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
3,951 results for “keyword:"ad"” in ICLR 2027. 1,018 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DAPrune: Dual-Adaptive Pruning via Adaptive Ratio and Layer Selection for Large Vision Language Models▲9.2k2.67
[PDF]CAER: Cost-Aware Expert Replication for Load Balancing in Mixture-of-Experts Multimodal Large Language Model Training▼4.3k2.00
[PDF]AgentDriftBench: Measuring Adaptation Dynamics of LLM Agents under Mid-Evaluation Environment Drift▼1361.33
[PDF]EXACT WARM-STATE REUSE FOR HYBRID DIFFUSION LANGUAGE MODELS: CONTRACTS, SPEEDUPS, AND FAILURE BOUNDARIES▲3.0k2.33
[PDF]LoadCalib: Cognitive-Load-Calibrated Chain-of-Thought Synthesis for Small Language Models▲11.00
[PDF]Emergent, Coordinate-Specific Structure in Dense Parameter Updates for Continual Learning▲11.00
[PDF]When a Load-Balancing Loss Rewards Dead Experts: Sharp Global Geometry of Switch Routing▲133.33
[PDF]L-MoL: Mitigating Multilingual Interference via a Language-Guided Mixture of Low-Rank Experts▼5.9k2.50
[PDF]Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression▼1361.33
[PDF]Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations▲3912.67
[PDF]Toward Optimal Adversarial Attacks in Reinforcement Learning via Rate–Distortion Theory▼1.2k1.67
Withdrawn or desk rejected (1,018)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00