Token Probabilities to Mitigate Large Language Models Overconfidence in Answering Medical Questions: Quantitative Study
【DL輪読会】Token Probabilities to Mitigate Large Language Models Overconfidence in Answer more
カテゴリー: dls-2026
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
【DL輪読会】Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspe more
Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
【DL輪読会】Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks by @De more
Pre-Trained Video Generative Models as World Simulators
【DL輪読会】Pre-Trained Video Generative Models as World Simulators by @DeepLearning2023
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
【DL輪読会】NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering by @D more
Dreamer 4: Training Agents Inside of Scalable World Models
【Diffusion勉強会】Dreamer 4: Training Agents Inside of Scalable World Models by @DeepLear more