LLM Guardrail Models are Less Robust Against Text Mutation Attacks
kalyan-ks
• • 1NEW Articles from Team or Enterprise organizations will get promoted to the main section.
An experiment with attention.
wop
• • 4📄 Research Papers Dataset
tegridydev
• • 2Eight Days in China: What I Learned from the AI Labs, Robotics Startups and Academia
matthew-d-white
• Text Degeneration: A Production Failure Mode That Most Benchmarks Do Not Track
Dharma-AI
• • 1Why Open Models Are the Only Sustainable Way to Teach AI
penelopegittos
• • 6Scaling Zero-Resource Vocabulary: A Data Pipeline for Sango
MEYNG
• When does autoresearch need a human?
ProlificAI
• LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning
VirgileBatto
• • 21SANA-WM Bidirectional on Apple Silicon
junafinity
• • 2Cross-game Slay the Spire 1 and 2 multimodal embeddings with Qwen3-VL: text-as-primary, art-as-secondary
t22000t
• Software Forgets: Agent Traces Are the Memory
huggingface
• • 8Building a prompt-to-deck generator: greedy semantic retrieval with hard feasibility constraints
t22000t
• Computing between models with residual coupling
pfekin
• GOLDENER <br> Smart sampling from embeddings and coreset selection
Yann-CV
• Beyond logs: building a local-first replay layer for AI agents
Spectorfrost123
• Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
nvidia
• • 18AI, Physical AI, World Models, VLA, VLM, and Other Terms We Should Stop Mixing Together
barakor
• • 1The Agentic Kill Chain: A Five-Phase Framework for LLM Security
AlephBeth-AI
• • 1Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages
adalat-ai
• • 11