Yansong Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yansong Tang has a total of 207 co-authors. Here are the top co-authors by number of shared publications:
- Jiwen Lu
Tsinghua University
17 shared publications - Jie Zhou
Tsinghua University, Beijing, China
9 shared publications Haoji Zhang
Tsinghua University
5 shared publicationsJie Zhou
Department of Automation Tsinghua University
5 shared publicationsJingqi Tian
Tsinghua Shenzhen International Graduate School, Tsinghua University
5 shared publications- Xiu Li
Tsinghua University
5 shared publications
Latest Publications
- 25 September 2026
- Published by Springer Nature
- p. 195-211
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
- 25 September 2026
- Published by Springer Nature
- p. 195-211
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
- 14 September 2026
- Published by Springer Nature
- p. 39-56
Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
- 14 September 2026
- Published by Springer Nature
- p. 39-56
Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
- 12 September 2026
- Published by Springer Nature
- p. 619-638
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
- 12 September 2026
- Published by Springer Nature
- p. 619-638
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
- 11 September 2026
- Published by Springer Nature
- p. 163-180
SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
- 11 September 2026
- Published by Springer Nature
- p. 163-180
SAFE-Pruner: Semantic Attention–Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (7) , 10276-10290
Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting
Arbitrary-scale super-resolution is an essential image upsampling task, typically tackled with implicit neural representations. Unlike INR-based methods that rely on slow per-pixel decoding, Gaussian Splatting is promising for arbitrary-scale super-resolution when the explicit region-based nature of GS allows for highly efficient rendering via a lightweight decoder. Recently, Gaussian splatting has outperformed implicit neural methods in 3D scenes. However, existing attempts to address the super-resolution problem with Gaussian splatting face efficiency and accuracy challenges, such as redundant Gaussian primitives and discrete pixel sampling. Efficient Gaussian applications may result in continuous texture constraints due to limited feature richness in explicit fields, particularly the mismatch between the learned Gaussian fields and out-of-distribution sampling rates. Moreover, insufficient discrete sampling based on the given upscale factor may fail to accurately represent the splatted Gaussian field in screen space, causing high-frequency signal redundancy and aliasing. To address these challenges, we propose a compact Gaussian splatting method for efficient arbitrary-scale super-resolution, CGSSR. It constructs an efficient Gaussian space by distilling the image into a reduced number of primitives, each represented by a compact, low-dimensional feature embedding. To balance detail preservation and anti-aliasing, we introduce a scale-aware smoothing filter to regulate splatting frequency. Extensive experiments show that CGSSR achieves superior performance over existing Gaussian-based methods, especially at large scales, with higher efficiency.
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (7) , 10276-10290
Efficient Arbitrary-Scale Super-Resolution With Compact Gaussian Splatting
Arbitrary-scale super-resolution is an essential image upsampling task, typically tackled with implicit neural representations. Unlike INR-based methods that rely on slow per-pixel decoding, Gaussian Splatting is promising for arbitrary-scale super-resolution when the explicit region-based nature of GS allows for highly efficient rendering via a lightweight decoder. Recently, Gaussian splatting has outperformed implicit neural methods in 3D scenes. However, existing attempts to address the super-resolution problem with Gaussian splatting face efficiency and accuracy challenges, such as redundant Gaussian primitives and discrete pixel sampling. Efficient Gaussian applications may result in continuous texture constraints due to limited feature richness in explicit fields, particularly the mismatch between the learned Gaussian fields and out-of-distribution sampling rates. Moreover, insufficient discrete sampling based on the given upscale factor may fail to accurately represent the splatted Gaussian field in screen space, causing high-frequency signal redundancy and aliasing. To address these challenges, we propose a compact Gaussian splatting method for efficient arbitrary-scale super-resolution, CGSSR. It constructs an efficient Gaussian space by distilling the image into a reduced number of primitives, each represented by a compact, low-dimensional feature embedding. To balance detail preservation and anti-aliasing, we introduce a scale-aware smoothing filter to regulate splatting frequency. Extensive experiments show that CGSSR achieves superior performance over existing Gaussian-based methods, especially at large scales, with higher efficiency.
- Open Access
- 12 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (1) , 1-24
Enhancing Pose-Guided Human Image Generation with Comprehensive and Adjustable 3D Control
Pose-guided human image generation aims to render a source image in a specific pose. Current methods predominantly employ 2D-based signals, which exhibit inherent information deficits, as pose conditions. This leads to difficulty in establishing precise source-target appearance-pose correspondence and further causing uncertainty in predicting self-occluded regions’ appearance. To address these issues, we propose a 3D Pose Conditional Diffusion model (3DPCD) that leverages a human parametric model to integrate comprehensive and adjustable 3D control into forward–backward diffusion steps. Specifically, we employ Fourier-transformed SMPL-X as the 3D pose representation to facilitate precise source-target correspondence by understanding the complete pose information. Building on this, we further propose a hierarchical appearance-pose alignment method, which aligns appearance with the complete pose information at both global and local levels. Moreover, motivated by the fact that human pose transformation is a progressive process in 3D space and our 3D pose representation is adjustable, we integrate progressively interpolated 3D control into a series of sampling steps. This effectively mitigates uncertainties in pixel transfer between poses. It should be noted that the proposed explicit pose-guided strategy also supports flexible adjustment of pose, shape, and viewpoint. Both quantitative and qualitative evaluations demonstrate that our 3DPCD outperforms state-of-the-art methods on the widely used DeepFashion InShop benchmark and our newly constructed PoseWeb-33 dataset, which features richer appearance variations and more diverse conditional poses.
