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
33 results for “keyword:"specialization"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]GradRouter: Decompose Gradient Before Assigning Learning Responsibility in Sparse Mixture-of-Experts▼4.3k2.00
[PDF]Layer-Informed Fine-Tuning in LLMs: Functional Segmentation and Bottleneck Identification▼4.3k2.00
[PDF]PSDFusion: Prior-Guided Feature Specialization with Cross-Paradigm Distillation for Infrared-Visible Image Fusion▲4012.67
[PDF]When the Label Space Shrinks: Task-Adaptive Depth Compression via Recomputed Gradient-Residual Sensitivity▼1351.33
[PDF]SAMLens: Canonical Quality Can Hide Negative-Point Reversal in Specialized Segment Anything Models▲9.2k2.67
[PDF]Where Models Diverge: Linear Predictability Trace the Direction of Representational Change▼5.8k2.33
[PDF]Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients▼4.3k2.00
[PDF]Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation▼4.3k2.00
[PDF]Den2MoEE: Reconstructing Dense LLMs into Expert-Specialized Mixture-of-Experts for Efficient Embedding Models▲1.7k3.33
[PDF]Revenge of Monosemanticity: Neuron Specialization as a New Form of Feature Learning in MLPs▼4.3k2.00
[PDF]Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization▼5.8k2.33
[PDF]Split the World: Are Regional Dynamics Better Than Global Dynamics for Latent World Models?▼4.3k2.00
[PDF]Learn from Weaknesses: Student-aware Domain Specialization for Small Computer-Use Agents▼4.3k2.00
[PDF]Direct Spectral Actuation: Prediction-Preserving Expert Differentiation in Mixture-of-Experts▼4.3k2.00
[PDF]MASCraft: Multi-Agent Specialization through Role–Skill Composition and Self-Evolving Orchestration▲3.0k2.33
[PDF]From Traces to Guarded Programs: Evidence-Gated Compilation of Recurrent Agent Workflows▼1351.33
[PDF]Understanding Affective Adaptation in Multimodal Foundation Models: Emergent Functional Specialization▼5.9k2.50
Withdrawn or desk rejected (9)
[PDF]S2E: Dense Functional Differentiation in Feed-Forward Networks via Prototype-Guided Subspace ModulationWithdrawn2.33
[PDF]Different Noise Levels, Different Needs: Discovering Diffusion Phases for Efficient DistillationWithdrawn2.00