ar Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory AI Research Performance & Scalability Hardware Q: 9 R: 9 May 30, 2026 Summary
Even (very) noisy LLM evaluators are useful for improving AI agents LLM & Prompting AI Research AI Tools Q: 8 R: 9 May 12, 2026 Summary
A LLMs believe false statements even after explicit warnings that they’re false LLM & Prompting AI News AI Research Q: 8 R: 9 May 28, 2026 Summary
Five frontier LLMs disagree on 67% of 1k real-world fact-check claims AI News AI Research LLM & Prompting Q: 8 R: 9 May 28, 2026 Summary
A Eureka machine that thinks like nature and explores what AI cannot AI News AI Research Hardware Q: 9 R: 9 May 28, 2026 Summary
ar Epicure: Navigating the Emergent Geometry of Food Ingredient Embeddings AI Research Machine Learning Q: 9 R: 9 May 27, 2026 Summary
ar Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper) LLM & Prompting AI Research Q: 8 R: 9 May 26, 2026 Summary
ar Language Models Need Sleep AI Research LLM & Prompting Machine Learning Q: 9 R: 9 May 26, 2026 Summary
ar Constraint Decay: The Fragility of LLM Agents in Backend Code Generation LLM & Prompting AI Tools AI Research Q: 8 R: 9 May 24, 2026 Summary
Perceptual Image Codec: What Matters in Practical Learned Image Compression AI Research AI News Q: 8 R: 9 May 24, 2026 Summary
ar CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs Machine Learning AI Research Q: 8 R: 9 May 22, 2026 Summary