Bandits in Your LLM Gateway
👨lectures
Flag this post
Just call clone (or alias)
💻programming languages
Flag this post
The Law of Leaky Abstractions
🌐Computer Networks
Flag this post
I build a TUI tool using golang to view delimited file in terminal
💻programming languages
Flag this post
MT-HuBERT: Self-Supervised Mix-Training for Few-Shot Keyword Spotting in Mixed Speech
arxiv.org·1d
👨lectures
Flag this post
Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention
arxiv.org·1d
👨lectures
Flag this post
Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
arxiv.org·1d
👨lectures
Flag this post
The Closure Trap: A JavaScript Bug That Shows Why Fundamentals Still Matter in the AI Era
💻programming languages
Flag this post
Emergent Misalignment via In-Context Learning: Narrow in-context examples canproduce broadly misaligned LLMs
💻programming languages
Flag this post
CG-TTRL: Context-Guided Test-Time Reinforcement Learning for On-Device Large Language Models
arxiv.org·1d
👨lectures
Flag this post
ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction with Fewer Primitives
arxiv.org·1d
👨lectures
Flag this post
I built a production-ready backend with NestJS & Prisma, focusing on clean architecture. Here's a look at the structure.
💻programming languages
Flag this post
DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering
arxiv.org·2h
👨lectures
Flag this post
Loading...Loading more...