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
5,612 results for “area:"foundation or frontier models, including LLMs"” in ICLR 2027. 1,074 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TRIM: Temporal-subspace Reconstruction Induced by Moments for Post-Training Structured Pruning of Spiking Neural Networks▲5.4k3.00
[PDF]Residual-Aware Neural Spectral Capacity: Allocating Capacity across the Network from Architecture Specification Alone▲2833.00
[PDF]InEx: Intrinsic and Extrinsic Evidence for Trustworthy Evaluation of Latently Verifiable Tasks▲352.75
[PDF]Parameter Conventions Confound Compute-Optimal Scaling Exponents of Dense Language Models▲5093.00
[PDF]The Hit Is (Almost) Always Cheaper: Prefix-Cache Economics on Bandwidth-Rich, FLOPs-Poor Accelerators▼1.2k1.67
[PDF]Melo: A Cognitive Science–Inspired Closed-Loop Long-Term Memory Framework for AI Agents▼1.2k1.67
[PDF]Pairwise-Safe, Jointly-Unsafe: Higher-Order Residual Risk in Parallel Decoding of Diffusion Language Models▼1361.33
[PDF]SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask▼1.2k1.67
[PDF]Never Evict Always Taper: A Static Logarithmic Bit-Width Schedule for KV Cache Quantization▲11.00
[PDF]CUDACoach: Guiding CUDA Kernel Optimization with Diverse Strategies Learned from Verified Code▼4.3k2.00
[PDF]CVIF: A Criticality-Driven Visual Intervention Framework for Geometric Diagram Understanding in MLLMs▼5.9k2.33
[PDF]Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization▲1.7k3.33
[PDF]Where to Apply Privilege: On-Policy Self-Distillation with Textual Privilege for Multimodal LLMs▼5.9k2.33
[PDF]Source References Fail to Constrain Inference: Diagnosing Source Misbinding in Multi-Image Contexts▼1361.33
[PDF]EchoSpec: Efficient Target-Integrated Speculative Decoding via Output-Projection Adaptation and Post-Target Refinement▼5.9k2.33
[PDF]TempoQuant: Timestep-Aware Calibration for Post-Training Quantization of Masked Diffusion Language Models▼4.3k2.00
[PDF]IKBQA-R1: Reinforcing Large Language Models for Question Answering over Incomplete Knowledge Graphs▲3.0k2.33
Withdrawn or desk rejected (1,074)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]When to Act, Not What to Act: Prospective Authorization for Tool-Using Language ModelsWithdrawn1.33
[PDF]Exploring Expert Concentration for Parameter-efficient Fine-tuning of Mixture-of-Expert LLMsWithdrawn1.67
[PDF]Beyond Tokens: Read and Predict N-gram Spans with a Shared Dictionary for Genomic Foundation ModelsWithdrawn
[PDF]CCQ: Compensation-Conditioned Quadratic Selection for Absorbing Skipped Experts in MoE LLMsWithdrawn2.00