1 citations · 4 across the 22 of their papers we have counts for
24 papers
SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation
Keyu Tu, Zhuowei Chen, Mengqi Huang +4
We introduce Semantic Task Completion Video Generation, an outcome-oriented video generation task. Under this formulation, success requires both achievement of the intended outcome…
EmoStyle: Affective Conditioning of Style-Specialist Experts for Emotional Image Generation
Dexiang Hong, Yijie Guo, Weidong Chen +4
Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion. In this challenge, the main…
See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning
Xiaojie Li, Xin Jiang, Luanyuan Dai +3
Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underlying differences. Existing m…
Towards Accurate Emotion-Attributed Video Captioning via Fine-grained Emotion-Cause Pair Extraction
Weidong Chen, Cheng Ye, Zhendong Mao +3
Emotional Video Captioning (EVC) is a challenging task that aims to generate factually accurate and emotionally rich descriptions for videos. Existing EVC methods leverage holistic…
Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
Huatian Zhang, Zhendong Mao, Lei Zhang +1
Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) by learning from preference pai…
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Bin Wu, Mengqi Huang, Shaojin Wu +4
Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the d…
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
Jiaang Li, Zhendong Mao, Quan Wang +2
Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhi…
CreatiParser: Generative Image Parsing of Raster Graphic Designs into Editable Layers
Weidong Chen, Dexiang Hong, Zhendong Mao +4
Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explic…
FACE-net: Factual Calibration and Emotion Augmentation for Retrieval-enhanced Emotional Video Captioning
Weidong Chen, Cheng Ye, Zhendong Mao +5
Emotional Video Captioning (EVC) is an emerging task, which aims to describe factual content with the intrinsic emotions expressed in videos. Existing works perceive global emotion…
Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles
Shaohan Wang, Benfeng Xu, Licheng Zhang +5
Deep Research Agents (DRAs) have demonstrated remarkable capabilities in autonomous information retrieval and report generation, showing great potential to assist humans in complex…
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
Chiwei Zhu, Benfeng Xu, Mingxuan Du +4
Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research often exceed model context limits…
In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback
Mingye Zhu, Yi Liu, Zheren Fu +2
Training Large Language Models (LLMs) for chain-of-thought reasoning presents a significant challenge: supervised fine-tuning on a single "golden" rationale hurts generalization as…
SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder
Dengcan Liu, Jiahao Li, Zheren Fu +4
Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. Howev…
Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models
Hou Xia, Zheren Fu, Fangcan Ling +4
Large video language models (LVLMs) have made notable progress in video understanding, spurring the development of corresponding evaluation benchmarks. However, existing benchmarks…
Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
Yihan Chen, Benfeng Xu, Xiaorui Wang +2
Autonomous agents, which perceive environments and take actions to achieve goals, have become increasingly feasible with the advancements in large language models (LLMs). However,…
Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
Yi Liu, Dianqing Liu, Mingye Zhu +3
The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods…
Leveraging Robust Optimization for LLM Alignment under Distribution Shifts
Mingye Zhu, Yi Liu, Zheren Fu +2
Preference alignment methods are increasingly critical for steering large language models (LLMs) to generate outputs consistent with human values. While recent approaches often rel…
Composed Multi-modal Retrieval: A Survey of Approaches and Applications
Kun Zhang, Jingyu Li, Zhe Li +10
The burgeoning volume of multi-modal data necessitates advanced retrieval paradigms beyond unimodal and cross-modal approaches. Composed Multi-modal Retrieval (CMR) emerges as a pi…
ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA
Jiaang Li, Quan Wang, Zhongnan Wang +2
Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors. Most model editing methods are solely designed for…
RealCustom++: Representing Images as Real Textual Word for Real-Time Customization
Zhendong Mao, Mengqi Huang, Fei Ding +3
Given a text and an image of a specific subject, text-to-image customization aims to generate new images that align with both the text and the subject's appearance. Existing works…
RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Mengqi Huang, Zhendong Mao, Mingcong Liu +2
Text-to-image customization, which aims to synthesize text-driven images for the given subjects, has recently revolutionized content creation. Existing works follow the pseudo-word…
Grammatical Error Correction via Mixed-Grained Weighted Training
Jiahao Li, Quan Wang, Chiwei Zhu +2
The task of Grammatical Error Correction (GEC) aims to automatically correct grammatical errors in natural texts. Almost all previous works treat annotated training data equally, b…
On the Calibration of Large Language Models and Alignment
Chiwei Zhu, Benfeng Xu, Quan Wang +2
As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an…
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation
Tianqi Zhong, Quan Wang, Jingxuan Han +2
Controllable text generation (CTG) aims to generate text with desired attributes, and decoding-time-based methods have shown promising performance on this task. However, in this pa…