arXiv subjects

Victor Gao

Publications and source records attributed to Victor Gao.

3 recordsLinked to original sources

arXiv2026

GVS5H: Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance

Frontier coding performance is typically attained with large, costly proprietary models. We introduce ledger-based zero-shot self-orchestration (GVS5H), a training-free method in which fresh instances of one model decompose problems and coordinate through a shared file system. Across eleven open and closed-weight models on the 100 latest hard LiveCodeBench problems, the method yields as much as 25.6 points improvement, boosting several cheaper models to frontier-level performance. Orchestrated Qwen3.8 Flash Next scores 93.0% against Fable 5's 90.4% at 9% of the cost, while the smaller Qwen3.8-27B reaches 92.4%. Gains are not universal: some models are unchanged or worse. Transcript analysis attributes the gain to decomposition and persistent context. Inference-time organization can reach or exceed frontier coding accuracy at a fraction of the cost on self-hostable weights.

cs.MA↗

arXiv2026

Defense-in-Depth Runtime Safety in Move

Move is a smart-contract language used to execute transactions on the Aptos blockchain. Move programs execute in a sandboxed VM as typed bytecode. The VM statically verifies foundational safety properties like type safety and reference safety at code loading time. In principle, this design gives strong guarantees for Move. However, the static verification logic is complex and continually evolving with the language; like any software, it is not immune to bugs. In a live blockchain setting, a missed rule violation can translate directly into loss of assets, forged authority, or unrecoverable corruption of on-chain state. For this reason, Aptos relies on defense-in-depth runtime safety checks that independently verify the critical invariants during execution, providing protection against latent verifier bugs and malicious bytecode. This paper motivates and describes the runtime safety checks for Move on Aptos.

cs.PL↗

arXiv2023

Subtractor-Based CNN Inference Accelerator

This paper presents a novel method to boost the performance of CNN inference accelerators by utilizing subtractors. The proposed CNN preprocessing accelerator relies on sorting, grouping, and rounding the weights to create combinations that allow for the replacement of one multiplication operation and addition operation by a single subtraction operation when applying convolution during inference. Given the high cost of multiplication in terms of power and area, replacing it with subtraction allows for a performance boost by reducing power and area. The proposed method allows for controlling the trade-off between performance gains and accuracy loss through increasing or decreasing the usage of subtractors. With a rounding size of 0.05 and by utilizing LeNet-5 with the MNIST dataset, the proposed design can achieve 32.03% power savings and a 24.59% reduction in area at the cost of only 0.1% in terms of accuracy loss.

cs.AR↗