A new preprint analyzing 8 open Transformer models finds that internal representations show statistically significant structured progression across depth (p = 0.00019996, 8/8 leave-one-model-out check…
A developer built ttsproof, an open-source QA framework for text-to-speech systems that separates structural defects from pronunciation errors, addressing the shortcomings of Word Error Rate metrics. …
A new paper on SSRN proposes ORCA, a cognitive runtime for LLM agents that structures reasoning as reusable components instead of embedding logic in prompts, addressing common failure patterns in agen…
Researchers at Zenodo published a cross-vendor evaluation documenting Claude Opus 4.6 returning successful provider responses with zero visible UTF-8 output bytes in 900 of 900 test cases, distinct fr…
Independent researcher Shakeel is seeking an arXiv endorsement for a new submission in the cs.AI category (cross-listed to cs.DB), for the survey paper 'Agentic AI for Data Engineering: A Systematic R…
A new measurement study across four models finds that the default LoRA target_modules of q_proj and v_proj underperforms a data-driven placement for capability retention: on Llama-3-8B fine-tuning cod…
Independent researcher Chance, founder of CharacterOS LLC, is seeking an arXiv endorser in cs.RO or cs.AI for a paper on social robot character safety certification under the RoboSafe standard, which …
Author Ruffian-L released a new record claiming operational AI consciousness and bounded adaptive agency in the Niodoo system, with evidence published on Zenodo (DOI 10.5281/zenodo.21965763) and code …
A new preprint by N. Trillard, 'Steer on a Sphere: Geometric Control of Transformer Outputs,' shows that a single tangent step on the sphere of hidden states reaches 91–98% of tokens at rank 1 across …
A developer has open-sourced the Phase-Shifted Agentic Swarm (PSAS), a multi-agent framework that uses destructive interference to eliminate hallucinated logic branches in LLM pipelines, with validati…
A developer has open-sourced the Unified Latent-State Memory Fabric (UL-SMF), a hardware-software co-designed architecture that compresses standard FP32 KV caches into a 16-dimensional discrete latent…
NXTG.AI published a page on August 10, 2026, listing ten publicly verifiable artifacts, each paired with a probe URL, to support narrow claims about the existence and reachability of its Forge Orchest…
Independent researcher Wolfgang Stegemann released v0.4 of the open-source reference implementation of the Artificial Local Intelligence (ALI) architecture, a Python-based agent framework that separat…
A new AI framework called ContactSeek uses Google DeepMind's AlphaFold3 to redesign gene-editing proteins, achieving dramatically higher accuracy than existing high-fidelity alternatives. Published in…
PathMap AI, developed by investigator Joshua Dungan, identified high amylose maize starch as a potential non-invasive tool to improve outcomes in traumatic brain injury and hypoxic neurovascular damag…
A developer introduced Robust-GAP, a hierarchical Retrieval-Augmented Generation (RAG) framework designed to eliminate hallucinations and knowledge drift in multi-document log summarization. The frame…
Researchers have released Deep4ge, a massive dataset containing 14,227 training runs from 59 deep neural network programs to help detect faults in deep learning systems. The dataset includes 9,845 fau…
A developer released GAP (Graph-Anchor Pyramid), a hierarchical context architecture that combines graph retrieval, topology-aware leaf grouping, and prompt-level semantic anchoring to solve the multi…
A developer ran an experiment testing whether syllogistic prompts improve AI models' internalization of constraints compared to imperative prompts. Initial results showed zero effect, but three expert…
A developer adapted a 2016 string concatenation algorithm, called the Pyramid Method, to solve memory loss in large language models (LLMs) when aggregating multiple documents. The new approach, Pyrami…