GSM8K

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses
   Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch.
2. Oct 8, 2026 · Research paper · 1 source
   Adversarial Cues in Decision Models Used as Judges: The Role of Request Presentation
   An answer judge instructed to grade the final commitment should reject an explicitly wrong final value even when an earlier value matches the reference.
3. Oct 7, 2026 · Research paper · 1 source
   Efficient Best-of-N policy evaluation for inference-time alignment
   Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model.
4. Oct 7, 2026 · Research paper · 1 source
   The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules
   We treat this keep-if-better step as selection under measurement noise, model the correlated errors of the candidates in a single decision, and study empirically what happens when the evaluation set is reused.
5. Oct 6, 2026 · Research paper · 1 source
   Few Bits, One Law: Toward W2A4KV2
   We introduce CanonQ, a unified quantization-aware training framework that addresses these challenges by separating source canonicalization from task-aware adaptation.
6. Oct 6, 2026 · Research paper · 1 source
   The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning
   We argue that pattern recognition and step-by-step reasoning are two ends of a spectrum.
7. Oct 6, 2026 · Research paper · 1 source
   Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling
   In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead.
8. Oct 6, 2026 · Research paper · 1 source
   Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes
   Ternary language models such as BitNet b1.58, Falcon-E and BitCPM are fine-tuned with higher-precision latent weights and deployed as ternary codes produced by an export step that, in the labs' documented pipelines, first casts the latents to bf16.
9. Sep 5, 2026 · Open-source release · 1 source
   sgl-project/sglang v0.5.19
   | Model | Type | PRs | Cookbook |
10. Aug 22, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.18
    | Model | Type | PRs | Cookbook |
11. May 26, 2026 · Open-source release · 1 source
    sgl-project/sglang v0.5.12.post1
    v0.5.12.post1 is a stability patch on top of v0.5.12.

Often appears with