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
1,051 results for “keyword:"control"” in ICLR 2027. 300 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]From Observation Prediction to Control Coordinates: Learning Differentially Flat Latent Representations▲3952.67
[PDF]ReCER: Recurrent Temporal Relation Refinement for Longitudinal Radiology Report Generation▼1.2k1.67
[PDF]OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, and Multi-Agent RL▼4.3k2.00
[PDF]FASTER: Fast Adjoint Stochastic Transport for Endpoint Refinement in Reward-Guided Image Editing▲5103.00
[PDF]Accuracy Is Not Evidence: Measuring and Training Evidence Dependence in Video Temporal Grounding▲3952.67
[PDF]The System Is Out of Control, but Causality Isn't: Leveraging Operational Shifts for Bivariate Causal Discovery▼4.5k2.25
[PDF]Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS▲3952.67
[PDF]When Tools Agree for the Wrong Reasons: Risk-Controlled Evidence Acquisition under Source Dependence▲11.00
[PDF]PhyAudioBench: Benchmarking Physical Consistency in Audio Generation through Controlled Interventions▼1361.33
[PDF]Do Not Disturb: When Plasticity Interventions Degrade Offline-to-Online Reinforcement Learning▲20k2.67
[PDF]Risk Control for Complete Evidence Actions: Uniform Authorization and Retrieval Limits▼4.3k2.00
[PDF]Dynamism of a Trajectory: Encoding Coarse Intent into the Source of Flow-Matching Policies▲143.33
[PDF]PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning▲1.7k3.33
[PDF]HOI-UP: Adapting Human-Object Interaction Motion to Unseen Object Properties without Property-Labeled Motion Data▲5103.00
[PDF]JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vectors Manipulation▼1611.50
[PDF]Transfer Asymmetry in Vehicle Pass-By Audio Synthesis: A Bidirectional Evaluation of PassByDiT and DopplerSim▼4.5k2.67
[PDF]CNLVerifier: A Controlled-Natural-Language Verifier for LLM-Driven Mathematical Reasoning▼4.3k2.00
Withdrawn or desk rejected (300)
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionWithdrawn2.00
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected