15 papers
GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation
Yuqing Jiang, Zijian Zhang, Weitao Zhou +8
Vision-Language-Action (VLA) policies have advanced language-conditioned robotic manipulation, yet action-imitation objectives provide only weak supervision for metric 3D structure…
GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models
Zijian Zhang, Yuqing Jiang, Weitao Zhou +6
World-Action Models (WAMs) jointly learn future visual prediction and action generation, using video dynamics as a representation-learning signal for robotic manipulation. However,…
Rosetta: Composable Native Multimodal Pretraining
Xiangyue Liu, Zijian Zhang, Miles Yang +3
Achieving true artificial general intelligence requires foundation models capable of integrating new modalities without forgetting prior knowledge. However, accommodating continuou…
OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning
Wenxuan Jiang, Zining Fan, Zijian Zhang +6
Reinforcement Learning (RL) has enabled LLMs to excel in objective reasoning tasks such as mathematics and code generation. However, applying RL to open-ended tasks, such as creati…
GaussianDream: A Feed-Forward 3D Gaussian World Model for Robotic Manipulation
Zijian Zhang, Yuqing Jiang, Qian Cheng +6
Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action gener…
QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding
Shuxiang Cao, Zijian Zhang, Abhishek Agarwal +29
Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no system…
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
Yuanjie Shi, Peihong Li, Zijian Zhang +2
Most methods for learning with noisy labels require privileged knowledge such as noise transition matrices, clean subsets or pretrained feature extractors, resources typically unav…
Symbiotic-MoE: Unlocking the Synergy between Generation and Understanding
Xiangyue Liu, Zijian Zhang, Miles Yang +3
Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts. While existing parad…
TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning
Wenxuan Jiang, Yuxin Zuo, Zijian Zhang +8
In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge…
: Unified Chain of Perception-Prediction-Planning Thought via Reinforcement Fine-Tuning
Yuqi Ye, Zijian Zhang, Junhong Lin +3
Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However…
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Meituan LongCat Team, Bin Xiao, Chao Wang +86
The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…
UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Yaqi Zhao, Wang Lin, Zijian Zhang +5
Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic informa…
HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs
Zijian Zhang, Xuecheng Wu, Danlei Huang +3
Driven by the rapid progress in vision-language models (VLMs), the responsible behavior of large-scale multimodal models has become a prominent research area, particularly focusing…
NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
Shuhao Han, Haotian Fan, Fangyuan Kong +112
This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoratio…
TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs
Zijian Zhang, Xuhui Zheng, Xuecheng Wu +2
While text-to-image (T2I) generation models have achieved remarkable progress in recent years, existing evaluation methodologies for vision-language alignment still struggle with t…