Unverified50% confidenceBenchmarkExact time
A compact language model trained from scratch jointly generates backbone and sequence on ProTok tokens, with 52% of the sampled backbones being designable, whereas the parameter-matched GeoBPE baseline achieves only 21%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
VerifiedZero-shot classification relies on the semantic understanding capabilities of pretrained large language models such as NLI variants of BART and RoBERTa.64% similarUnverifiedNonobench is an open-source benchmarking project that has 49 large language models solve nonogram/picross puzzles.63% similarUnverifiedZero-shot models require no labeled data; simply writing out labels in natural language is enough to produce classification results.58% similarUnverifiedDiscrete masked diffusion draws on BERT's masked language modeling idea—randomly masking and restoring sequences during training and iteratively filling in from a fully masked sequence at inference—with representative works including MDLM and SEDD.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023976API
curl https://kongchang.com/api/v1/knowledge/claims/1023976MCP
get_claim(id=1023976)