- 12 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22  (1) , 1-24
Open AccessEnhancing Pose-Guided Human Image Generation with Comprehensive and Adjustable 3D Control
Pose-guided human image generation aims to render a source image in a specific pose. Current methods predominantly employ 2D-based signals, which exhibit inherent information deficits, as pose conditions. This leads to difficulty in establishing precise source-target appearance-pose correspondence and further causing uncertainty in predicting self-occluded regions’ appearance. To address these issues, we propose a 3D Pose Conditional Diffusion model (3DPCD) that leverages a human parametric model to integrate comprehensive and adjustable 3D control into forward–backward diffusion steps. Specifically, we employ Fourier-transformed SMPL-X as the 3D pose representation to facilitate precise source-target correspondence by understanding the complete pose information. Building on this, we further propose a hierarchical appearance-pose alignment method, which aligns appearance with the complete pose information at both global and local levels. Moreover, motivated by the fact that human pose transformation is a progressive process in 3D space and our 3D pose representation is adjustable, we integrate progressively interpolated 3D control into a series of sampling steps. This effectively mitigates uncertainties in pixel transfer between poses. It should be noted that the proposed explicit pose-guided strategy also supports flexible adjustment of pose, shape, and viewpoint. Both quantitative and qualitative evaluations demonstrate that our 3DPCD outperforms state-of-the-art methods on the widely used DeepFashion InShop benchmark and our newly constructed PoseWeb-33 dataset, which features richer appearance variations and more diverse conditional poses.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10195-10210
Decomposed Structural Pattern Banks for Efficient Screen Content Image Super-Resolution
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 10195-10210
Decomposed Structural Pattern Banks for Efficient Screen Content Image Super-Resolution
- Open Access
Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines. However, current approaches in long video generation typically rely on window attention, which naively discards historical context outside the window, leading to catastrophic forgetting and scene inconsistency; conversely, retaining full history incurs prohibitive memory costs. To address this trade-off, we propose Memorize-and-Generate (MAG), a framework that decouples memory compression and frame generation into distinct tasks. Specifically, we train a memory model to compress historical information into a compact KV cache, and a separate generator model to synthesize subsequent frames utilizing this compressed representation. Furthermore, we introduce MAG-Bench to strictly evaluate historical memory retention. Extensive experiments demonstrate that MAG achieves superior historical scene consistency while maintaining competitive performance on standard video generation benchmarks.
Open AccessMemorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines. However, current approaches in long video generation typically rely on window attention, which naively discards historical context outside the window, leading to catastrophic forgetting and scene inconsistency; conversely, retaining full history incurs prohibitive memory costs. To address this trade-off, we propose Memorize-and-Generate (MAG), a framework that decouples memory compression and frame generation into distinct tasks. Specifically, we train a memory model to compress historical information into a compact KV cache, and a separate generator model to synthesize subsequent frames utilizing this compressed representation. Furthermore, we introduce MAG-Bench to strictly evaluate historical memory retention. Extensive experiments demonstrate that MAG achieves superior historical scene consistency while maintaining competitive performance on standard video generation benchmarks.
- Open Access
DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation
Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual misalignment, which lead to biases toward louder or larger objects while overlooking weaker, smaller, or co-occurring sources. To address these challenges, we propose DDAVS, a Disentangled Audio Semantics and Delayed Bidirectional Alignment framework. To mitigate multi-source entanglement, DDAVS employs learnable queries to extract audio semantics and anchor them within a structured semantic space derived from an audio prototype memory bank. This is further optimized through contrastive learning to enhance discriminability and robustness. To alleviate audio-visual misalignment, DDAVS introduces dual cross-attention with delayed modality interaction, improving the robustness of multimodal alignment. Extensive experiments on the AVS-Objects and VPO benchmarks demonstrate that DDAVS consistently outperforms existing approaches, exhibiting strong performance across single-source, multi-source, and multi-instance scenarios. These results validate the effectiveness and generalization ability of our framework under challenging real-world audio-visual segmentation conditions. Project page: https://trilarflagz.github.io/DDAVS-page/
Open AccessDDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation
Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by jointly leveraging auditory and visual information. However, existing methods often suffer from multi-source entanglement and audio-visual misalignment, which lead to biases toward louder or larger objects while overlooking weaker, smaller, or co-occurring sources. To address these challenges, we propose DDAVS, a Disentangled Audio Semantics and Delayed Bidirectional Alignment framework. To mitigate multi-source entanglement, DDAVS employs learnable queries to extract audio semantics and anchor them within a structured semantic space derived from an audio prototype memory bank. This is further optimized through contrastive learning to enhance discriminability and robustness. To alleviate audio-visual misalignment, DDAVS introduces dual cross-attention with delayed modality interaction, improving the robustness of multimodal alignment. Extensive experiments on the AVS-Objects and VPO benchmarks demonstrate that DDAVS consistently outperforms existing approaches, exhibiting strong performance across single-source, multi-source, and multi-instance scenarios. These results validate the effectiveness and generalization ability of our framework under challenging real-world audio-visual segmentation conditions. Project page: https://trilarflagz.github.io/DDAVS-page/