⚗️ Knowledge Distillation - hop1.ng.1357 · Scour

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory 🔢BitNet

arxiv.org·3d

Bespoke OLAP: Using AI to Synthesize Workload-Specific Database Engines from Scratch 🔍EXPLAIN ANALYZE

ucbskyadrs.github.io·11h·Hacker News

anhnguyensynctree/optinum: AI-native diff-scoped integration test synthesis. Catches blind spots at integration boundaries. 🎮Deterministic Simulation

github.com·2d·Hacker News

OpenAI, Anthropic, Google unite to combat model copying in China 🇨🇳Chinese AI

businesstimes.com.sg·3d·Hacker News

Gemma 4 E4B vs. Gemma Family: Enterprise Benchmark Across 8 Task Suites 🪝eBPF

aiexplorer-blog.vercel.app·3d·Hacker News

The case for sustained, rapid, inclusive-enough economic growth as a focus of development 🌱Bootstrapping

lantpritchett.org·6d·Hacker News

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

arxiv.org·1d

KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning 🤝Multi-Agent Orchestration

arxiv.org·1d

Show HN: Ownscribe – local meeting transcription, summarization and search 🤖LLM

github.com·5d·Hacker News

HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues 🤖LLM

arxiv.org·1d

PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models 🛡️AI Security

arxiv.org·2d

WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search 🕷️Web Crawling

arxiv.org·1d

ReLU Networks for Exact Generation of Similar Graphs 📚RAG

arxiv.org·2d

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner ⚡Edge AI

arxiv.org·2d

Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization ✨LLMs

arxiv.org·4d

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation ✨Gemini

arxiv.org·2d

Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation ✨Gemini

arxiv.org·3d

Weakly Supervised Distillation of Hallucination Signals into Transformer Representations ⚡Edge AI

arxiv.org·1d

DP-OPD: Differentially Private On-Policy Distillation for Language Models 🤖LLM

arxiv.org·3d

Learning the Stellar Structure Equations via Self-supervised Physics-Informed Neural Networks 🔍AI Interpretability

arxiv.org·1d

Loading more...