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
94 results for “keyword:"capability"” in ICLR 2027. 25 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Can Agents Safely Expand Their Capabilities? An Empirical Study of Trust Decisions in Autonomous Capability Discovery▲3.0k2.33
[PDF]SCALABLE: Scaling CApabilities Beyond the Best-of- Limit with Adaptive Boundary LEarning▼4.5k2.25
[PDF]Unseen Is Not New: Partial Identification of Capability Expansion in Reinforcement Learning with Verifiable Rewards▼1.2k1.67
[PDF]The Hidden Fragility of AI Safety: How Guardrails Can Weaken Cyber and Biological Resilience▼1.2k1.67
[PDF]Capability Budgeting: Acquiring Mathematical Reasoning While Retaining Capabilities in Multilingual Continual Pretraining▼1.3k1.75
[PDF]Don't Wear Too Many Hats: Capability Modularization for Multi-Document Analytical Question Answering▲5103.00
[PDF]Viscot-steer: Disentangling and Transferring Visual Chain-of-Thought via Activation Steering▲3.0k2.33
[PDF]Mixture of Outputs: Dynamic Decoding-Time Expertise Integration Between Large Language Models▼5.8k2.33
[PDF]Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation▼1.3k1.75
[PDF]Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination▼5.8k2.33
[PDF]When Atomic Constraint Application Does Not Compose: Diagnosing Constraint Composition Failure in LLMs▼1361.33
[PDF]Disentangling Safety and Capability in Large Language Models via Causal Interventional Decomposition▼1361.33
[PDF]Capability Calibration in Role-Playing Language Models: A Benchmark and Metacognitive Agentic Framework▲3.0k2.33
[PDF]Defending Multilingual Refusal Capability Against Three-Layer Cascading Attacks with Behavior-Invariant LoRA Distillation▼1.2k1.67
[PDF]Is This Agent Evaluable? Certifying Verdicts About LLM Agents Under Nondeterminism, Oracle and Coverage Obstructions▼1.2k1.67
[PDF]Specialist Drift: Continual RL for Capability-Preserving Foundation Model Post-Training▲6.1k2.00
[PDF]Self-Regression-Test:Continuous Integration for Self-Evolving Agents That Rewrite Their Own Skills▲5.4k3.00
Withdrawn or desk rejected (25)
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected
[PDF]Unified Multimodal Models Do Not Learn in Unison: Active Probing of Cross-Capability TransferWithdrawn1.33
[PDF]Enhancing Robustness through Repair-Oriented Honeypots and Selective Knowledge AggregationWithdrawn1.33
[PDF]High Influence Is Not New Influence: A No-Arbitrage Analysis of Multi-Capability Data SelectionWithdrawn2.00
[PDF]NavDBench: A Diagnostic Benchmark for Evaluating General Instruction‑Following Abilities of Navigation Foundation ModelsDesk rejected
[PDF]Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance ThrottlingWithdrawn1.67
[PDF]Beyond Single-Method Merging: Hierarchical Chains and Capability-Guarded Evaluation of LoRA ExpertsWithdrawn1.00