Claims Browser

LLM-generated text now exhibits at least 38 identifiable clichéd patterns

"My LLM cliché highlighter is up to 38 patterns now"

There are now 38 identifiable patterns of clichéd language produced by LLMs

"My LLM cliché highlighter is up to 38 patterns now"

MAELLE naturally recovers mechanistic trajectories that align with known chemistry and can predict side products of a reaction

"because the learned flow operates over the full electron redistribution, MAELLE naturally recovers mechanistic trajectories that align with known chemistry and can predict side products of a reaction."

MAELLE maintains strong performance in out-of-distribution settings where existing methods degrade

"we evaluate robustness across two out-of-distribution settings - structural complexity and reaction type - and find that MAELLE maintains strong performance where existing methods degrade."

MAELLE achieves competitive performance on the USPTO-480K benchmark compared with leading reaction prediction models

"MAELLE achieves competitive performance on the USPTO-480K benchmark compared with leading reaction prediction models."

On DNA-to-amino-acid transduction, the method reduces runtime by several orders of magnitude compared to threshold-pruned beam summing and makes estimating prefix probabilities for long target strings feasible

"On a DNA-to-amino-acid transduction, it reduces runtime by several orders of magnitude relative to threshold-pruned beam summing and makes estimating prefix probabilities for long target strings feasible."

The proposed beam-summing algorithm achieves better compute-variance tradeoff on text and lower error on DNA compared to sequential Monte Carlo baselines

"We evaluate the method on encyclopedic text and DNA against sequential Monte Carlo baselines that resample with replacement. It achieves a better compute--variance tradeoff on text and lower error at the same maximum number of particles on DNA."

Resampling source prefixes without replacement and reweighting by inverse inclusion probability gives an unbiased estimator of target prefix probability in TLMs

"Instead, we resample source prefixes without replacement and reweight each selected prefix by the inverse of its inclusion probability. We show that applying this correction recursively gives an unbiased estimator of the target prefix probability and lets us estimate the mass lost by threshold pruning."

Transduced language models can compute target prefix probabilities by composing a pretrained source language model with a functional finite-state transducer

"Transduced language models (TLMs) compose a pretrained \emph{source} language model with a functional finite-state transducer to induce a language model over \emph{target} strings."

The Latent Advertiser Mixture Auction (LAMA) mechanism satisfies Markov DSIC and IR properties while achieving near-optimal KL-regularized welfare

"We show that LAMA satisfies Markov DSIC and IR, and achieves near-optimal KL-regularized welfare."

Machine learning fails as a predictor for nitrogen rate optimization in winter wheat, with no model able to recover the best rate within farm tolerance

"On this bench, machine learning fails as a predictor. No model recovers the best rate within farm tolerance, and the benchmark noise shows none can."

At normal prices, every machine learning model loses to standard advice on profit for nitrogen rate optimization

"At normal prices, every model also loses to the standard advice on profit."

A simple correction step applied after the machine learning model cuts profit losses by 25%, while better models and extra features provide no additional gain

"A simple correction step applied after the model cuts profit losses by a quarter, while better models and extra features give no gain."

Accurate prediction does not by itself make recommended nitrogen rates more profitable

"However, it is usually judged on prediction accuracy, and accurate prediction does not by itself make the recommended rate more profitable."

Foundation models that use a full year of Earth observations can have their embeddings recomputed over much shorter windows (down to a single day) while retaining substantial value for land-use/land-cover mapping

"Keeping the encoder frozen, we recompute its embeddings over varying observation windows, from a full year down to a single day."

For phenology-separated classes like crop types, Tessera embeddings achieve 46% better performance than the best from-scratch models

"Where classes are separated by phenology, as for the crop types of PASTIS-R, they reach a mean Intersection-over-Union of $58.3$, about $46\%$ above the best from-scratch model."

Tessera embeddings remain markedly more label-efficient than from-scratch models even when classes are temporally stable

"On both datasets, Tessera embeddings remain markedly more label-efficient."

Contracting the observation window from one year to one month costs 39% of segmentation accuracy on crop classification but only 5% on stable land cover classes

"Contracting the window from one year to one month costs $39\%$ of the segmentation accuracy on PASTIS-R but only $5\%$ on DynamicEarthNet."