🦾 Rust ML

Candle Integration, tch, SmartCore, Linfa, High-performance Computing

Four types of approaches for your emotional problems
lesswrong.com·13h
📈Graph Algorithms
Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
arxiv.org·2d
🤖AI
A Context-aware Attention and Graph Neural Network-based Multimodal Framework for Misogyny Detection
arxiv.org·2d
🕯️Candle
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
arxiv.org·2d
🕯️Candle
Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
arxiv.org·1d
🔒Hardware Security
Benchmarking Large Language Models for Geolocating Colonial Virginia Land Grants
arxiv.org·3d
🕯️Candle
Topos Causal Models
arxiv.org·3d
🧮Linear Algebra
LET-US: Long Event-Text Understanding of Scenes
arxiv.org·4d
🕯️Candle
CountQA: How Well Do MLLMs Count in the Wild?
arxiv.org·4d
🕯️Candle
A Risk Taxonomy and Reflection Tool for Large Language Model Adoption in Public Health
arxiv.org·3d
🕯️Candle
Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach
arxiv.org·2d
⏱️Real-time Systems
DAS: Dual-Aligned Semantic IDs Empowered Industrial Recommender System
arxiv.org·1d
🤖AI
Generating Feasible and Diverse Synthetic Populations Using Diffusion Models
arxiv.org·2d
🎮Game Engines
My Interview With Cade Metz on His Reporting About Lighthaven
lesswrong.com·1h
🤖AI
How to get ChatGPT to really thoroughly research something
lesswrong.com·1d
🗄️Database Internals
Beyond Single: A Data Selection Principle for LLM Alignment via Fine-Grained Preference Signals
arxiv.org·4d
🤖AI
Fed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning
arxiv.org·4d
🏗️LLVM
BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
arxiv.org·4d
🕯️Candle
Fractal Language Modelling by Universal Sequence Maps (USM)
arxiv.org·4d
🕯️Candle
Detection of Odor Presence via Deep Neural Networks
arxiv.org·2d
🕯️Candle