Papers2

#long-form generation

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

Zecheng Tang, Baibei Ji et al.Jan 17arXiv

This paper builds MemoryRewardBench, a big test that checks if reward models (AI judges) can fairly grade how other AIs manage long-term memory, not just whether their final answers are right.

#reward models#long-term memory#long-context reasoning

Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules

Beginner

Amr Mohamed, Yang Zhang et al.Dec 2arXiv

Diffusion language models (dLLMs) can write all parts of an answer in parallel, but they usually take many tiny cleanup steps, which makes them slow.

#diffusion language models#early exit decoding#progress-aware threshold