⚗️ Knowledge Distillation - codenm.no2 · Scour

Extraction of linearized models from pre-trained networks via knowledge distillation 🧠LLM

arxiv.org·6d

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective 🤖Large Language Models

arxiv.org·2d

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models 🤖Large Language Models

arxiv.org·2d

A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP 🤖Large Language Models

arxiv.org·6d

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents 🎮Reinforcement Learning

arxiv.org·1d

Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation 🤖LLM Inference

arxiv.org·2d

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning 💬LLMs

arxiv.org·5d

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories ✍️Prompt Engineering

arxiv.org·1d

DTCRS: Dynamic Tree Construction for Recursive Summarization 🎯Retrieval Systems

arxiv.org·6d

Distilling Genomic Models for Efficient mRNA Representation Learning via Embedding Matching 🤖LLM Inference

arxiv.org·2d

RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering 🎯Retrieval Systems

arxiv.org·1d

Structured Distillation of Web Agent Capabilities Enables Generalization 💬LLMs

arxiv.org·5d

Choose, Don't Label: Multiple-Choice Query Synthesis for Program Disambiguation 🧠Context Engineering

arxiv.org·2d

On-Policy Distillation of Language Models for Autonomous Vehicle Motion Planning 🤝Human-AI Collaboration

arxiv.org·5d

Cross-Modal Knowledge Distillation from Spatial Transcriptomics to Histology 🎨Generative AI

arxiv.org·2d

Automated Batch Distillation Process Simulation for a Large Hybrid Dataset for Deep Anomaly Detection 🤖LLM Inference

arxiv.org·2d

Cross-Tokenizer LLM Distillation through a Byte-Level Interface 🧠LLM

arxiv.org·5d

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation 🤖LLM Inference

arxiv.org·1d

TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization 💬LLMs

arxiv.org·5d

LVSum: A Benchmark for Timestamp-Aware Long Video Summarization 🎯Retrieval Systems

arxiv.org·1d

Loading more...