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
149 results for “keyword:"scaling laws"” in ICLR 2027. 19 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]nUniMixer: Breaking the Barrier to a Unified and Scalable Backbone for Recommender Systems▼4.5k2.67
[PDF]Cross-Entropy Loss Falls Short: What Cross-Entropy Loss Reveals about Large-Language-Model Performance?▼1361.33
[PDF]DUEL: Exact Likelihood for Masked Diffusion Reveals Improved Pre-Training Scaling Laws▼4.5k2.67
[PDF]DEYES: Denoise Everything You Ever Saw — Pretrained Visual Priors for Spatiotemporal Monte Carlo Denoising▼1.2k3.00
[PDF]MolToken: Scaling a Molecular Foundation Model with Unified Graph Tokenization across Chemical and Biological Space▲3.0k2.33
[PDF]Tokenizer Distortion as a Floor: Compute-Optimal Visual Compression for Multimodal Pretraining▼1611.50
[PDF]TRAIL: An Efficient Industrial Ranking Framework via Interest Evolution and Target-Relevant Aggregation▲3952.67
[PDF]Specialist Drift: Continual RL for Capability-Preserving Foundation Model Post-Training▲6.1k2.00
[PDF]ELiT: An Expressive Lite Transformer for CTR Prediction with Error-Bounded Attention Approximation▲3.0k2.33
[PDF]LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation▼5.8k2.33
Withdrawn or desk rejected (19)
[PDF]The Price of Recurrence: Parameter Equivalence and Circuit Complexity in Token-Recurrent ModelsDesk rejected