1.1k citations · 1.1k across the 38 of their papers we have counts for
42 papers
What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle
Peilin Wang, Feng Shiyang, Hongfu Gao +4
Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer recursive paths is also expo…
RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance
Yiming Liu, Ben Wan, Tongxuan Liu +5
Diffusion models enable high-quality visual generation, but iterative denoising remains computationally expensive, especially under classifier-free guidance (CFG), which requires b…
Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models
Yiwen Liang, Hui Chen, Yizhe Xiong +7
Test-time adaptation (TTA) has been widely explored in single-label recognition, effectively mitigating distribution shifts, especially when combined with vision-language models. H…
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
Chuangxin Zhao, Canran Xiao, Siyuan Ma +5
Multimodal large language models (MLLMs) are increasingly required to adapt to non-stationary streams of visual domains, question types, and user instructions, yet continual fine-t…
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing
Zihan Tang, Leqi Shen, Hui Chen +7
Vision-Language Models (VLMs) have shown strong promise on Optical Character Recognition (OCR), yet the sheer number of visual tokens required to encode dense documents incurs proh…
CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension
Lihao Liu, Yan Wang, Biao Yang +10
Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct applic…
OOCO: Latency-disaggregated Architecture for Online-Offline Co-locate LLM Serving
Siyu Wu, Zihan Tang, Yuting Zeng +5
Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving…
Tracking and Segmenting Anything in Any Modality
Tianlu Zhang, Qiang Zhang, Guiguang Ding +1
Tracking and segmentation play essential roles in video understanding, providing basic positional information and temporal association of objects within video sequences. Despite th…
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
Fengyuan Sun, Hui Chen, Xinhao Xu +5
While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon,…
Source-Free Object Detection with Detection Transformer
Huizai Yao, Sicheng Zhao, Shuo Lu +7
Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existi…
xLLM Technical Report
Tongxuan Liu, Tao Peng, Peijun Yang +50
We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimi…
Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
Yiwen Liang, Hui Chen, Yizhe Xiong +7
Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable, which has motiva…
Neutralizing Token Aggregation via Information Augmentation for Efficient Test-Time Adaptation
Yizhe Xiong, Zihan Zhou, Yiwen Liang +6
Test-Time Adaptation (TTA) has emerged as an effective solution for adapting Vision Transformers (ViT) to distribution shifts without additional training data. However, existing TT…
Fast Quiet-STaR: Thinking Without Thought Tokens
Wei Huang, Yizhe Xiong, Xin Ye +4
Large Language Models (LLMs) have achieved impressive performance across a range of natural language processing tasks. However, recent advances demonstrate that further gains parti…
LSNet: See Large, Focus Small
Ao Wang, Hui Chen, Zijia Lin +2
Vision network designs, including Convolutional Neural Networks and Vision Transformers, have significantly advanced the field of computer vision. Yet, their complex computations p…
Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning
Mengyao Lyu, Yan Li, Huasong Zhong +5
The hypothesis that pretrained large language models (LLMs) necessitate only minimal supervision during the fine-tuning (SFT) stage (Zhou et al., 2024) has been substantiated by re…
YOLOE: Real-Time Seeing Anything
Ao Wang, Lihao Liu, Hui Chen +3
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predef…
Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts
Leiyu Pan, Zhenpeng Su, Minxuan Lv +10
Large language models have demonstrated exceptional performance across a wide range of tasks. However, dense models usually suffer from sparse activation, where many activation val…
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
Minxuan Lv, Zhenpeng Su, Leiyu Pan +10
As large language models continue to scale, computational costs and resource consumption have emerged as significant challenges. While existing sparsification methods like pruning…
UniAttn: Reducing Inference Costs via Softmax Unification for Post-Training LLMs
Yizhe Xiong, Wei Huang, Xin Ye +6
Post-training is essential for adapting Large Language Models (LLMs) to real-world applications. Deploying post-trained models faces significant challenges due to substantial memor…
YOLO-UniOW: Efficient Universal Open-World Object Detection
Lihao Liu, Juexiao Feng, Hui Chen +4
Traditional object detection models are constrained by the limitations of closed-set datasets, detecting only categories encountered during training. While multimodal models have e…
Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning
Hui-Yue Yang, Hui Chen, Ao Wang +7
Segment Anything Model (SAM) has made great progress in anomaly segmentation tasks due to its impressive generalization ability. However, existing methods that directly apply SAM t…
Breaking the Stage Barrier: A Novel Single-Stage Approach to Long Context Extension for Large Language Models
Haoran Lian, Junmin Chen, Wei Huang +8
Recently, Large language models (LLMs) have revolutionized Natural Language Processing (NLP). Pretrained LLMs, due to limited training context size, struggle with handling long tok…
[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs
Ao Wang, Fengyuan Sun, Hui Chen +3
Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across a wide range of vision-language tasks, garnering significant attention in the computer…