Cloud + Agents + Inference

arXiv2d ago

Bi-Predictability: A Real-Time Signal for Monitoring LLM Interaction Integrity

arXiv2d ago

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents

arXiv1d ago

Mistake gating leads to energy and memory efficient continual learning

arXiv1d ago

Geometric Routing Enables Causal Expert Control in Mixture of Experts

arXiv3d ago

Aethon: A Reference-Based Replication Primitive for Constant-Time Instantiation of Stateful AI Agents

arXiv2d ago

Sparse Goodness: How Selective Measurement Transforms Forward-Forward Learning

arXiv1d ago

Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

nvidia blog2d ago

Rethinking AI TCO: Why Cost per Token Is the Only Metric That Matters

YHN1d ago

Claude Opus 4.7

arXiv3d ago

LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks

arXiv2d ago

Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents

arXiv1d ago

Can Large Language Models Detect Methodological Flaws? Evidence from Gesture Recognition for UAV-Based Rescue Operation Based on Deep Learning

arXiv2d ago

Analog Optical Inference on Million-Record Mortgage Data

aws ai blog1d ago

Introducing Anthropic’s Claude Opus 4.7 model in Amazon Bedrock

arXiv1d ago

SAGE Celer 2.6 Technical Card

arXiv2d ago

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs

arXiv3d ago

ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism

arXiv1d ago

Formalizing Kantian Ethics: Formula of the Universal Law Logic (FULL)

arXiv1d ago

Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems

arXiv2d ago

Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI Modellin

YHN1d ago

Cloudflare's AI Platform: an inference layer designed for agents

GitHub3d ago

danielmiessler/Personal_AI_Infrastructure

arXiv1d ago

Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning

Anthropic2d ago

Introducing Claude Opus 4.7

arXiv3d ago

Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score

YHN1d ago

Guy builds AI driven hardware hacker arm from duct tape, old cam and CNC machine

GitHub3d ago

Tracer-Cloud/opensre

GitHub1d ago

datawhalechina/hello-agents

arXiv2d ago

EVE: A Domain-Specific LLM Framework for Earth Intelligence

arXiv2d ago

Quantifying and Understanding Uncertainty in Large Reasoning Models

arXiv1d ago

Thermodynamic Diffusion Inference with Minimal Digital Conditioning

arXiv2d ago

Before the First Token: Scale-Dependent Emergence of Hallucination Signals in Autoregressive Language Models

OpenAI2d ago

Introducing GPT-Rosalind for life sciences research

arXiv1d ago

Internal Knowledge Without External Expression: Probing the Generalization Boundary of a Classical Chinese Language Model

arXiv2d ago

Spectral Entropy Collapse as an Empirical Signature of Delayed Generalisation in Grokking

arXiv2d ago

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

GitHub8h ago

Cloud + Agents + Inference

Signals (37)

Bi-Predictability: A Real-Time Signal for Monitoring LLM Interaction Integrity

The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents

Mistake gating leads to energy and memory efficient continual learning

Geometric Routing Enables Causal Expert Control in Mixture of Experts

Aethon: A Reference-Based Replication Primitive for Constant-Time Instantiation of Stateful AI Agents

Sparse Goodness: How Selective Measurement Transforms Forward-Forward Learning

Interpretable and Explainable Surrogate Modeling for Simulations: A State-of-the-Art Survey and Perspectives on Explainable AI for Decision-Making

Rethinking AI TCO: Why Cost per Token Is the Only Metric That Matters

Claude Opus 4.7

LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks

Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents

Can Large Language Models Detect Methodological Flaws? Evidence from Gesture Recognition for UAV-Based Rescue Operation Based on Deep Learning

Analog Optical Inference on Million-Record Mortgage Data

Introducing Anthropic’s Claude Opus 4.7 model in Amazon Bedrock

SAGE Celer 2.6 Technical Card

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs

ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism

Formalizing Kantian Ethics: Formula of the Universal Law Logic (FULL)

Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems

Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI Modellin

Cloudflare's AI Platform: an inference layer designed for agents

danielmiessler/Personal_AI_Infrastructure

Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning

Introducing Claude Opus 4.7

Beyond Majority Voting: Efficient Best-Of-N with Radial Consensus Score

Guy builds AI driven hardware hacker arm from duct tape, old cam and CNC machine

Tracer-Cloud/opensre

datawhalechina/hello-agents

EVE: A Domain-Specific LLM Framework for Earth Intelligence

Quantifying and Understanding Uncertainty in Large Reasoning Models

Thermodynamic Diffusion Inference with Minimal Digital Conditioning

Before the First Token: Scale-Dependent Emergence of Hallucination Signals in Autoregressive Language Models

Introducing GPT-Rosalind for life sciences research

Internal Knowledge Without External Expression: Probing the Generalization Boundary of a Classical Chinese Language Model

Spectral Entropy Collapse as an Empirical Signature of Delayed Generalisation in Grokking

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior

cloudflare/agents