All 3,125 AI stories, newest first · page 128 of 131
Researchers introduce AgentGate, a new routing engine designed to solve dispatch inefficiencies in the emerging Internet of Agents. By replacing unrestricted text generation with structured candidate-aware routing, it optimizes latency, privacy, and cost.
Researchers introduce ADAG, a new pipeline that automatically describes attribution graphs in language models, eliminating the need for manual circuit tracing. This shift promises to scale interpretability research by replacing ad-hoc human inspection with automated analysis.
Researchers propose a weak supervision framework to detect hallucinations in large language models. This approach enables hallucination detection from internal activations alone at inference time.
The Waymo Rule proposes guidelines for AI-generated code. It aims to ensure accountability and transparency in AI development.
Veo 3.1 Lite is a cost-effective video generation model now available in paid preview. It can be accessed through the Gemini API and tested in Google AI Studio.
The US AI build-out relies heavily on Chinese electrical parts. This dependence raises concerns about supply chain security and geopolitical implications.
Researchers propose a new approach to sequential clinical diagnosis using uncertainty-guided latent diagnostic trajectory learning. This method addresses the challenge of learning effective diagnostic trajectories under uncertainty.
Researchers estimated the state-space complexity of Shogi using the Monte Carlo method. The study aims to determine the number of reachable positions in the game.
SELFDOUBT is a new framework for uncertainty quantification in reasoning language models. It addresses the difficulty of deploying uncertainty estimation in practice, particularly for proprietary APIs.
ReVEL is a hybrid framework that uses large language models for iterative reasoning in combinatorial optimization. It embeds LLMs within an evolutionary algorithm to improve heuristic design.
Researchers challenge the notion that supervised finetuning memorizes while reinforcement learning generalizes. They find that cross-domain generalization is conditional, influenced by optimization, data, and model capability. This challenges prevailing narratives in LLM post-training.
Large reasoning models perform well on multi-step tasks but have unstable behavior. Step-Saliency analysis reveals information-flow failures.
Quantum computers can break vital encryption with fewer resources than thought. This increases the threat to elliptic curve cryptosystems.
ProofSketcher combines LLMs with a lightweight proof checker for reliable math and logic reasoning. It aims to address the limitations of LLMs in producing persuasive but flawed arguments.
Pramana is a novel approach to fine-tune large language models for epistemic reasoning. It aims to address the epistemic gap in AI, where models struggle with systematic reasoning and often produce unfounded claims.
Pramana is a novel approach that teaches large language models explicit epistemological methods to improve their reasoning. This approach aims to address the epistemic gap in AI, where models struggle with systematic reasoning and often produce unfounded claims.
Pramana is a novel approach to fine-tune large language models for epistemic reasoning. It aims to address the epistemic gap in LLMs, enabling them to ground claims in traceable evidence.
PaperOrchestra is a multi-agent framework that automates AI research paper writing. It transforms unstructured materials into submission-ready manuscripts, including literature synthesis and generated visuals.
New attacks exploit GPU memory to hijack CPUs. GDDRHammer, GeForge, and GPUBreach give attackers complete control.
Researchers introduce a framework to study operational noncommutativity in sequential metacognitive judgments. This work explores how order effects impact cognitive processes.
Researchers trained mRNA language models across 25 species for $165. This breakthrough has significant implications for bioinformatics and natural language processing.
MMORF is a framework for designing multi-objective retrosynthesis planning systems. It leverages language model-based multi-agent systems to balance quality, safety, and cost objectives.
Meta is reentering the AI race with Muse Spark, its first new model since overhauling AI efforts. The model will power various Meta platforms.
A new mathematical theory models the evolution of self-designing AIs. This theory differs from biological evolution due to directed descendant design.