3 citations · 6 across the 9 of their papers we have counts for
11 papers
World Action Modeling with Progressive Visual Planning
Fei Zhang, Zhaochong An, Duncan Frost +5
World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruc…
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
Yuhan Chen, Ke Yu, Pengfei Liu +3
Flow-based vision-language-action (VLA) models are highly effective for generalist robot manipulation, yet their reliance on computationally expensive VLM encoding and multi-step i…
VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes
Yan Ma, Jiadi Su, Zhulin Hu +4
Video foundation models increasingly rely on large-scale pretraining data, yet the end-to-end data pipelines behind them remain largely closed and difficult to inspect or reuse. Re…
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Ethan Chern, Zhulin Hu, Bohao Tang +4
Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems. However, the simultaneous denoising of all video frames with b…
Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Yi Yang, Xueqi Li, Yiyang Chen +7
Recent advances in Vision-Language-Action (VLA) models demonstrate that visual signals can effectively complement sparse action supervisions. However, letting VLA directly predict…
Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
Bohao Tang, Yan Ma, Fei Zhang +6
Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools…
Thinking with Generated Images
Ethan Chern, Zhulin Hu, Steffi Chern +5
We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to native…
LIMO: Less is More for Reasoning
Yixin Ye, Zhen Huang, Yang Xiao +3
We challenge the prevailing assumption that complex reasoning in large language models (LLMs) necessitates massive training data. We demonstrate that sophisticated mathematical rea…
Halu-J: Critique-Based Hallucination Judge
Binjie Wang, Steffi Chern, Ethan Chern +1
Large language models (LLMs) frequently generate non-factual content, known as hallucinations. Existing retrieval-augmented-based hallucination detection approaches typically addre…
ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
Ethan Chern, Jiadi Su, Yan Ma +1
Previous open-source large multimodal models (LMMs) have faced several limitations: (1) they often lack native integration, requiring adapters to align visual representations with…
BeHonest: Benchmarking Honesty in Large Language Models
Steffi Chern, Zhulin Hu, Yuqing Yang +5
Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has recei…