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
5,613 results for “area:"foundation or frontier models, including LLMs"” in ICLR 2027. 1,073 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Understanding Reasoning Uncertainty in Workflow Optimization of Self-Evolving Agents: A Stochastic Search Perspective▲9.2k2.67
[PDF]Semantic Role Projection: Structured Visual Embeddings for Compositional Reasoning in Multimodal LLMs▼1.2k1.67
[PDF]Standard Data Scaling Analyses Obscure Loss of Important Information in Math Reasoning▼4.3k2.00
[PDF]Evidence, Not Independence: Reviewer Identity Alone Does Not Verify a Coding Agent's Claims▼1.2k1.67
[PDF]Shaping Latent Mixture-of-Experts: From Expert Geometry to Layerwise Capacity Allocation▼11k2.33
[PDF]HPOD: Hierarchical Preference Optimization via On-Policy Distillation for LLM Concept Unlearning
[PDF]Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding▼4.3k2.00
[PDF]Verification as a Budget: Posterior-Separation Scheduling for Self-Evolving Agent Skills▼4.3k2.00
[PDF]ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective
[PDF]HSS-DR: From Hidden-State Spectral Signatures to Object Hallucination Detection and Repair in LVLMs▲3.0k2.33
[PDF]Beyond Stable Convergence: Noise Covariance Design for Efficient Test-Time Scaling in Looped Models▼4.3k2.00
[PDF]Distilling Structure, Not Solutions: Structural Bottlenecks for On-Policy Self-Distillation▼4.3k2.00
[PDF]Spot the Difference: Detecting Hallucinations through Context-Head Intervention and Sparse Autoencoder Feature Contrasts▲9.2k2.67
[PDF]GrokRSI: Few-Shot Agentic Recursive Self-Improvement Through Qualified Task–Harness Co-Evolution▼4.3k2.00
[PDF]Task-Aware Configuration Selection for Preference Optimization via Early Training Dynamics▲3.0k2.33
Withdrawn or desk rejected (1,073)
[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