information bottleneck
- Papers
- 3
- Released code
- 0
- First seen
- Sept 2026
- Latest
- Nov 2026
3 papers in the last two months, against 0 in the two before.
Start here
The paper to read first- 1AI avatars can copy face and body movements in real time
A feed-forward transformer learns a compact motion embedding for real-time whole-human animation.
Nov 2026
How fast it is moving
Often studied with
context compactionCompressing or summarizing an LLM's past context into a smaller representation to extend memory and improve reasoning within limited token budgets.1 togethercontrastive alignmentA method that learns embeddings by minimizing distance between positive pairs and maximizing distance between negative pairs.1 togethercounterfactual reasoningComparing actual outcomes with imagined alternatives to estimate the effects of different actions or conditions.1 togetherThe papers
Most central to this idea first, not most recent.
- Big Techcs.CV
AI avatars can copy face and body movements in real time
A feed-forward transformer learns a compact motion embedding for real-time whole-human animation.
NVIDIA, Seoul National University · Nov 2026
- Big Techcs.AI
FOCUS Compresses Agent Histories While Preserving Future Decisions
FOCUS cuts peak context by up to 48% and improves task success by up to 8.9 percentage points without training.
M365 Research, Microsoft · Sept 2026
- Research Labcs.LG
Spectral hybrid parameterizations robustly accelerate flow matching optimization
Hybrid spectral parameterizations for flow matching that adapt across time and data covariance directions accelerate optimization with no extra training cost.
Inria, ENS de Lyon · Oct 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.