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
13,573 results for “keyword:"es"” in ICLR 2027. 3,307 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]M2E: Lightweight Motion-to-Emotion Inference for Edge-Oriented Micro-Expression Recognition▲9.2k2.67
[PDF]BeTAR: Belief-Guided Trajectory Learning with Agentic Reinforcement Learning for Multi-Degradation Surgical Image Restoration▲21.00
[PDF]From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain▲3762.67
[PDF]Normalize the Update, Not the Weights: Efficient Loss Weighting for Multi-Objective Pretraining▲3.0k2.33
[PDF]AgenticGNN: A Spectral-Inspired Agentic Framework for Automated Graph Learning Algorithm Design▼1611.50
[PDF]PixReenact: Pixel-Conditioned Causal Video Diffusion for Streaming Head-Avatar Reenactment▼5.9k2.33
[PDF]RetVDQ: Retrieval-Aware Variable-Depth Residual Quantization for Visual Document Retrieval▼5.9k2.33
[PDF]All you need to break LLMs are Black-Box, Adapting, Efficient, Transferable, Harmful, Applicable … Attacks▲13k2.33
[PDF]CRAVE: Recovering Progress from Repeated Demonstrations for Contact-Rich Robot Post-Training▼1351.33
[PDF]Beyond One-Step Accuracy: Trajectory, Invariant, and Dissipative Fidelity in Modelling of PDE Dynamics▲6.1k2.00
[PDF]GazeLens for Efficient Egocentric Video Question Answering with Simple Gaze-Driven Adaptive Token Reduction▼5.9k2.33
[PDF]Where to Verify, Where to Explore: Test-Time Reinforcement Learning with Confidence-Conditioned Verification▼5.9k2.33
[PDF]GaitReader: From Large-Scale Healthy Gait Pretraining to Cross-Center Disease Recognition▲5.4k3.00
[PDF]ComPass: Demand-Guided Latent Compression for High-Dimensional Time Series Forecasting▲9.2k2.67
[PDF]MedShard: Task-Structured Inference Improves Clinical Quality Control across Model Scales▼1611.50
[PDF]Cross-lingual Multi-view On-Policy Self-Distillation:Many Voices, One Model, No New Knowledge▼1.2k1.67
[PDF]Zero-LLM Trajectory Search over Line-Lifted Knowledge Graphs: Internalizing Query Decomposition for Multi-Hop RAG▲9.2k2.67
[PDF]FinEvolvingAgent: Self-Evolving Financial Deep Research Agent via Gradient-Guided Group Direct Preference Optimization▲21.00
[PDF]Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes▲5073.00
[PDF]Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning▲20k2.67
[PDF]Human–AI Disparity Distortion: A Component-Referenced Diagnostic for Hybrid Decision Systems▲9.2k2.67
Withdrawn or desk rejected (3,307)
[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