4 citations · 4 across the 16 of their papers we have counts for
20 papers
No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation
Jingang Zhou, Feiyu Han, Han Zhu +6
Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced by on-policy distillation (OPD…
Marathoner: Ultra-Long-Horizon Autonomous Intelligence
Zhang Ruiyang, Ou Jinpeng, Xie Yifan +4
Humans naturally possess the ability to work persistently toward long-term goals. Given a challenging task, humans can continuously work for months or even years to accomplish a sp…
Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation
Jingang Zhou, Yuyi Zhou, Haiyang Guo +6
On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supervision along its own genera…
TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems
Shunwen Bai, Ziping Ma, Chaoyang Zhang +4
The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning paths and all…
Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models
Ruihan Xu, Yuting Gao, Lan Wang +5
Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference…
FlattenGPT: Depth Compression for Transformer with Layer Flattening
Ruihan Xu, Qingpei Guo, Yao Zhu +3
Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pr…
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Inclusion AI, :, Bowen Ma +73
We propose Ming-Flash-Omni, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100 billion total parameters, of which on…
From Mapping to Composing: A Two-Stage Framework for Zero-shot Composed Image Retrieval
Yabing Wang, Zhuotao Tian, Qingpei Guo +4
Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of…
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Muzhi Zhu, Yuzhuo Tian, Hao Chen +5
While MLLMs have demonstrated adequate image understanding capabilities, they still struggle with pixel-level comprehension, limiting their practical applications. Current evaluati…
M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance
Qingpei Guo, Kaiyou Song, Zipeng Feng +9
We present M2-omni, a cutting-edge, open-source omni-MLLM that achieves competitive performance to GPT-4o. M2-omni employs a unified multimodal sequence modeling framework, which e…
Referencing Where to Focus: Improving VisualGrounding with Referential Query
Yabing Wang, Zhuotao Tian, Qingpei Guo +4
Visual Grounding aims to localize the referring object in an image given a natural language expression. Recent advancements in DETR-based visual grounding methods have attracted co…
LoTLIP: Improving Language-Image Pre-training for Long Text Understanding
Wei Wu, Kecheng Zheng, Shuailei Ma +7
Understanding long text is of great demands in practice but beyond the reach of most language-image pre-training (LIP) models. In this work, we empirically confirm that the key rea…
DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding
Yudong Han, Qingpei Guo, Liyuan Pan +3
The challenge in LLM-based video understanding lies in preserving visual and semantic information in long videos while maintaining a memory-affordable token count. However, redunda…
Social Debiasing for Fair Multi-modal LLMs
Harry Cheng, Yangyang Guo, Qingpei Guo +4
Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities. However, these models oft…
SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval
Xuzheng Yu, Chen Jiang, Xingning Dong +3
The user base of short video apps has experienced unprecedented growth in recent years, resulting in a significant demand for video content analysis. In particular, text-video retr…
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining
Qingpei Guo, Furong Xu, Hanxiao Zhang +6
Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and…
M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval
Xingning Dong, Zipeng Feng, Chunluan Zhou +3
We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP. Upon popular image-text…
SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment
Ziping Ma, Furong Xu, Jian Liu +2
Multimodal alignment between language and vision is the fundamental topic in current vision-language model research. Contrastive Captioners (CoCa), as a representative method, inte…
Text as Image: Learning Transferable Adapter for Multi-Label Classification
Xuelin Zhu, Jiuxin Cao, Jian liu +7
Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-la…
Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs
Shiyu Xuan, Qingpei Guo, Ming Yang +1
Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks…