4 citations · 7 across the 26 of their papers we have counts for
32 papers
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
Chenhao Dang, Siyuan Xiong, Conghui He +1
Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to continually…
One Query, Many Scales: Sparse Mixture-of-Experts for Efficient Hierarchical Cross-View Geo-Localization
Ruijie Fan, Junyan Ye, Qi Zhu +1
Cross-view geo-localization (CVGL) retrieves geo-tagged satellite imagery for a ground-view query. Most systems exhaustively search a flat, fixed-resolution gallery, incurring high…
PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs
Haojie Hu, Chenhao Dang, Yaojia Liu +3
Scientific poster construction compresses a long multimodal paper into a readable, editable canvas. Existing systems hide request-level failures by scoring only completed outputs;…
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
Haocong He, Chenfei Liao, Zichen Wen +13
Multimodal Large Language Models (MLLMs) have demonstrated promising spatial reasoning capabilities, while these abilities remain underexplored in the emerging visual modality of p…
ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
Chenhao Dang, Dantong Zhu, Jun Yang +2
Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and subtle cross-modal…
Optimality of Random Regular Graphs in Sparse Network Designs
Weijia Li, Xiaochun Niu, Yehua Wei +1
The problems of designing sparse networks arise frequently in resource allocation and operations research. In production systems, for example, sparse process flexibility designs ar…
Asymptotic Anytime-Valid Inference for U-statistics
Leheng Cai, Qirui Hu, Weijia Li
We study asymptotic anytime-valid confidence sequences for degree-two U-statistics under continuous monitoring. In the nondegenerate case, Hoeffding's projection reduces the proble…
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
Junlong Ke, Zichen Wen, Weijia Li +2
On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervi…
Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction
Jinxiao Zhang, Runmin Dong, Xiyong Wu +14
Earth observation is becoming one of the largest data-producing activities in science, yet current pipelines still treat compression as a storage and transmission tool rather than…
IPCV: Information-Preserving Compression for MLLM Visual Encoders
Yuan Chen, Zichen Wen, Yuzhou Wu +6
Multimodal Large Language Models (MLLMs) deliver strong vision-language performance but at high computational cost, driven by numerous visual tokens processed by the Vision Transfo…
OmniAID: Decoupling Semantics and Artifacts for Universal AI-Generated Image Detection in the Wild
Yuncheng Guo, Junyan Ye, Chenjue Zhang +4
A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, en…
AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
Peize He, Zichen Wen, Yubo Wang +13
Processing long-form audio is a major challenge for Large Audio Language models (LALMs). These models struggle with the quadratic cost of attention () and with modeling lon…
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Zichen Wen, Shaobo Wang, Yufa Zhou +8
Visual tokens consume substantial computational resources in multi-modal large models (MLLMs), significantly compromising their efficiency. Recent works have attempted to improve e…
The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
Zichen Wen, Jiashu Qu, Zhaorun Chen +13
Diffusion-based large language models (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs, offering faster inference and greater interactivity via parall…
GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
Zhiyuan Yan, Junyan Ye, Weijia Li +7
The recent breakthroughs in OpenAI's GPT4o model have demonstrated surprisingly good capabilities in image generation and editing, resulting in significant excitement in the commun…
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Xuyang Liu, Zichen Wen, Shaobo Wang +14
The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further mode…
Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration
Zilong Huang, Jun He, Junyan Ye +4
The reconstruction of immersive and realistic 3D scenes holds significant practical importance in various fields of computer vision and computer graphics. Typically, immersive and…
LEGION: Learning to Ground and Explain for Synthetic Image Detection
Hengrui Kang, Siwei Wen, Zichen Wen +8
The rapid advancements in generative technology have emerged as a double-edged sword. While offering powerful tools that enhance convenience, they also pose significant social conc…
Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning
Junyuan Gao, Jiahe Song, Jiang Wu +9
Evaluating the multilingual capabilities of Large Vision-Language Models (LVLMs) remains challenging because most benchmarks rely on non-parallel corpora, making it unclear whether…
Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
Siwei Wen, Junyan Ye, Peilin Feng +7
With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challe…
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
Zichen Wen, Yifeng Gao, Weijia Li +2
Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abu…
Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
Zichen Wen, Yifeng Gao, Shaobo Wang +5
Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods…
Where am I? Cross-View Geo-localization with Natural Language Descriptions
Junyan Ye, Honglin Lin, Leyan Ou +5
Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-t…
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
Junyan Ye, Baichuan Zhou, Zilong Huang +12
With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data in…