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5,616 results for “area:"foundation or frontier models, including LLMs"” in ICLR 2027. 1,070 withdrawn or desk rejected listed apart.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]ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents▼5.8k2.33
[PDF]SEEING IS NOT RELATING: LEARNING RELATIONAL REPRESENTATIONS FOR MULTI-IMAGE UNDERSTANDING▼4.3k2.00
[PDF]DART: Decoded Attention over Recurrent States for Efficient Long-Context Sequence Modeling▲3942.67
[PDF]DivOPD: Spread Wide, Look Close for Asynchronous On-Policy Distillation of Multi-turn Agents▲43.67
[PDF]Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints▼4.5k2.67
[PDF]Accumulation Is Maintenance: Anti-Preferential Placement and Online Structural Curation for Hierarchical Agent Memory▲6.1k2.00
[PDF]GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives▲5103.00
[PDF]Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models▲6.9k4.00
[PDF]Not All Tokens Contribute Equally: Token-Level Reinforcement Learning for Multimodal Hallucination Mitigation▲9.2k2.67
[PDF]Semantic Flashlight: Plan-First Context Construction with Response-Adaptive Evidence Exposure for Deep Research▼4.3k2.00
[PDF]Relay, Don’t Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution▼4.3k2.00
[PDF]APL-OPSD: Instance-Adaptive Privileged Language Selection for Multilingual On-Policy Self-Distillation▲5.4k3.00
[PDF]Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation▼1.2k3.00
[PDF]ORDDAR: OBSERVATION- DRIVEN REASONING FOR DISTORTION- RESILIENT DECISION, ACTION, AND COGNITIVE RECOVERY▼1.2k1.67
[PDF]You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinement▼4.3k2.75
[PDF]TeachBack: Learning to Teach via Bidirectional Preference Optimization for On-Policy Self-Distillation▼4.3k2.00
Withdrawn or desk rejected (1,070)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