3 citations · 12 across the 33 of their papers we have counts for
40 papers
Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering
Dongxing Mao, Jinpeng Wang, Jiahao Tang +6
Visual Autoregressive (AR) models generate images by predicting discrete tokens that are decoded by a visual tokenizer. Despite demonstrating strong overall image generation abilit…
RAGEN-2: Reasoning Collapse in Agentic RL
Zihan Wang, Chi Gui, Xing Jin +13
RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. Howeve…
FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
Junchao Yi, Rui Zhao, Jiahao Tang +7
Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking wh…
Glance: Accelerating Diffusion Models with 1 Sample
Zhuobai Dong, Rui Zhao, Songjie Wu +5
Diffusion models have achieved remarkable success in image generation, yet their deployment remains constrained by the heavy computational cost and the need for numerous inference…
Computer-Use Agents as Judges for Generative User Interface
Kevin Qinghong Lin, Siyuan Hu, Linjie Li +4
Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed pr…
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang, Pingyue Zhang, Zihan Wang +13
A key challenge in training Vision-Language Model (VLM) agents, compared to Language Model (LLM) agents, lies in the shift from textual states to complex visual observations. This…
EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
Tianyu Chen, Yasi Zhang, Zhi Zhang +13
Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images…
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?
Yiyang Zhou, Linjie Li, Shi Qiu +10
Existing video benchmarks often resemble image-based benchmarks, with question types like "What actions does the person perform throughout the video?" or "What color is the woman's…
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models
Cheng-Han Chiang, Xiaofei Wang, Linjie Li +7
Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking proc…
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Xiyao Wang, Zhengyuan Yang, Chao Feng +10
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasonin…
What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
Ming Li, Zhengyuan Yang, Xiyao Wang +4
Large reasoning models (LRMs) achieve strong reasoning performance by emitting long chains of thought. Yet, these verbose traces slow down inference and often drift into unnecessar…
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
Xiyao Wang, Zhengyuan Yang, Chao Feng +6
We introduce ThinkLite-VL, a family of visual reasoning models that achieve state-of-the-art (SoTA) performance using an order of magnitude fewer training samples, relying purely o…
Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
Minheng Ni, Zhengyuan Yang, Linjie Li +4
Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, exte…
Measurement of LLM's Philosophies of Human Nature
Minheng Ni, Ennan Wu, Zidong Gong +6
The widespread application of artificial intelligence (AI) in various tasks, along with frequent reports of conflicts or violations involving AI, has sparked societal concerns abou…
V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models
Xiangxi Zheng, Linjie Li, Zhengyuan Yang +5
Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual-text processing. However, existing static image-text benchmarks…
Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising
Yan-Bo Lin, Kevin Lin, Zhengyuan Yang +6
In this paper, we introduce zero-shot audio-video editing, a novel task that requires transforming original audio-visual content to align with a specified textual prompt without ad…
Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
Alex Jinpeng Wang, Linjie Li, Zhengyuan Yang +2
Recent advancements in autoregressive and diffusion models have led to strong performance in image generation with short scene text words. However, generating coherent, long-form t…
ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
Jiaqi Liao, Zhengyuan Yang, Linjie Li +4
In this work, we study the problem of Text-to-Image In-Context Learning (T2I-ICL). While Unified Multimodal LLMs (MLLMs) have advanced rapidly in recent years, they struggle with c…
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
Yunzhuo Hao, Jiawei Gu, Huichen Will Wang +4
The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such…
Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension
Xiyao Wang, Zhengyuan Yang, Linjie Li +6
Despite significant advancements in vision-language models (VLMs), there lacks effective approaches to enhance response quality by scaling inference-time computation. This capabili…
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Kevin Qinghong Lin, Linjie Li, Difei Gao +6
Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-sour…
LiVOS: Light Video Object Segmentation with Gated Linear Matching
Qin Liu, Jianfeng Wang, Zhengyuan Yang +4
Semi-supervised video object segmentation (VOS) has been largely driven by space-time memory (STM) networks, which store past frame features in a spatiotemporal memory to segment t…
GenXD: Generating Any 3D and 4D Scenes
Yuyang Zhao, Chung-Ching Lin, Kevin Lin +6
Recent developments in 2D visual generation have been remarkably successful. However, 3D and 4D generation remain challenging in real-world applications due to the lack of large-sc…
SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Yining Hong, Beide Liu, Maxine Wu +9
Human beings are endowed with a complementary learning system, which bridges the slow learning of general world dynamics with fast storage of episodic memory from a new experience.…