Papers

• Progressive Cramming: Reliable Token Compression and What It Reveals (2026)
  Dmitrii Tarasov et al.
  5.01
• Surprisal Theory is Tautological (without Rational Grounding) (2026)
  Ryan Cotterell
  5.01
• Can a Language Model Learn Facts Continually in Its Weights? (2026)
  Charles O'Neill
  4.39
• The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning (2026)
  Ishan S. Kshirsagar
  4.39
• ResonatorLM: Causal Resonant Field Mixing for Efficient Long-Context Language Modelin (2026)
  Archie Chaudhury
  3.51
• Length Penalties Make Chain-of-Thought Less Monitorable (2026)
  Bryce Little
  3.51
• A scaling law of contextual persistence in human language (2026)
  Elan Barenholtz
  2.00
• Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors (2026)
  Jianfei Ma et al.
  2.00
• Localized Adaptation Reveals Distinct Learning Signatures in Transformers (2026)
  Rebecca Ramnauth et al.
  2.00
• Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (2026)
  Tommaso Cerruti et al.
  2.00
• Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition (2026)
  Geo Ahn et al.
  1.94
• Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations (2026)
  Hiskias Dingeto
  1.94
• Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context (2026)
  Keivan Alizadeh et al.
  1.78