETECTION▲3342.67
[PDF]TRUSTCONS: EXACTLY VERIFYING CONSISTENCY, COMPLETENESS , AND CONDITIONED RE-ENUMERATION IN LANGUAGE MODELS▼1361.33
[PDF]Same Groups, Different Values: Decomposing Step-Level Credit Assignment for LLM Agents▲6.0k2.00
[PDF]nUniMixer: Breaking the Barrier to a Unified and Scalable Backbone for Recommender Systems▼4.5k2.67
[PDF]CALIPER: Compute-Aware Local Intervention and Targeted Policy Updates for Tool-Augmented Agents▼1.2k1.67
[PDF]MambaX‑AD: Region‑Aware Contrastive Learning with Mamba-CNN Cross‑Modulation for Multimodal Anomaly Detection▼4.3k2.00
[PDF]What to Learn and Who to Ask: Adaptive Curriculum and Expert Allocation for Interactive Imitation▲4743.00
[PDF]Where Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts▲31.00
[PDF]Scalable Audit and Mitigation of Intersectional Fairness Bugs in VLMs with Combinatorial Interaction Testing▲6.0k2.00
[PDF]From Physics to Experiment: Learning Resolution-Controllable Cryo-EM Density with Structured Diffusion▲9.3k2.67
[PDF]Beating the Worst-Case Per-Iteration Update Time: A Novel Dynamic Network Simplex Method for Optimal Transport▲3.0k2.50
[PDF]AsymStego: Exploiting Information Asymmetry to Bypass Content-Level Auditing in LLM Agents▲3342.67
[PDF]ACT-SNN: Activity-Constrained Two-Stage Conversion for Efficient Spiking Large Language Models▲3342.67
[PDF]Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution▲3.1k2.33
Withdrawn or desk rejected (3,081)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]NEAR-Bench: Benchmarking Predictive Performance and EEG Input Dependence in EEG-to-Text DecodingWithdrawn2.00