A new conformal prediction framework called Scientific Feasibility Control (SFC) achieves 50.1% accuracy on the PhyX physics reasoning benchmark, outperforming DeepSeek-R1 (49.8%) and GPT-4 (45.8%), w…
A new arXiv paper (2607.17531v1) introduces a fixed-pool diagnostic framework for test-time collaboration in LLMs, decomposing net gains into recoverable mass, verification-signal coverage, conditiona…
Researchers propose PPL-Factory, a task-aware and budget-aware data selection framework for large language model fine-tuning that uses perplexity-based scores to select informative training samples. E…
Researchers introduce KV-PRM, a process reward model that reduces scoring cost from O(L²) to O(L) by reading the KV cache from LLM generation instead of re-encoding trajectory text, achieving up to 5,…
TinyToT, a lightweight inference server compatible with Ollama, achieves 97% accuracy on a 35-question benchmark spanning graduate-level science, medicine, law, finance, and software engineering witho…
LLM benchmarks like MMLU and HumanEval are irrelevant for most businesses building AI products, as they measure generic performance rather than specific system tasks. Teams should instead build custom…
Sapient Inc. open-sourced HRM-Text in May 2026, a 1.15 billion parameter text generation model based on the HRM architecture. Trained on roughly 40 billion tokens—up to 1,000 times less data than comp…
Researchers have developed Fast-dLLM++, a training-free extension to diffusion large language models that accelerates inference by selecting parallel token commit sets based on the full sorted confide…