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
138 results for “keyword:"training dynamics"” in ICLR 2027. 35 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Not Order but Support: Curriculum Effects on Grokking Are a Transient-Support Phenomenon▲14k3.00
[PDF]The Rate Measure: How Far Linearisation Governs Training, and Why That Horizon Cannot Be Read▲11.00
[PDF]When to Switch: From Adversarial Training to ERM for Out-of-Distribution Generalization▼4.3k2.00
[PDF]What Behavior Cloning Gives and Takes: Action Learning and Visual Reorganization in VLAs▼1351.33
[PDF]Ideal Paths: Geometric Approximation of Logistic Gradient Descent Trajectories at Large Initialization▲13k2.33
[PDF]WHAT EMPIRICAL TRAINING DYNAMICS DO NOT DETERMINE: RELU HISTORIES AND ROBUST PREDICTION SEPARATION▼1351.33
[PDF]When Should Agents Differ? Learning to Schedule Behavioral Diversity from Training Dynamics in Multi-Agent RL▲3.0k2.33
[PDF]What Does a Training Token Buy? Contextual Information Gain Beyond Perplexity Across Open Model Suites▼1.2k1.67
[PDF]How Multi-Head Transformers Specialize for In-Context Learning: A Theoretical Analysis of Training Dynamics and Generalization▲2843.00
[PDF]Batch-Aware Hierarchical Routing for Mixture-of-Experts with Reduced Memory Traffic and Theoretical Guarantees▼1.2k1.67
[PDF]Imperfect Alignment, Reliable Similarity: Score–Encoder Separation in Multimodal Contrastive Learning▼1.2k1.67
[PDF]What Do INRs Find Difficult? Understanding and Exploiting Coordinate-Level Training Dynamics▼1.2k1.67
[PDF]Forward Similarity Does Not Guarantee Training Equivalence: Precision Placement in Differentiable Gram Solvers▼1.2k1.67
[PDF]Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary Supervision▲3.8k2.50
Withdrawn or desk rejected (35)
[PDF]Tracing How Backdoors Are Learned: Poisoned Sample Detection via Information-Trajectory DistortionWithdrawn1.33
[PDF]Data-Weight Directions Rotate Along Training: Horizon-Matched Attribution for GUI TrajectoriesWithdrawn1.33
[PDF]Learning to Be Fooled: pretraining grows knowledge but keeps the scar of framing susceptibilityDesk rejected
[PDF]Before the Breakthrough: Bottleneck Crossings as Precursors in Long-Horizon Agent RLWithdrawn2.00