Using Self-hosting Language Models So You Can Evaluate Claude Code
blog.matthewbrunelle.com·3h
🤖AI
Flag this post
Stanford's new Equivariant Encryption enables private AI inference with zero slowdown - works with any symmetric encryption
🔮ML
Flag this post
Genomes of 24,000 previously unknown microbes revealed by new tools
phys.org·5h
🤖AI
Flag this post
AI Memory: Enabling The Next Era Of High-Performance Computing
semiengineering.com·2d
🔮ML
Flag this post
Argus: Quality-Aware High-Throughput Text-to-Image Inference Serving System
arxiv.org·2d
🤖AI
Flag this post
A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving
arxiv.org·2d
🔮ML
Flag this post
DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
arxiv.org·2d
🔮ML
Flag this post
One Weird Hashing Trick
🔮ML
Flag this post
Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation
arxiv.org·14h
🤖AI
Flag this post
Interaction Dynamics as a Reward Signal for LLMs
arxiv.org·1d
🔮ML
Flag this post
Next-Latent Prediction Transformers Learn Compact World Models
arxiv.org·2d
🔮ML
Flag this post
Constrained and Robust Policy Synthesis with Satisfiability-Modulo-Probabilistic-Model-Checking
arxiv.org·1d
🤖AI
Flag this post
Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment
arxiv.org·14h
🔮ML
Flag this post
Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation
arxiv.org·2d
🤖AI
Flag this post
MoM – Mixture of Model Service
🔮ML
Flag this post
Loading...Loading more...