Quipu: A Governed Bitemporal Knowledge Graph Store

When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents

Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, driving their gradual evolution from text…

2026-08-17 ·arxiv.org

Diagnosing Dense Same-Class Attribute Misbinding in Large Vision-Language Models

Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance.

2026-08-17 ·arxiv.org

Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment

Sign language serves as a vital means of communication for individuals with hearing impairments, yet recognition resources for the over 100 distinct sign languages are severely lacking.

2026-08-17 ·arxiv.org

Shadow Traffic Is the Only Honest Free Model Evaluation

The demo replay played in the dim glow of a conference room, and everyone agreed the free model sounded good. The same four prompts produced crisp summaries, polite error handling, and no obvious…

• Shadow traffic approach compares free model with primary model
• Real production traffic used to test free model's performance
• Metrics like error rates, latency, token consumption analyzed

2026-08-17 ·dev.to