LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning Paper • 2606.01336 • Published 6 days ago • 7
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 10 days ago • 419
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts Paper • 2605.22641 • Published 16 days ago • 4
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Paper • 2605.22791 • Published 16 days ago • 31
Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution Paper • 2605.15138 • Published 23 days ago • 6
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 30 days ago • 233
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published May 3 • 166