Daily papers

Systems 1

  1. 1 Tomer Solberg

    Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language Models

    Sable proves an integer-quantized LLM's exact token sequence in 92.5 seconds per 4,096 tokens, for audit-sensitive use.

AI engineering 5

  1. 1 ▲ 22 Lorenz K. Muller et al.

    MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

    Layer-local W4A4 quantization adds 2.3% vLLM overhead, useful when fitting models under tight GPU memory.

  2. 2 ▲ 57 Yukyeong Lee et al.

    Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

    Evidence-linked lessons let agents verify prior trajectories before acting, reducing errors from misleading or misapplied memory.

  3. 3 ▲ 10 Jack Lu et al.

    The Surprising Effectiveness of Deleting Weights in LLM Post-Training

    A learned binary mask matches full fine-tuning while changing under 0.05% of weights, useful for compact post-training updates.

  4. 4 Vikash Singh et al.

    Are Dense Rewards Worth Their Tokens in GRPO?

    Matched-compute tests found dense rewards lag GRPO by 14.3 points, while targeting near-uncertain prompts improved accuracy.

  5. 5 ▲ 14 Xiaohan Qin et al.

    DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

    Hierarchical KV sharing cuts cache by roughly one third and improves downstream scores, useful when designing deep models.