{"total":22,"rows":[{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2601.22950","title":"Perplexity Cannot Always Tell Right from Wrong","created":"2026-01-30","cited_by_count":9,"area":null},{"id":"2605.15514","title":"RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably","created":"2026-05-15","cited_by_count":8,"area":null},{"id":"2602.17929","title":"ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging","created":"2026-02-20","cited_by_count":7,"area":null},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2512.14391","title":"RePo: Language Models with Context Re-Positioning","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2606.20097","title":"HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization","created":"2026-06-18","cited_by_count":4,"area":null},{"id":"2604.15180","title":"AdaSplash-2: Faster Differentiable Sparse Attention","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2604.27263","title":"Decoupling the Benefits of Subword Tokenization for Language Model Training via Byte-level Simulation","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2605.21803","title":"Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.00906","title":"hZACH-ViT: Curved Latent Geometry for Compact Vision Transformers in Low-Data Medical Imaging","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.31585","title":"DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.11909","title":"Disentangling the Expressivity of RoPE","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2604.18603","title":"Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.24715","title":"Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.21249","title":"Does RoPE Prevent or Degrade Retrieval Heads? A Mechanistic Analysis Across Model Families","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.22575","title":"Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.20069","title":"V-REX: Efficient Specialist VLM Training for Veterinary X-Rays","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.29715","title":"Higher-Dimensional Rotary Position Embedding","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.30784","title":"Symbiotic Architecture for Post-Hoc Audio Extension of Frozen Language Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38530","title":"Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04791","title":"Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}