acceptodds: the papers of ICLR 2027
33,040 results for “keyword:"r"” in ICLR 2027. 8,260 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Conservation-Aware Fine-Tuning: Injecting Physical Laws into LLM Reasoning via Preference Optimization▼1351.33
[PDF]Beyond the Population Prior: Reliable and Amortizable Person Representations in Models of Human Decision-Making▼1351.33
[PDF]Benchmarking and Evaluating Implicit Biases in Single- and Multi-Agent Language Models▼5.9k2.33
[PDF]The Reference Is Part of the Signal: Structural Limits of Black-Box Sandbagging Detection▼4.3k2.00
[PDF]StrataTok: Local-Variation-Guided Dynamic Tokenization for PDE Forecasting from Sparse and Irregular Observations▼5.9k2.33
[PDF]More Than Correct Answers: Testing, Tracing, and Predicting Multi-Hop Execution in Transformers▲6.0k2.00
[PDF]The Privacy Fallacy of Crowdsourced Fine-tuning: Extracting Proprietary Data via Topic-Based Poisoning▲3.1k2.33
[PDF]Joint Branch-Space Transform Coding for Diffusion Activation Quantization with Classifier-Free Guidance▼4.5k2.67
[PDF]VeriGraphi: A Multi-Agent Framework of Hierarchical RTL Generation for Large Hardware Designs▲31.00
[PDF]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.1k2.33
[PDF]LoadCalib: Cognitive-Load-Calibrated Chain-of-Thought Synthesis for Small Language Models▲31.00
[PDF]SpeechAnchor: Enhancing Speech Large Language Models for Consistent Multi-Turn Spoken Dialogue▲9.3k2.67
[PDF]HRAE: One-Step Action Generation for Flow-Matching VLAs via Hierarchical Recurrent Action Expert▲3162.67
[PDF]TRACE: Transparent Reasoning through Aligned Concept Explanations in Clinical Reinforcement Learning▼1.2k1.67
[PDF]Theory-Driven Conceptualization and Implementation of Evaluation Metrics for Chart Editing▲3.1k2.33
[PDF]Learning composable time-unconditional molecular energy landscapes for zero-shot environmental transfer▼1.2k1.67
Withdrawn or desk rejected (8,260)
[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]Same-Checkpoint Intervention on Pre- and Post-Context States in Entity-Local Temporal EncodersWithdrawn1.33
[PDF]Pulse2View: Same-Sensor Cross-View Pre-Training for Patient-Level Multi-Disease Classification from Wearable PPGWithdrawn1.67