Training LLMs Beyond Next Token Prediction - Filling the Mutual Information Gap
arxiv.org·5h
💻Local LLMs
Flag this post
Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals
arxiv.org·1d
🌀Fractal Compression
Flag this post
Reasoning Models Sometimes Output Illegible Chains of Thought
arxiv.org·1d
🧠Intelligence Compression
Flag this post
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
arxiv.org·5h
💻Local LLMs
Flag this post
Building a Writing Tool Taught Me More About Explaining Ideas Than I Expected
🌳Incremental Parsing
Flag this post
Aligning LLM agents with human learning and adjustment behavior: a dual agent approach
arxiv.org·5h
🔲Cellular Automata
Flag this post
Efficient Test-Time Retrieval Augmented Generation
arxiv.org·5h
🔍Information Retrieval
Flag this post
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
arxiv.org·5h
📊Learned Metrics
Flag this post
Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge
arxiv.org·5h
🔍Information Retrieval
Flag this post
[D][P] PKBoost v2 is out! An entropy-guided boosting library with a focus on drift adaptation and multiclass/regression support.
🌀Brotli Dictionary
Flag this post
Panther: A Cost-Effective Privacy-Preserving Framework for GNN Training and Inference Services in Cloud Environments
arxiv.org·5h
💻Local LLMs
Flag this post
Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models
arxiv.org·1d
💻Local LLMs
Flag this post
The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses
arxiv.org·5h
🔍Information Retrieval
Flag this post
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
arxiv.org·5h
🧮Vector Embeddings
Flag this post
I Built an AI Agent to End Team Arguments (Mostly) - My HNG Stage 3 Journey
🌊Streaming Systems
Flag this post
Measuring Machine Companionship: Scale Development and Validation for AI Companions
arxiv.org·5h
🤖AI Curation
Flag this post
AstuteRAG-FQA: Task-Aware Retrieval-Augmented Generation Framework for Proprietary Data Challenges in Financial Question Answering
arxiv.org·1d
🔍BitFunnel
Flag this post
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
arxiv.org·5h
✨Effect Handlers
Flag this post
Complex QA and language models hybrid architectures, Survey
arxiv.org·5h
🧮Kolmogorov Complexity
Flag this post
Loading...Loading more...