Skip to main content

Sookmyung Women's University

2 related articles

Subscribe to updates

arXiv Oct 14, 2026
An excavator stops taking language orders at face value: a one-use lease ties approval to the exact motion, cutting closed-site dumping from 1.23 to 0.33 cubic meters
An LLM-directed excavator can execute mechanically feasible motion whose destination or authority no longer matches the operator's approval. The work binds authorization to the exact motion: a one-use lease ties the action, generated motion, mission contract and admission tolerance together, atomic dispatch rechecks current authority and measured joint drift, and revocation requests a carry-pitch quintic stop. Across a 672-case interface suite the gateway admitted all 120 benign cases and produced zero unauthorized dispatches in the attack suite; in synchronous simulation, dump-phase revocation cut maximum closed-site deposition from 1.23 to 0.33 cubic meters.
An LLM-directed excavator can execute mechanically feasible motion whose destination or authority no longer matches the operator's approval. The work binds authorization to the exact motion: a one-use lease ties the action, generated motion, mission contract and admission tolerance together, atomic dispatch rechecks current authority and measured joint drift, and revocation requests a carry-pitch quintic stop. Across a 672-case interface suite the gateway admitted all 120 benign cases and produced zero unauthorized dispatches in the attack suite; in synchronous simulation, dump-phase revocation cut maximum closed-site deposition from 1.23 to 0.33 cubic meters.
Sookmyung Women's University Tampere University Ajou University Korea University
Mehdi Heydari Shahna（First author）
Execution-Bound Authorization Autonomous Excavation ExecutionBound
arXiv Sep 29, 2026
RenderRank reranks documents from compressed visual tokens rendered as images, reaching 55.96 average NDCG@10 on BEIR with 16.5–35.5% fewer input tokens
RenderRank renders document text as images and encodes them into compressed visual tokens, aligning relevance scores to a text-based teacher and then refining positive-versus-negative scores within each query, reaching an average NDCG@10 of 55.96 on 11 BEIR datasets with 290.07 average input tokens, 16.5–35.5% fewer than the evaluated text-based rerankers, and an average NDCG@10 of 88.27 on four long-document datasets at roughly half their average input token count.
RenderRank renders document text as images and encodes them into compressed visual tokens, aligning relevance scores to a text-based teacher and then refining positive-versus-negative scores within each query, reaching an average NDCG@10 of 55.96 on 11 BEIR datasets with 290.07 average input tokens, 16.5–35.5% fewer than the evaluated text-based rerankers, and an average NDCG@10 of 88.27 on four long-document datasets at roughly half their average input token count.
Sookmyung Women's University Korea University
Seongtae Hong（First author）
RenderRank Document Reranking Visual Text Compression Knowledge Distillation Qwen3-VL

You’re all caught up