News
AI, cybersecurity, machine learning, scraping & programming news.
113 results on this page · clear filters
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
Prior work on LLM-guided evolutionary methods such as AlphaEvolve has demonstrated strong results on computational optimization problems, including circle packing. However, these approaches typically optimize for performance gain...
"Torturing" LLMs in a Robot Prison Has Triggered the Dumbest Debate in AI Yet
GitHub project puts locally hosted LLMs through Saw-style experiments A GitHub project has sparked heated discussion on X after its creator began running torture and pain experiments on a series of large language models run locall...
OpenAI safety leader quits, warning AI company's culture is 'broken'
A safety leader at OpenAI has quit the company, warning that its culture was broken and that AI firms were not "being nearly careful enough" about developing the technology. David Robinson, who led the writing of safety reports th...
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
Author-Annotated Benchmark for Scientific Paper Retrieval ScholarCatalyst introduces a benchmark designed to study how researchers identify prior work that inspired their projects. The dataset was built by having 184 lead authors...
VISTA: A Visual Harness for Reasoning in an Interactive World
We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce VISTA, a visual harness that gives a...
The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models
Large language models now solve competition-level mathematics yet it remains unclear whether they grasp the structural logic behind their solutions. This paper introduces the Mathematical Primitive as a probe for structural unders...
Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation
Sparse Routing in Multimodal Mixture-of-Experts Architectures Mixture-of-Experts (MoE) architectures have become a cornerstone for scaling modern multimodal models. The standard Transformer feed-forward layer replaces a single den...
Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a frozen or EMA version of themselves that receives privileged information. Its applicat...
LLM2Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
Standard chat models generate free-form text that must be parsed into structured values, introducing latency and the risk of malformed outputs. Jev-style decision models return categorical probability distributions over predefined...
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints
Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption (FHE) offers a compelling solution for secure computation, pr...