bambolleo's Top FindsLoading...
Debian GNU/Hurd 2025 Released With Completed 64-bit Support, Rust Ported
phoronix.com·16h·
Discuss: Hacker News
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
arxiv.org·1d
🕯️Candle
Sign up or login to customize your feed and get personalized topic recommendations
Sign UpLogin
Practical Guidelines for Ideology Detection Pipelines and Psychosocial Applications
arxiv.org·1d
📈Graph Algorithms
In-Context Reinforcement Learning via Communicative World Models
arxiv.org·1d
🤖AI
UR$^2$: Unify RAG and Reasoning through Reinforcement Learning
arxiv.org·2d
🤖AI
LaVieID: Local Autoregressive Diffusion Transformers for Identity-Preserving Video Creation
arxiv.org·1d
🦾Rust ML
TLCCSP: A Scalable Framework for Enhancing Time Series Forecasting with Time-Lagged Cross-Correlations
arxiv.org·1d
🕯️Candle
AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning
arxiv.org·1d
🔢SIMD Programming
Learning Generalizable and Efficient Image Watermarking via Hierarchical Two-Stage Optimization
arxiv.org·2h
DKG-LLM : A Framework for Medical Diagnosis and Personalized Treatment Recommendations via Dynamic Knowledge Graph and Large Language Model Integration
arxiv.org·2d
🦾Rust ML
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation
arxiv.org·2d
🏗️LLVM
A Federated Learning Framework for Handling Subtype Confounding and Heterogeneity in Large-Scale Neuroimaging Diagnosis
arxiv.org·1d
🕯️Candle
"Draw me a curator" Examining the visual stereotyping of a cultural services profession by generative AI
arxiv.org·1d
🎨Computer Graphics
TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
arxiv.org·1d
🌐WebGPU
Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networks
arxiv.org·1d
🌍Distributed Systems
Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models
arxiv.org·1d
🕯️Candle
Thoughts on extrapolating time horizons
lesswrong.com·1d
🤖AI
A Study on Regularization-Based Continual Learning Methods for Indic ASR
arxiv.org·2d
🕯️Candle
BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context
arxiv.org·1d
🕯️Candle
RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning
arxiv.org·1d
🤖AI