#Knowledge Distillation
Latest news articles tagged with "Knowledge Distillation". Follow the timeline of events, related topics, and entities.
Articles (9)
-
🇺🇸 Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
[USA]
arXiv:2603.13260v1 Announce Type: cross Abstract: Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Tho...
Related: #AI Reasoning -
🇺🇸 PACED: Distillation at the Frontier of Student Competence
[USA]
arXiv:2603.11178v1 Announce Type: new Abstract: Standard LLM distillation wastes compute on two fronts: problems the student has already mastered (near-zero gradients) and problems far beyond its rea...
Related: #Machine Learning -
🇺🇸 BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations
[USA]
arXiv:2603.06576v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic unders...
Related: #AI Perception -
🇺🇸 MobileFetalCLIP: Selective Repulsive Knowledge Distillation for Mobile Fetal Ultrasound Analysis
[USA]
arXiv:2603.05421v1 Announce Type: cross Abstract: Fetal ultrasound AI could transform prenatal care in low-resource settings, yet current foundation models exceed 300M visual parameters, precluding d...
Related: #Medical AI, #Mobile Health -
🇺🇸 Reinforcement-aware Knowledge Distillation for LLM Reasoning
[USA]
arXiv:2602.22495v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the hi...
Related: #Machine Learning, #Reinforcement Learning -
🇺🇸 Decoder-based Sense Knowledge Distillation
[USA]
arXiv:2602.22351v1 Announce Type: cross Abstract: Large language models (LLMs) learn contextual embeddings that capture rich semantic information, yet they often overlook structured lexical knowledge...
Related: #AI Research, #Natural Language Processing -
🇺🇸 STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
[USA]
arXiv:2602.03022v2 Announce Type: replace Abstract: The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders wid...
Related: #AI Model Optimization, #Function Calling -
🇺🇸 Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty
[USA]
arXiv:2602.12687v1 Announce Type: cross Abstract: The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are...
Related: #Model Compression, #Uncertainty Quantification -
🇺🇸 FastWhisper: Adaptive Self-knowledge Distillation for Real-time Automatic Speech Recognition
[USA]
arXiv:2601.19919v1 Announce Type: cross Abstract: Knowledge distillation is one of the most effective methods for model compression. Previous studies have focused on the student model effectively tra...
Related: #Artificial Intelligence, #Model Compression
Key Entities (4)
- Reinforcement learning (1 news)
- Science Publishing Group (1 news)
- Large language model (1 news)
- Probability distribution (1 news)
About the topic: Knowledge Distillation
The topic "Knowledge Distillation" aggregates 9+ news articles from various countries.