Jingjing Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jingjing Chen has a total of 159 co-authors. Here are the top co-authors by number of shared publications:
- Yu-Gang Jiang
Fudan University, China
38 shared publications - Bin Zhu
Singapore Management University, Singapore, Singapore
15 shared publications Yu-Gang Jiang
13 shared publications- Zuxuan Wu
Fudan University, China
9 shared publications - Chong-Wah Ngo
Singapore Management University, Singapore
8 shared publications - Zhipeng Wei
Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China
8 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5145-5153
SVIE: Stitching Video Priors for Physics-Aware Image Editing
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5145-5153
Open AccessSVIE: Stitching Video Priors for Physics-Aware Image Editing
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4465-4474
SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4465-4474
Open AccessSphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5523-5532
SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5523-5532
Open AccessSpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3971-3979
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3971-3979
Open AccessDisentangling Semantic Attention from Structural Bias in the Attention Manifold
- 3 October 2026
- Published by Springer Nature
- p. 39-56
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
- 3 October 2026
- Published by Springer Nature
- p. 39-56
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
- 12 September 2026
- Published by Springer Nature
- p. 560-576
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
- 12 September 2026
- Published by Springer Nature
- p. 560-576
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2457-2466
RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2457-2466
Open AccessRoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (6) , 7050-7061
Enhancing Adversarial Transferability With Cost-Efficient Landscape Flattening
The transferability of adversarial examples across different models has drawn considerable attention recently, particularly in targeted transferability. Prior research has empirically shown that optimizing adversarial perturbations at neighboring points with the highest loss value improves transferability. While effective, such a method requires multiple iterations to reach the local maxima and disregards the local minima of the input loss landscape. In this paper, we theoretically show that enhancing adversarial transferability is attainable by flattening the input loss landscape. This is accomplished through the perturbation optimization at both local maxima and minima. Moreover, we propose the Cost-efficient LandscapE Flattening (CLEF) attack to consider local maxima and minima around current inputs in a cost-efficient way to flatten the loss landscape and improve adversarial transferability. Specifically, we reuse the gradients of the previous attack step to assist current inputs in reaching local maxima, and employ probabilistic modeling to learn the distributional representations of perturbations that assist current inputs in reaching local minima. This probabilistic modeling can be pre-trained on dozens of images from other domains, enabling us to directly sample this type of perturbation from the pre-trained distribution when attacking. Experimental results demonstrate that integrating local maxima and minima into targeted transferable attacks can significantly flatten the loss landscape of the crafted adversarial examples, resulting in improved adversarial transferability.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (6) , 7050-7061
Enhancing Adversarial Transferability With Cost-Efficient Landscape Flattening
The transferability of adversarial examples across different models has drawn considerable attention recently, particularly in targeted transferability. Prior research has empirically shown that optimizing adversarial perturbations at neighboring points with the highest loss value improves transferability. While effective, such a method requires multiple iterations to reach the local maxima and disregards the local minima of the input loss landscape. In this paper, we theoretically show that enhancing adversarial transferability is attainable by flattening the input loss landscape. This is accomplished through the perturbation optimization at both local maxima and minima. Moreover, we propose the Cost-efficient LandscapE Flattening (CLEF) attack to consider local maxima and minima around current inputs in a cost-efficient way to flatten the loss landscape and improve adversarial transferability. Specifically, we reuse the gradients of the previous attack step to assist current inputs in reaching local maxima, and employ probabilistic modeling to learn the distributional representations of perturbations that assist current inputs in reaching local minima. This probabilistic modeling can be pre-trained on dozens of images from other domains, enabling us to directly sample this type of perturbation from the pre-trained distribution when attacking. Experimental results demonstrate that integrating local maxima and minima into targeted transferable attacks can significantly flatten the loss landscape of the crafted adversarial examples, resulting in improved adversarial transferability.
- Open Access
Predicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction
Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are consistent proxies for importance across all heads. However, this overlooks the heterogeneity in predictive fidelity across attention heads. While certain heads prioritize the instantaneous contribution of tokens, others are dedicated to capturing long-horizon utility. In this paper, we propose that optimal budget allocation should be governed by the marginal utility in preserving long-term semantic information. Based on this insight, we propose LU-KV, a novel framework that optimizes head-level budget allocation through a convex-hull relaxation and a marginal-utility-based greedy solver to achieve near-optimal precision. Furthermore, we implement a data-driven offline profiling protocol to facilitate the practical deployment of LU-KV. Extensive evaluations on LongBench and RULER benchmarks demonstrate that LU-KV achieves an 80% reduction in KV cache size with minimal performance degradation, while simultaneously reducing inference latency and GPU memory footprint.
Open AccessPredicting Future Utility: Global Combinatorial Optimization for Task-Agnostic KV Cache Eviction
Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are consistent proxies for importance across all heads. However, this overlooks the heterogeneity in predictive fidelity across attention heads. While certain heads prioritize the instantaneous contribution of tokens, others are dedicated to capturing long-horizon utility. In this paper, we propose that optimal budget allocation should be governed by the marginal utility in preserving long-term semantic information. Based on this insight, we propose LU-KV, a novel framework that optimizes head-level budget allocation through a convex-hull relaxation and a marginal-utility-based greedy solver to achieve near-optimal precision. Furthermore, we implement a data-driven offline profiling protocol to facilitate the practical deployment of LU-KV. Extensive evaluations on LongBench and RULER benchmarks demonstrate that LU-KV achieves an 80% reduction in KV cache size with minimal performance degradation, while simultaneously reducing inference latency and GPU memory footprint.
- 6 February 2026
- Published by Springer Nature
- p. 188-202
Benchmarking Gaslighting Negation Attacks Against Reasoning Models
- 6 February 2026
- Published by Springer Nature
- p. 188-202
Benchmarking Gaslighting Negation Attacks Against Reasoning Models