12 citations · 18 across the 21 of their papers we have counts for
23 papers
SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding
Senbin Xu, Zijun Zhang, Xinhua Wu +7
Streaming video understanding requires answering questions from the observed video, with evidence drawn from recent observations or earlier events. Historical context can improve r…
Generative Transmission: Rethinking Computation, Bandwidth, and Memory in Communication
Xiangyu Chen, Jixiang Luo, Yuankai Fan +3
Under the AI Flow framework, communication is shifting from transmitting fidelity-oriented information flows toward delivering task-oriented and perception-oriented token flows acr…
Visual Implicit Autoregressive Modeling
Pengfei Jiang, Jixiang Luo, Luxi Lin +2
Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and i…
Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation
Luxi Lin, Zhihang Lin, Zhanpeng Zeng +5
Speculative decoding accelerates LLM inference but suffers from performance degradation when target models are fine-tuned for specific domains. A naive solution is to retrain draft…
STMI: Segmentation-Guided Token Modulation with Cross-Modal Hypergraph Interaction for Multi-Modal Object Re-Identification
Xingguo Xu, Zhanyu Liu, Weixiang Zhou +5
Multi-modal object Re-Identification (ReID) aims to exploit complementary information from different modalities to retrieve specific objects. However, existing methods often rely o…
Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission
Xiangyu Chen, Jixiang Luo, Jingyu Xu +3
Whether a video can be compressed at an extreme compression rate as low as 0.01%? To this end, we achieve the compression rate as 0.02% at some cases by introducing Generative Vide…
TeleMem: Building Long-Term and Multimodal Memory for Agentic AI
Chunliang Chen, Ming Guan, Xiao Lin +8
Large language models (LLMs) excel at many NLP tasks but struggle to sustain long-term interactions due to limited attention over extended dialogue histories. Retrieval-augmented g…
Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management
Changzhi Sun, Xiangyu Chen, Jixiang Luo +2
External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is st…
EV-NVC: Efficient Variable bitrate Neural Video Compression
Yongcun Hu, Yingzhen Zhai, Jixiang Luo +4
Training neural video codec (NVC) with variable rate is a highly challenging task due to its complex training strategies and model structure. In this paper, we train an efficient v…
TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
Jiaqi Yan, Ruilong Ren, Jingren Liu +13
Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing…
Infinite Video Understanding
Dell Zhang, Xiangyu Chen, Jixiang Luo +6
The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental ch…
Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation
Yuansheng Gao, Peng Gao, Han Bao +4
Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online interactions. Detecting such behavior is…
SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding
Qianqian Sun, Jixiang Luo, Dell Zhang +1
Recent advancements in image editing have utilized large-scale multimodal models to enable intuitive, natural instruction-driven interactions. However, conventional methods still f…
Rethinking Learned Image Compression: Context is All You Need
Jixiang Luo
Since LIC has made rapid progress recently compared to traditional methods, this paper attempts to discuss the question about 'Where is the boundary of Learned Image Compression(LI…
Task-Aware Encoder Control for Deep Video Compression
Xingtong Ge, Jixiang Luo, Xinjie Zhang +7
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In c…
Compressible and Searchable: AI-native Multi-Modal Retrieval System with Learned Image Compression
Jixiang Luo
The burgeoning volume of digital content across diverse modalities necessitates efficient storage and retrieval methods. Conventional approaches struggle to cope with the escalatin…
Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization
Jixiang Luo, Yan Wang, Hongwei Qin
Learned Image Compression (LIC) has achieved dramatic progress regarding objective and subjective metrics. MSE-based models aim to improve objective metrics while generative models…
Unified learning-based lossy and lossless JPEG recompression
Jianghui Zhang, Yuanyuan Wang, Lina Guo +5
JPEG is still the most widely used image compression algorithm. Most image compression algorithms only consider uncompressed original image, while ignoring a large number of alread…
Efficient Learned Lossless JPEG Recompression
Lina Guo, Yuanyuan Wang, Tongda Xu +6
JPEG is one of the most popular image compression methods. It is beneficial to compress those existing JPEG files without introducing additional distortion. In this paper, we propo…
Learned Lossless Compression for JPEG via Frequency-Domain Prediction
Jixiang Luo, Shaohui Li, Wenrui Dai +3
JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well tra…
Evaluating the Practicality of Learned Image Compression
Hongjiu Yu, Qiancheng Sun, Jin Hu +9
Learned image compression has achieved extraordinary rate-distortion performance in PSNR and MS-SSIM compared to traditional methods. However, it suffers from intensive computation…
PO-ELIC: Perception-Oriented Efficient Learned Image Coding
Dailan He, Ziming Yang, Hongjiu Yu +7
In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate re…
GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising
Kecheng Chen, Jiayu Sun, Jiang Shen +8
Being low-level radiation exposure and less harmful to health, low-dose computed tomography (LDCT) has been widely adopted in the early screening of lung cancer and COVID-19. LDCT…