Lexical reference frames read LM hidden states without a lens
LexFrame[1] reaches 0.97 coherence on SmolLM3-3B and OLMo3-7B, versus 0.30 and 0.35 for fixed lenses.
36
AI model
SmolLM3-3B
- Mentions · 7d0
- Mentions · 30d1
- All mentions5
- First seenSep 16, 2026
- Last mentioned28d ago
Timeline
5 articles · newest firstFrom Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
A study of Qwen3-1.7B shows multi-teacher on-policy distillation is shaped by averaging, Adam, and BF16 precision.
42
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
A distillation study shows averaging, Adam, and BF16 reshape how multi-teacher signals update student models.
40
QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency
QAM merges checkpoints to match sequential gradient descent through second order, with an O(h^3) error bound.
34
What Does Privileged Information Add to On-Policy Self-Distillation?
Study of on-policy self-distillation on 5,319 AMPLE-Math problems finds reference-free distillation drives most gains, with modest extra benefit from privileged references.
30
Appears with
- Qwen3-1.7Bai model · 3
- Hugging Facevendor · 1
- OLMo3-7Bai model · 1
- AMPLE-Mathproduct · 1
- OpenEuroLLM-Prelude-9Bai model · 1
- Alibabavendor · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.