Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
本文介绍了一个名为Quanta的Python库，通过融合量化嵌入、词法索引和知识图谱的方法解决了混合检索系统集成复杂的问题。
0 citationsRead paper
Selected work
Representative Papers
Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation
"This study addresses the challenge of enhancing the accuracy of field plant disease diagnosis by proposing a Hybrid Hierarchical Multi-Agent Framework (H²MAF). This framework integrates the decision outputs from EfficientNet-B3 and ConvNeXt-Tiny visual models, leveraging multimodal large language models such as Gemma 4 E4B and Qwen3.5 4B for semantic arbitration. The method generates explainable diagnoses, risk levels, and treatment urgency assessments based on JSON-formatted evidence. Experimental results demonstrate that H²MAF significantly improves diagnostic accuracy, particularly in conflict data subsets, with an increase from 63.9% to 68.5% on the PlantDoc dataset, and a 7.6% improvement in CNN prediction conflicts. Furthermore, the framework achieves high accuracy rates of 99.3% and 98.9% on real-world field datasets from Cornell University."
0 citationsRead paper
Selective Credibility-Limited Belief Update
This work addresses a key limitation of traditional credibility-limited belief revision, which treats cognitive inputs as indivisible wholes and thus struggles to handle composite inputs where only parts are realizable. To overcome this, the paper proposes a selective credibility-limited belief revision framework that introduces a source-world-dependent mechanism for selectively accepting input components, transforming them into weaker proxies before performing revision. The framework defines two well-behaved classes of update operators—consistency-preserving and maximally consistency-preserving—and provides both semantic characterizations and axiomatic foundations by integrating proxy transformation functions with credibility-based accessibility relations to model belief dynamics. Theoretical analysis demonstrates that this approach strictly generalizes and unifies the Katsuno-Mendelzon update semantics and existing credibility-limited methods, offering enhanced expressivity and broader applicability.
0 citationsRead paper
Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Networks
This work addresses the challenges posed by large language models—such as high latency, hallucination, and insufficient control guarantees—in meeting the near-real-time scheduling demands of 5G/6G vehicular networks (V2X). To overcome these limitations, the authors propose Agentic-V2X, a novel architecture that employs a compact local language model as a non-real-time rApp policy generator, working in tandem with a lightweight xApp-style controller to periodically produce and execute verified, deadline-aware scheduling policies. The framework incorporates policy verification and repair mechanisms, along with telemetry-driven structured policy generation and adaptive scheduling weight adjustment. Evaluated on the ns-3/ns3-ai platform, Agentic-V2X demonstrates superior reliability over proportional fairness in scheduling critical services under high-density scenarios, effectively balancing policy flexibility with execution safety and exhibiting strong practical applicability.
0 citationsRead paper
Simple Power Analysis on Post-Quantum Code Based Cryptosystems
This study investigates whether code-based post-quantum cryptographic schemes, such as McEliece and BIKE, are vulnerable to side-channel attacks during the decapsulation phase that could leak secret keys through power consumption. Using low-cost equipment to capture electromagnetic emissions and combining simple power analysis (SPA) with machine learning modeling, the authors demonstrate—for the first time—that partial bits of the session key can be successfully recovered using only 200 power traces. The experiments reveal a strong correlation between electromagnetic emanations during decapsulation and secret key values, providing concrete evidence of practical side-channel vulnerabilities in these schemes. These findings underscore the necessity of incorporating physical security considerations into the design and deployment of post-quantum cryptographic implementations.
0 citationsRead paper
Recent publications
Latest Papers
Quanta: A Self-Contained Python Library for Hybrid Retrieval over Quantised Embeddings, Lexical Indexes, and Knowledge Graphs
本文介绍了一个名为Quanta的Python库，通过融合量化嵌入、词法索引和知识图谱的方法解决了混合检索系统集成复杂的问题。
0 citationsRead paper
Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation
"This study addresses the challenge of enhancing the accuracy of field plant disease diagnosis by proposing a Hybrid Hierarchical Multi-Agent Framework (H²MAF). This framework integrates the decision outputs from EfficientNet-B3 and ConvNeXt-Tiny visual models, leveraging multimodal large language models such as Gemma 4 E4B and Qwen3.5 4B for semantic arbitration. The method generates explainable diagnoses, risk levels, and treatment urgency assessments based on JSON-formatted evidence. Experimental results demonstrate that H²MAF significantly improves diagnostic accuracy, particularly in conflict data subsets, with an increase from 63.9% to 68.5% on the PlantDoc dataset, and a 7.6% improvement in CNN prediction conflicts. Furthermore, the framework achieves high accuracy rates of 99.3% and 98.9% on real-world field datasets from Cornell University."
0 citationsRead paper
Selective Credibility-Limited Belief Update
This work addresses a key limitation of traditional credibility-limited belief revision, which treats cognitive inputs as indivisible wholes and thus struggles to handle composite inputs where only parts are realizable. To overcome this, the paper proposes a selective credibility-limited belief revision framework that introduces a source-world-dependent mechanism for selectively accepting input components, transforming them into weaker proxies before performing revision. The framework defines two well-behaved classes of update operators—consistency-preserving and maximally consistency-preserving—and provides both semantic characterizations and axiomatic foundations by integrating proxy transformation functions with credibility-based accessibility relations to model belief dynamics. Theoretical analysis demonstrates that this approach strictly generalizes and unifies the Katsuno-Mendelzon update semantics and existing credibility-limited methods, offering enhanced expressivity and broader applicability.
0 citationsRead paper
Agentic-V2X: Small Language Model Agents for Deadline-Aware V2X Scheduling in 5G/6G Networks
This work addresses the challenges posed by large language models—such as high latency, hallucination, and insufficient control guarantees—in meeting the near-real-time scheduling demands of 5G/6G vehicular networks (V2X). To overcome these limitations, the authors propose Agentic-V2X, a novel architecture that employs a compact local language model as a non-real-time rApp policy generator, working in tandem with a lightweight xApp-style controller to periodically produce and execute verified, deadline-aware scheduling policies. The framework incorporates policy verification and repair mechanisms, along with telemetry-driven structured policy generation and adaptive scheduling weight adjustment. Evaluated on the ns-3/ns3-ai platform, Agentic-V2X demonstrates superior reliability over proportional fairness in scheduling critical services under high-density scenarios, effectively balancing policy flexibility with execution safety and exhibiting strong practical applicability.
0 citationsRead paper
Simple Power Analysis on Post-Quantum Code Based Cryptosystems
This study investigates whether code-based post-quantum cryptographic schemes, such as McEliece and BIKE, are vulnerable to side-channel attacks during the decapsulation phase that could leak secret keys through power consumption. Using low-cost equipment to capture electromagnetic emissions and combining simple power analysis (SPA) with machine learning modeling, the authors demonstrate—for the first time—that partial bits of the session key can be successfully recovered using only 200 power traces. The experiments reveal a strong correlation between electromagnetic emanations during decapsulation and secret key values, providing concrete evidence of practical side-channel vulnerabilities in these schemes. These findings underscore the necessity of incorporating physical security considerations into the design and deployment of post-quantum cryptographic implementations.
0 citationsRead paper