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
5,616 results for “area:"foundation or frontier models, including LLMs"” in ICLR 2027. 1,070 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AID: Asymmetric Intermediate-Answer Distillation for Budget-Constrained Long-CoT Inference▼4.5k2.67
[PDF]Relative Capability Organizes the Geometry of Answer Distributions in Test-Time Scaling▼4.5k2.67
[PDF]Beyond Token-Average Loss: Rebalancing Control and Binding in Agent Policy Distillation▼1.2k1.67
[PDF]Prompt Search Is Not Prompt Expressivity: Continuous Prompts Beat GEPA, MIPROv2 and SIMBA, and an Exact Vocabulary Frontier▼1361.33
[PDF]Training-Free Failure Attribution in Multi-Agent Systems via Structured Trajectory Diagnosis▼1361.33
[PDF]Rewriting Is Forgetting: Zero Rewrite Capture and Budgeted Reading for Long Horizon Agent Memory▼1361.33
[PDF]SLICE-Mem: Salience-Gated Lightweight Information Curation for Efficient LLM Agent Memory▼4.3k2.00
[PDF]When the Evaluator Changes: Measuring False Progress in Self-Improving Language Models▼5.8k2.33
[PDF]Frequencies Rank, Probabilities Allocate: Calibrated Draft Trees for Drafter-Free Speculative Decoding▲3952.67
[PDF]NuAlign: A Numerical Distance Perception Alignment for Large Language Models as Evaluators▲3.0k2.33
[PDF]Rethinking KL Regularization in RLHF: From Wrong Value Estimation to Correct Gradient Optimization▼1361.33
[PDF]VasoDPO: Aligning Treatment Actions with Patient States through State-Fixed Preference Construction▼4.5k2.25
[PDF]PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction▲6.1k2.00
[PDF]The Emperor's New Scaffold: Semantically Equivalent Harnesses Reshuffle the Leaderboard▼4.3k2.00
[PDF]LCRA: Local Attention with Hierarchically Routed Coarse-Residual Memory for Long-Context Retrieval▼4.3k2.00
[PDF]Adaptive View Harness: Learning to Select Target-Preserving Views for Large Language Models▼71.25
[PDF]Teach Only What Is Missing: Frontier-Calibrated Counterfactual Self-Distillation for Multilingual Reasoning▼4.5k2.67
[PDF]Certified but Not Useful: An Information-Theoretic Ceiling on LLM-Based Mathematical Discovery▼1.2k1.67
[PDF]When Situations Take Effect: Psychological Situation Modulation for Personalized Dialogue Generation▼4.3k2.00
[PDF]A Unified Information-Geometric Framework for Collective Belief Dynamics in Multi-Agent LLMs▼1361.33
Withdrawn or desk rejected (1,070)
[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