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
5,615 results for “area:"foundation or frontier models, including LLMs"” in ICLR 2027. 1,071 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss▼4.5k2.67
[PDF]Beyond the Canvas: Efficient dLLMs via Self-Guided CoT Compression and Suffix Sparsification▼5.8k2.33
[PDF]Schedule the Optimizer, Not the Teacher: Diagnosing and Mitigating Long-Horizon Collapse in On-Policy Self-Distillation▲3.0k2.33
[PDF]Rewarding Beliefs, Not Only Actions: Belief-Consistent Reinforcement Learning for Long-Horizon Agents▼1.2k1.67
[PDF]Helpful When Right, Controlling When Wrong: Causal Dependence on External Intermediate States in Small Language Models▼1361.33
[PDF]CostBit: Candidate-Cost-Informed Bit Allocation for Post-Training Quantization of LLMs▼5.8k2.33
[PDF]Gradient as Behavior Fingerprint: Stable Sequential Model Editing via Gradient Drift Regularization▲14k3.00
[PDF]Correct Yet Insensitive to Vision: Adaptive Intervention to Improve Visual Reliance in VLMs▲5103.00
[PDF]SAPS-COT: STEP-AWARE VISUAL GROUNDING WITH DYNAMIC RESIDUAL INJECTION FOR INTERPRETABLE MULTIMODAL REASONING▼1.2k1.67
[PDF]Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features▼5.8k2.33
[PDF]CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Skill–Policy Co-Evolution▲3922.67
[PDF]Attention Routing Stabilizes Early: Working-Set Inference for Recurrent-Depth Language Models▼13k2.00
[PDF]SuffiKV: Learning Sufficient Task States via Layer-wise KV Memories for Scalable Tabular Foundation Models▼1361.33
[PDF]BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems▼4.3k2.00
[PDF]Not All Tokens Deserve Equal Resolution: Score-Adaptive Indexing for Sparse Attention in Long-Context LLMs▲5103.00
Withdrawn or desk rejected (1,071)
[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