Large reasoning models exhibit reasoning collapse, with accuracy dropping sharply beyond task-specific complexity thresholds in controlled versions of nine classical reasoning tasks using strict validity validators.
write newline
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
MoME with HTL outperforms single-modal and multimodal baselines on driver action recognition by enabling adaptive expert collaboration and token-based intra- and inter-expert refinement.
CoRaCMG augments LLM prompts with retrieved similar diff-message pairs to improve automatic generation of commit messages from code changes.
NARFIMA integrates ARFIMA long memory with neural networks and exogenous variables to forecast BRIC exchange rates, establishes asymptotic stationarity, uses conformal prediction for uncertainty, and outperforms benchmarks empirically.
A comparative evaluation of nine point-cloud leaf surface reconstruction methods on LAST-STRAW, Pheno4D, and Crops3D datasets reveals method-specific trade-offs in area accuracy, smoothness, robustness, and compute cost for agricultural robotics.
citing papers explorer
-
Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints
Large reasoning models exhibit reasoning collapse, with accuracy dropping sharply beyond task-specific complexity thresholds in controlled versions of nine classical reasoning tasks using strict validity validators.
-
Mixture-of-Modality-Experts with Holistic Token Learning for Fine-Grained Multimodal Visual Analytics in Driver Action Recognition
MoME with HTL outperforms single-modal and multimodal baselines on driver action recognition by enabling adaptive expert collaboration and token-based intra- and inter-expert refinement.
-
CoRaCMG: Contextual Retrieval-Augmented Framework for Commit Message Generation
CoRaCMG augments LLM prompts with retrieved similar diff-message pairs to improve automatic generation of commit messages from code changes.
-
Neural ARFIMA model for forecasting BRIC exchange rates with long memory
NARFIMA integrates ARFIMA long memory with neural networks and exogenous variables to forecast BRIC exchange rates, establishes asymptotic stationarity, uses conformal prediction for uncertainty, and outperforms benchmarks empirically.
-
Review and Evaluation of Point-Cloud based Leaf Surface Reconstruction Methods for Agricultural Applications
A comparative evaluation of nine point-cloud leaf surface reconstruction methods on LAST-STRAW, Pheno4D, and Crops3D datasets reveals method-specific trade-offs in area accuracy, smoothness, robustness, and compute cost for agricultural robotics.