Claims Browser

HALO improves zero-shot open-set accuracy by 13.7 percentage points over MOMENT across 87 training labels

"HALO improves zero-shot open-set accuracy, measured over all 87 training labels, by 13.7 percentage points"

All models including HALO fail in zero-shot settings when faced with severe distribution shift on certain datasets

"On two further datasets with severe distribution shift, every model including HALO collapses zero-shot"

Language-aligned training with synonym-aware soft contrastive learning enables open-set recognition without per-dataset classifiers

"aligns this IMU encoder with text embeddings via synonym-aware soft contrastive learning, enabling open-set recognition via cosine-similarity retrieval without per-dataset classifiers"

Adverse drug reactions are a major, largely preventable source of patient harm

"Adverse drug reactions (ADRs) are a major, largely preventable source of patient harm."

A smartphone-based safety-check system using image capture and drug reference matching can provide allergy alerts in resource-constrained hospital settings

"This paper proposes and outlines the evaluation of a lightweight, smartphone-based safety-check system for this setting. At registration a soft identifier (a phone number) is recorded; after the physician writes a prescription, its image is captured, the brand names are resolved to active ingredients using national drug references, and the ingredients are matched against the patient's recorded severe reaction history."

Retrieval-based systems that are silent by default and only flag high-risk matches are more appropriate than predictive systems in high-volume clinical settings due to alert fatigue concerns

"The system is retrieval-based rather than predictive, and is silent by default, raising a flag only for high-risk matches a design grounded in the alert-fatigue literature."

The low base rate of severe adverse drug events places clinical-outcome effects beyond the scope of a single-site feasibility study

"We explicitly do not claim a clinical-outcome effect, which the low base rate of severe events places beyond a single-site feasibility study."

Deep transformers remain relatively underexplored in tabular data applications compared to computer vision and natural language processing

"While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored."

Transformer models remain resilient to performance drops when low-importance attention heads are removed in 72.5% of tabular dataset experiments

"In 72.5\% of experimental examples, the model remains most resilient to performance drops when heads with the lowest importance scores are gradually removed."

Removing the most important attention head first causes the greatest reduction in classification performance

"removing the most important attention head first results in the greatest reduction in classification performance"

Important attention heads are scattered across layers without consistent layer-specific patterns in tabular transformers

"A closer look at individual head importance scores across six attention layers reveals that important heads are scattered across layers, with no consistent layer-specific trends."

Attention head importance varies considerably across different tabular datasets, unlike in image and language domains

"In contrast to the image and language domains, the importance of individual attention heads varies considerably across tabular datasets with different schemas and feature spaces."

Head importance scoring can improve efficiency and reduce redundancy in transformer architectures

"The proposed importance score can improve efficiency and redundancy within transformer architectures."

LLM compute accounts for 80-90% of query cost in production semantic data processing systems

"In production, LLM compute accounts for $80-90\%$ of query cost"

Each LLM call costs 100,000 to 10,000,000 times more than a relational predicate

"each call costs $10^5-10^7\times$ a relational predicate"

LLM latency is high enough that per-call gradient steps and per-batch threshold solves can fit inside the round-trip time

"At LLM latency, per-call gradient steps and per-batch threshold solves fit inside the round-trip."

Compositional online learning at the LLM call boundary can achieve an 11.4x upper bound improvement on conjunction-filter workloads

"Under independence, the two learning components compose multiplicatively to an $11.4\times$ upper bound on a representative conjunction-filter workload."

In realistic conditions with self-selection and drift effects, compositional online learning achieves approximately 8x improvement on LLM query costs

"Self-selection at the cascade boundary, sample-budget shrinkage, and selectivity-estimation drift reduce it to a realistic figure near $8\times$."