SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space Paper • 2511.20102 • Published 30 days ago • 26
When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment Paper • 2509.00544 • Published Aug 30 • 11
Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? Paper • 2508.19827 • Published Aug 27 • 33
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation Paper • 2502.21074 • Published Feb 28 • 4
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems Paper • 2508.07407 • Published Aug 10 • 98
Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation Paper • 2508.05909 • Published Aug 8 • 21
Direct Preference Optimization Using Sparse Feature-Level Constraints Paper • 2411.07618 • Published Nov 12, 2024 • 17