33 citations · 69 across the 28 of their papers we have counts for
31 papers
GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation
Kaichen Zhang, Yuzhong Hong, Junwei Bao +4
Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent advances in post-training met…
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding
Keming Wu, Baoyi Wang, Kaichen Zhang +7
Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memory, retrieval, and compressi…
Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation
Yueting Zhu, Yuehao Song, Kaicheng Zhang +5
Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming…
Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation
Kaichen Zhang, Wei Huang, Keming Wu +2
Existing streaming multimodal models process observations incrementally but still follow a turn-based prefill-then-decode pattern, making them non-duplex: new observations cannot n…
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Senqiao Yang, Kaichen Zhang, Zhaoyang Jia +20
Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process…
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
Xinjie Zhang, Peng Zhang, Shicheng Zheng +21
Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack for efficient text-to…
OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents
Kaicheng Zhang, Wen Ge, Lei Jiang +5
Although large language model agents are increasingly applied to quantitative-finance workflows, their evaluation remains fragmented across isolated tasks, while the financial rele…
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
Xiang An, Yin Xie, Feilong Tang +27
We introduce LLaVA-OneVision-2 (LLaVA-OV-2), the most capable vision-language model in the LLaVA-OneVision series to date, achieving superior performance across a broad range of mu…
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Zuhao Yang, Kaichen Zhang, Sudong Wang +7
Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promising route to long-video unders…
EponaV2: Driving World Model with Comprehensive Future Reasoning
Jiawei Xu, Zhizhou Zhong, Zhijian Shu +8
Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive man…
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
Trung Nguyen Quang, Yiming Gao, Fanyi Pu +3
When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Kaichen Zhang, Keming Wu, Zuhao Yang +6
Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoni…
DINO-RotateMatch: A Rotation-Aware Deep Framework for Robust Image Matching in Large-Scale 3D Reconstruction
Kaichen Zhang, Tianxiang Sheng, Xuanming Shi
This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet im…
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Zuhao Yang, Sudong Wang, Kaichen Zhang +8
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when proc…
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Tiancheng Gu, Kaicheng Yang, Kaichen Zhang +6
Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidat…
RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models
Kaichen Zhang, Shenghao Gao, Yuzhong Hong +6
Current large language model post-training optimizes a risk-neutral objective that maximizes expected reward, yet evaluation relies heavily on risk-seeking metrics like Pass@k (at…
Generalized Linear Markov Decision Process
Sinian Zhang, Kaicheng Zhang, Ziping Xu +4
Offline reinforcement learning for longitudinal studies often faces two linked challenges: rewards may be binary or bounded, and reward observations may be available only for a sub…
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang +7
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing ben…
Wasserstein Transfer Learning
Kaicheng Zhang, Sinian Zhang, Doudou Zhou +1
Transfer learning is a powerful paradigm for leveraging knowledge from source domains to enhance learning in a target domain. However, traditional transfer learning approaches ofte…
GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
Kaichen Zhang, Yuzhong Hong, Junwei Bao +4
Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training technique…
Rethinking the Vulnerability of Concept Erasure and a New Method
Alex D. Richardson, Kaicheng Zhang, Lucas Beerens +1
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In…
Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
Kaichen Zhang, Yifei Shen, Bo Li +1
Recent advances in Large Multimodal Models (LMMs) lead to significant breakthroughs in both academia and industry. One question that arises is how we, as humans, can understand the…
MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures
Jinjie Ni, Yifan Song, Deepanway Ghosal +10
Perceiving and generating diverse modalities are crucial for AI models to effectively learn from and engage with real-world signals, necessitating reliable evaluations for their de…