Claims Browser

Current models face persistent challenges with variant characters, specialized symbols, and hallucination when processing ancient Chinese texts

"persistent challenges in variant characters, specialized symbols, and hallucination"

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."

Single-day embeddings from foundation models can still classify land cover at 3.4 times the chance level

"Single-day embeddings still classify land cover in LUCAS at $3.4$ times the chance level."

Strong text-only LLMs exceed 90% accuracy in consistent cases but drop to 33-48% in conflict cases where acoustic and textual signals disagree

"strong text-only LLMs exceed 90% accuracy in consistent cases but drop to 33-48% in conflict cases"

Direct AudioLLMs provide only partial grounding, still selecting the transcript-biased trap in roughly 30-40% of conflict cases

"Direct AudioLLMs provide only partial grounding, still selecting the transcript-biased trap in roughly 30-40% of conflict cases"

A Swin V2 encoder pretrained on 10,444 public 3D CT volumes using a DINOv2-style objective can be successfully adapted to T2-weighted MRI for rectal cancer segmentation

"A Swin V2 encoder pretrained on 10,444 public 3D CT volumes using a DINOv2-style objective was adapted to T2-weighted MRI through four cumulative configurations"

SWIFTe reduced total parameters by 70.1% compared to SWIFT while increasing tumor detection rate from 89.9% to 93.9%

"SWIFTe reduced total parameters by 70.1% (from 72.8M to 21.8M) and increased tumor detection rate from 89.9% to 93.9%"

There is a trade-off between tumor detection and boundary agreement in rectal cancer segmentation: removing tumor-aware augmentation reduced detection from 93.9% to 89.9% but increased surface DSC from 0.61 to 0.64

"removing tumor-aware augmentation reduced detection from 93.9% to 89.9% but increased surface DSC from 0.61 to 0.64, demonstrating a detection-boundary-agreement trade-off"

SWIFTe-LoRA achieved similar segmentation performance while using only 14.6% of SWIFTe's trainable parameters

"SWIFTe-LoRA used 14.6% of SWIFTe's trainable parameters while retaining similar segmentation performance"

Knowledge distillation combined with generative models can enable robust and green robotic vehicle communications in NOMA frameworks

"we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA."

The SWIFTe-LDE4 ensemble achieved the best calibration after temperature scaling but still exhibited residual miscalibration with an expected calibration error of 0.217

"SWIFTe-LDE4 achieved the lowest calibration errors among the four configurations after temperature scaling (expected calibration error, 0.217; Brier score, 0.222), although the absolute expected calibration error indicates residual miscalibration"

LLM agents are increasingly being applied to anomaly detection and root-cause analysis in time-series observations from real-world systems

"LLM agents are increasingly applied to anomaly detection and root-cause analysis in time-series observations collected from real-world systems"

LLM agents benefit substantially from domain context when analyzing time-series observations from dynamical systems

"Our results show that agents benefit substantially from domain context"

LLM agents explore time-series data primarily through numerical console output rather than visualizations

"explore data primarily through numerical console output rather than visualizations"

LLM agents generally perform worse when required to produce a Python script for root-cause prediction than when submitting predictions directly

"agents generally perform worse when required to produce a Python script that maps each time-series sample to a predicted root-cause label than when they submit predictions directly"

Large language models enable direct translation from design intent to hardware implementations in electronic design automation

"Large language models (LLMs) extend this trajectory by enabling direct translation from design intent to hardware implementations."