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
535 results for “keyword:"scaling"” in ICLR 2027. 84 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CANVAS: Adjustable Creativity Control in Large Language Models via Sparse Neuron Scaling▼4.3k2.00
[PDF]Parameter Conventions Confound Compute-Optimal Scaling Exponents of Dense Language Models▲5103.00
[PDF]SCALABLE: Scaling CApabilities Beyond the Best-of- Limit with Adaptive Boundary LEarning▼4.5k2.25
[PDF]A Pre-Registered Invariance Audit of Post-Hoc Out-of-Distribution Detectors under Exact Network Symmetries▼1361.33
[PDF]LatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents▼5.8k2.33
[PDF]Spend Less, Reason Better: Budget-Annealed Tree Search for LLM Agents that Spend Only on New Evidence▲3.0k2.33
[PDF]Revisiting the 16× Pretraining Compute Gap between Diffusion and Autoregressive Language Models▼4.3k2.00
[PDF]Hard, Not Rare: Human Item Difficulty, Not Concept Frequency, Orders Model Errors Across Professional Examinations▼5.8k2.33
[PDF]AdaptQuant: Hardware-Aligned Per-Tile MX Format Selection for Post-Training Quantization on NVIDIA Blackwell▲4.6k3.00
[PDF]nUniMixer: Breaking the Barrier to a Unified and Scalable Backbone for Recommender Systems▼4.5k2.67
Withdrawn or desk rejected (84)
[PDF]VeriVLA: Adaptive Test-Time Verification for Flow-Based VLAs with Latent World ModelsWithdrawn2.00
[PDF]Foreign Exchange and Proof Diversity: Which Failures to Borrow and Which Retries to BuyDesk rejected