6 papers
Demystifying Video Reasoning
Ruisi Wang, Zhongang Cai, Fanyi Pu +11
Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a…
Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation
Chao Hao, Jun Xu, Ji Du +6
Language-guided segmentation transcends the scope limitations of traditional semantic segmentation, enabling models to segment arbitrary target regions based on natural language in…
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Haiwen Diao, Penghao Wu, Hanming Deng +55
Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fra…
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Haoyu Wang, Yifan Shang, Zhongxiang Sun +3
Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have be…
From Clicks to Preference: A Multi-stage Alignment Framework for Generative Query Suggestion in Conversational System
Junhao Yin, Haolin Wang, Peng Bao +2
Generative query suggestion using large language models offers a powerful way to enhance conversational systems, but aligning outputs with nuanced user preferences remains a critic…
ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
Jingwei Yi, Junhao Yin, Ju Xu +4
Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG)…