12 papers
Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Masking
Dongzhou Cheng, Ziang Li, Yixiao Zhou +6
Query-based Vision-Language-Action (VLA) models offer low-latency inference that is attractive for bimanual robotic manipulation, but we observe that they can still exhibit discont…
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Penghui Yang, Long Xing, Xiaoyi Dong +10
Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Curren…
Harnessing Streaming Video in the Wild
Dingyu Yao, Shuhuan Gu, Qingyi Si +8
Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentary, and embodied robots. An i…
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
Jiahao Wang, An Ping, Yanghai Wang +13
While Omni-modal Large Language Models (OLLMs) have demonstrated impressive capabilities in jointly processing audio and visual streams, their ability to strictly adhere to complex…
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO
Jiazi Bu, Pengyang Ling, Yujie Zhou +8
Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences. However, we have identified that t…
LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
Feng Han, Zhixiong Zhang, Zheming Liang +2
Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multim…
UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing
Dianyi Wang, Chaofan Ma, Feng Han +8
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabil…
Unified Personalized Reward Model for Vision Generation
Yibin Wang, Yuhang Zang, Feng Han +4
Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style pre…
EtCon: Edit-then-Consolidate for Reliable Knowledge Editing
Ruilin Li, Yibin Wang, Wenhong Zhu +5
Knowledge editing aims to update specific facts in large language models (LLMs) without full retraining. Prior efforts sought to tune the knowledge layers of LLMs, achieving improv…
UniREditBench: A Unified Reasoning-based Image Editing Benchmark
Feng Han, Yibin Wang, Chenglin Li +7
Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and…
RLFR: Extending Reinforcement Learning for LLMs with Flow Environment
Jinghao Zhang, Naishan Zheng, Ruilin Li +4
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, poli…
UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
Yibin Wang, Zhimin Li, Yuhang Zang +8
Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their tex…