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
318 results for “keyword:"trajectory"” in ICLR 2027. 79 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning to Teach, Learning to Play: Dual Reinforcement Learning with Active Trajectory Inquiry▼4.3k2.00
[PDF]FlowPlan: Flow-Matching Trajectory Planning Guided by Counterfactual Interaction Consequences▼5.8k2.33
[PDF]When Does an Edit Become Unsafe? Tracing Safety Emergence Along the Generative Trajectory of Image Editing Models▼4.3k2.00
[PDF]Lifetime: KV Cache Eviction from Attention Trajectories for Long-Context Language Models▼4.3k2.00
[PDF]Track-OPD: Learning from Future Consequences for Multi-Object Tracking via On-Policy Distillation▼4.5k2.67
[PDF]Minimal Repair Subtrajectories: Verifier-Certified Local Recovery for Long-Horizon Agents▼1.2k1.67
[PDF]SEAM: Shared-Expert Adaptation Masked by Closed-Loop Scores in Reward Fine-Tuned Diffusion Planners▲3.0k2.33
[PDF]AUDITING TEST-TIME TRAINING IN STREAMING 3D RECONSTRUCTION: SCALE-INVARIANT UPDATES, LARGE WEIGHT CHANGES, SMALL POSE EFFECTS▲3972.67
[PDF]HorizonLoRA: Distilling Motion Adapter Banks for Trajectory-Conditioned Video World Models▲11.00
[PDF]StyleFinger: Learning Vehicle-Level Interaction Tendencies for Controllable Scenario Generation in Autonomous Driving Testing▼1.2k1.67
[PDF]Where to Go and How to Move: Goal–Motion Latent Flow for Multimodal Trajectory Prediction▼4.3k2.00
[PDF]Projection-Based Alignment with a Fractional Trajectory Metric for Time Series Forecasting▼5.8k2.33
[PDF]Simulate, Don't Interpolate: Recovering Continuous Spatial Dynamics from Discrete, Unpaired Snapshots▼4.5k2.67
[PDF]MetricFly: Numerical Instruction Following via Action-Conditioned Calibration for UAV Vision-Language-Action Models▼5.8k2.33
[PDF]The Sensing Gap: Counterfactual Trajectory Forks for Contract-Relative Pre-Commitment Sensing▼1361.33
[PDF]GraphFM: Graph-Constrained Flow Matching for Dynamics Reconstruction from Temporal Snapshots▲3.9k1.67
[PDF]RethinkDrive: Supervision Targets for Lightweight Trajectory Refinement in End-to-End Driving▼4.3k2.00
[PDF]Segment-Delta: Exact and Scalable Replacement Refinement for Trajectory Simplification▲5.4k3.00
Withdrawn or desk rejected (79)
[PDF]Auditing Learned Mean-Field Equilibrium Claims: Claim-Conditioned Response and Flow EvidenceWithdrawn1.67
[PDF]When Should an Agent Trust a Reward? Trajectory-Supported Learning under Corrupted Reward ObservationsDesk rejected2.00
[PDF]Limits of Surprisal-Based Self-Evaluation: Non-Identifiability of Reasoning Correctness from Single-Model Output ProbabilitiesDesk rejected
[PDF]scUGPT: Gene-wise Response Curves Along a Supplied Single-Cell Trajectory AxisDesk rejected2.00