Selected work

Representative Papers

Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

Sep 24, 2026

This study addresses the challenge in Retrieval-Augmented Generation (RAG) where conflicts between externally retrieved knowledge and internal parametric knowledge often lead to unreliable responses. To mitigate this issue, this work proposes TRACE, a novel framework that introduces a fine-grained supervision mechanism for knowledge source selection based on multi-agent debate trajectories. Furthermore, it incorporates answer completeness regularization during model fine-tuning. By mining high-quality supervision signals from these debate trajectories and reinforcing the generation of tail segments in answers, the proposed approach significantly enhances the model's robustness against misleading knowledge while effectively alleviating the problem of incomplete responses.

0 citationsRead paper

Selective Amortization of Full-Budget Counterfactual Reasoning for Visual Token Communication

Sep 24, 2026

This study addresses the high computational overhead of full-budget counterfactual evaluation in generative image communication by proposing the ACV-Gate framework. This framework integrates terminal value learning with adaptive candidate evaluation to establish a controllable computation allocation mechanism. Specifically, it employs an ensemble-aware student network, terminal advantage and regret training, and local minimum description length (MDL) with cost thresholding to selectively execute approximate evaluations or exact computations, thereby optimizing token selection and reconstruction quality. Experimental results on CIFAR-10 demonstrate that the proposed method improves PSNR by 0.636 dB while reducing the number of evaluations to 27.6% of those required by expert mode, significantly enhancing communication performance under low-bitrate conditions.

0 citationsRead paper

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

Aug 17, 2026

This study addresses the misalignment between existing visual token selection criteria and reconstruction quality under fixed bandwidth constraints. We propose Gated Counterfactual Rectification (GCR-C), a method that constructs candidate sets and performs full-budget counterfactual evaluations to dynamically replace baseline actions only when positive gains are confirmed. This approach effectively bridges the gap between selection strategies and final reconstruction outcomes. Experiments demonstrate that GCR-C significantly improves reconstruction quality at low-to-medium bitrates across diverse datasets and channel conditions without increasing actual bitrate consumption. Furthermore, the method exhibits robust generalization capabilities, establishing a novel paradigm for communication-aware reconstruction tasks.

0 citationsRead paper

Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems

Jun 24, 2026

This work addresses the challenge of balancing semantic fidelity and transmission efficiency in resource-constrained visual Internet-of-Things systems by proposing a semantic-aware generative image transmission framework. The approach integrates instance segmentation–driven semantic scoring with prediction entropy–guided recoverability assessment to intelligently sample discrete VQ tokens, and leverages MaskGIT for reconstructing missing content at the edge or cloud. Spatially dispersed scheduling via Halton sequences is introduced to enhance generation quality. At a bitrate of 0.074 bpp—only 44.6% of that required by DeepJSCC/WITT—the method achieves a PSNR of 29.9 dB, while downstream detection tasks demonstrate that its semantic masking strategy significantly outperforms random masking.

0 citationsRead paper

Recent publications

Latest Papers

Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

Sep 24, 2026

This study addresses the challenge in Retrieval-Augmented Generation (RAG) where conflicts between externally retrieved knowledge and internal parametric knowledge often lead to unreliable responses. To mitigate this issue, this work proposes TRACE, a novel framework that introduces a fine-grained supervision mechanism for knowledge source selection based on multi-agent debate trajectories. Furthermore, it incorporates answer completeness regularization during model fine-tuning. By mining high-quality supervision signals from these debate trajectories and reinforcing the generation of tail segments in answers, the proposed approach significantly enhances the model's robustness against misleading knowledge while effectively alleviating the problem of incomplete responses.

0 citationsRead paper

Selective Amortization of Full-Budget Counterfactual Reasoning for Visual Token Communication

Sep 24, 2026

This study addresses the high computational overhead of full-budget counterfactual evaluation in generative image communication by proposing the ACV-Gate framework. This framework integrates terminal value learning with adaptive candidate evaluation to establish a controllable computation allocation mechanism. Specifically, it employs an ensemble-aware student network, terminal advantage and regret training, and local minimum description length (MDL) with cost thresholding to selectively execute approximate evaluations or exact computations, thereby optimizing token selection and reconstruction quality. Experimental results on CIFAR-10 demonstrate that the proposed method improves PSNR by 0.636 dB while reducing the number of evaluations to 27.6% of those required by expert mode, significantly enhancing communication performance under low-bitrate conditions.

0 citationsRead paper

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

Aug 17, 2026

This study addresses the misalignment between existing visual token selection criteria and reconstruction quality under fixed bandwidth constraints. We propose Gated Counterfactual Rectification (GCR-C), a method that constructs candidate sets and performs full-budget counterfactual evaluations to dynamically replace baseline actions only when positive gains are confirmed. This approach effectively bridges the gap between selection strategies and final reconstruction outcomes. Experiments demonstrate that GCR-C significantly improves reconstruction quality at low-to-medium bitrates across diverse datasets and channel conditions without increasing actual bitrate consumption. Furthermore, the method exhibits robust generalization capabilities, establishing a novel paradigm for communication-aware reconstruction tasks.

0 citationsRead paper

Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems

Jun 24, 2026

This work addresses the challenge of balancing semantic fidelity and transmission efficiency in resource-constrained visual Internet-of-Things systems by proposing a semantic-aware generative image transmission framework. The approach integrates instance segmentation–driven semantic scoring with prediction entropy–guided recoverability assessment to intelligently sample discrete VQ tokens, and leverages MaskGIT for reconstructing missing content at the edge or cloud. Spatially dispersed scheduling via Halton sequences is introduced to enhance generation quality. At a bitrate of 0.074 bpp—only 44.6% of that required by DeepJSCC/WITT—the method achieves a PSNR of 29.9 dB, while downstream detection tasks demonstrate that its semantic masking strategy significantly outperforms random masking.

0 citationsRead paper