Claims Browser

ES improves Pass@1 while attaining higher Pass@K than GRPO, unlike GRPO which exhibits entropy collapse

"Empirically, unlike GRPO, which exhibits entropy collapse, ES improves Pass@1 while attaining higher Pass@K than GRPO."

The task-performance gains of ES are only contributed to a sparse subset of larger-magnitude updates despite substantial whole-model parameter drift

"we find that despite substantial whole-model parameter drift, the task-performance gains of ES are only contributed to a sparse subset of larger-magnitude updates."

Large parameter movement in ES need not imply widespread functional change and does not necessarily lead to catastrophic forgetting

"This functional sparsity suggests that large parameter movement need not imply widespread functional change, and held-out evaluations further show that it does not necessarily lead to catastrophic forgetting."

ES requires a smaller population size in a larger LLM

"we study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM."

Influential public discourse can mislead not only through what is stated, but also through how information is framed, omitted, contextualized, and communicated

"Influential public discourse shapes public beliefs and can also mislead, not only through what is stated, but also through how information is framed, omitted, contextualised, and communicated."

Less research has focused on how misleadingness arises and shapes reader interpretations

"Yet less research has focused on how such misleadingness arises and shapes the interpretations formed by readers."

Misleadingness extends well beyond fabrication, with unsupported inference, exaggeration, and omission among the prevalent mechanisms

"misleadingness is diverse and extends well beyond fabrication, with unsupported inference, exaggeration, and omission among the prevalent mechanisms"

Current LLM-based EDA approaches struggle to scale to industrial designs

"Comparisons across the three roles show that current approaches struggle to scale to industrial designs"

6G-empowered robotic vehicles require high-fidelity visual perception under stringent bandwidth and energy constraints for sustainable intelligent mobility

"To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidelity visual perception under stringent bandwidth and energy constraints."

Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access RV networks

"Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access (NOMA) RV networks."

KDG-SemNOMA significantly outperforms state-of-the-art methods in both pixel-level accuracy and perceptual fidelity on FFHQ-256

"Experiments on FFHQ-256 demonstrate that KDG-SemNOMA significantly outperforms state-of-the-art methods in both pixel-level accuracy and perceptual fidelity."

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."

Vision-Language Models demonstrate exceptional visual reasoning capabilities, but their inference costs escalate rapidly with the proliferation of visual tokens

"Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation of visual tokens."

PACE framework enables Qwen2.5-VL-7B to retain 93.8% of original performance while using only 10% of visual tokens, achieving 3.1x speedup in time to first token

"By integrating PACE into Qwen2.5-VL-7B, the model retains 93.8% of its original performance while utilizing only 10% of the visual tokens, yielding a 3.1x speedup in time to first token (TTFT)."

A training-free inference framework can accelerate both the vision encoder and LLM via a unified Condense-and-Extract paradigm that addresses visual token pruning limitations

"we propose PACE (Pixel-Adaptive Condense and Extract), a training-free inference framework that accelerates both the vision encoder and the Large Language Model (LLM) via a unified Condense-and-Extract paradigm."