42 citations · 88 across the 34 of their papers we have counts for
35 papers
MLLM-Guided Semantic Correction for Text-to-Video Generation
Junhao Chen, Zheqi Lv, Keting Yin +6
Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic err…
NaviCache: Test-Time Self-Calibration Caching for Video Generation
Zheqi Lv, Zhibo Zhu, Jinke Wang +6
Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive cali…
Training-Free Semantic Correction for Autoregressive Visual Models
Junhao Chen, Chanyu Zhu, Zheqi Lv +2
Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decomposing the generation process i…
DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery
Jiawei Wang, Ming Lei, Yaning Yang +8
Identifying species in biology among tens of thousands of visually similar taxa while discovering unknown species in open-world environments remains a fundamental challenge in biod…
Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation
Tianyu Zhan, Kairui Fu, Chengfei Lv +2
Generative Recommendation (GR) has recently transitioned from atomic item-indexing to Semantic ID (SID)-based frameworks to capture intrinsic item relationships and enhance general…
UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits
Keming Ye, Zhipeng Huang, Canmiao Fu +7
With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source mode…
RASTP: Representation-Aware Semantic Token Pruning for Generative Recommendation with Semantic Identifiers
Tianyu Zhan, Kairui Fu, Zheqi Lv +1
Generative recommendation systems typically leverage Semantic Identifiers (SIDs), which represent each item as a sequence of tokens that encode semantic information. However, repre…
Tackling Device Data Distribution Real-time Shift via Prototype-based Parameter Editing
Zheqi Lv, Wenqiao Zhang, Kairui Fu +6
The on-device real-time data distribution shift on devices challenges the generalization of lightweight on-device models. This critical issue is often overlooked in current researc…
A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
Wenkai Wang, Hongcan Guo, Zheqi Lv +1
Self-evaluation, a model's ability to assess the correctness of its own output, is crucial for Large Multimodal Models (LMMs) to achieve self-improvement in multi-turn conversation…
Graft: Integrating the Domain Knowledge via Efficient Parameter Synergy for MLLMs
Yang Dai, Jianxiang An, Tianwei Lin +6
Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data in…
Device-Cloud Collaborative Correction for On-Device Recommendation
Tianyu Zhan, Shengyu Zhang, Zheqi Lv +4
With the rapid development of recommendation models and device computing power, device-based recommendation has become an important research area due to its better real-time perfor…
Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion
Zheqi Lv, Junhao Chen, Qi Tian +3
Diffusion models have become the mainstream architecture for text-to-image generation, achieving remarkable progress in visual quality and prompt controllability. However, current…
Cuff-KT: Tackling Learners' Real-time Learning Pattern Adjustment via Tuning-Free Knowledge State Guided Model Updating
Yiyun Zhou, Zheqi Lv, Shengyu Zhang +1
Knowledge Tracing (KT) is a core component of Intelligent Tutoring Systems, modeling learners' knowledge state to predict future performance and provide personalized learning suppo…
ThinkRec: Thinking-based recommendation via LLM
Qihang Yu, Kairui Fu, Zheqi Lv +6
Recent advances in large language models (LLMs) have enabled more semantic-aware recommendations through natural language generation. Existing LLM for recommendation (LLM4Rec) meth…
Disentangled Knowledge Tracing for Alleviating Cognitive Bias
Yiyun Zhou, Zheqi Lv, Shengyu Zhang +1
In the realm of Intelligent Tutoring System (ITS), the accurate assessment of students' knowledge states through Knowledge Tracing (KT) is crucial for personalized learning. Howeve…
Optimize Incompatible Parameters through Compatibility-aware Knowledge Integration
Zheqi Lv, Keming Ye, Zishu Wei +7
Deep neural networks have become foundational to advancements in multiple domains, including recommendation systems, natural language processing, and so on. Despite their successes…
Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation
Zheqi Lv, Tianyu Zhan, Wenjie Wang +6
Large Language Models (LLMs) for Recommendation (LLM4Rec) is a promising research direction that has demonstrated exceptional performance in this field. However, its inability to c…
Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation
Kairui Fu, Zheqi Lv, Shengyu Zhang +2
In cloud-centric recommender system, regular data exchanges between user devices and cloud could potentially elevate bandwidth demands and privacy risks. On-device recommendation e…
Cascaded Self-Evaluation Augmented Training for Lightweight Multimodal LLMs
Zheqi Lv, Wenkai Wang, Jiawei Wang +2
Efficient Multimodal Large Language Models (EMLLMs) can improve performance through Chain-of-Thought (CoT) reasoning, but they have poor self-evaluation capabilities during the CoT…
MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation
Haoyu Zheng, Wenqiao Zhang, Zheqi Lv +8
Diffusion-based text-to-image (T2I) models have demonstrated remarkable results in global video editing tasks. However, their focus is primarily on global video modifications, and…
Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework
Jiang Liu, Bolin Li, Haoyuan Li +13
Efficient multimodal large language models (EMLLMs), in contrast to multimodal large language models (MLLMs), reduce model size and computational costs and are often deployed on re…
Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)
Tianyu Zhan, Zheqi Lv, Shengyu Zhang +1
This paper explores the application and effectiveness of Test-Time Training (TTT) layers in improving the performance of recommendation systems. We developed a model, TTT4Rec, util…
Semantic Codebook Learning for Dynamic Recommendation Models
Zheqi Lv, Shaoxuan He, Tianyu Zhan +5
Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve the personalization of sequential recommendation under various user preferen…
DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation
Kairui Fu, Shengyu Zhang, Zheqi Lv +2
Due to the continuously improving capabilities of mobile edges, recommender systems start to deploy models on edges to alleviate network congestion caused by frequent mobile reques…