14 papers
ProAR: Learning Prospective Reasoning with Autoregressive Video Models
Linghui Shen, Tinghui Zhu, Sheng Zhang +1
Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is par…
Implicit Reasoning Steering via Concept Chaining
Xiao Ye, Sanika Chavan, Yuxi Huang +4
Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how f…
ASCII Art Turns LLMs into VLA Controllers
Yitao Jiang, Roy Xing, Luyang Zhao +3
Vision--Language--Action (VLA) controllers are often built by extending vision--language models (VLMs) with action supervision, relying on multimodal backbones with large data and…
FlowMo-WM: A World Model with Object Momentum and Hidden Ambient Drift
Yitao Jiang, Luyang Zhao, Muhao Chen +1
World models in robot learning predict future states from visual observations and actions, enabling agents to reason about the consequences of their controls. However, many action-…
VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images
Zhaonan Li, Kyle R. Chickering, Bangzheng Li +13
A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties…
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees
Yuankai Li, Tinghui Zhu, Ha Min Son +3
Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iterat…
Video Models Can Reason with Verifiable Rewards
Tinghui Zhu, Sheng Zhang, James Y. Huang +5
Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable re…
GQA-μP: The maximal parameterization update for grouped query attention
Kyle R. Chickering, Huijuan Wang, Mengxi Wu +7
Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The maximal update parameterization…
When Vision Speaks for Sound
Xiaofei Wen, Wenjie Jacky Mo, Xingyu Fu +6
Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual cues to infer or hallucinate…
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
Shahriar Kabir Nahin, Hadi Askari, Muhao Chen +1
The rapid growth of online video platforms and AI-generated content has made reliable video guardrails a key challenge for safety and real-world deployment. While most videos can b…
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
Yixu Huang, Tinghui Zhu, Muhao Chen
Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning. However, they often suffer fr…
Reinforced Attention Learning
Bangzheng Li, Jianmo Ni, Chen Qu +5
Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multi…
Unbiased Visual Reasoning with Controlled Visual Inputs
Zhaonan Li, Shijie Lu, Fei Wang +11
End-to-end Vision-language Models (VLMs) often answer visual questions by exploiting spurious correlations instead of causal visual evidence, and can become more shortcut-prone whe…
Latent Visual Reasoning
Bangzheng Li, Ximeng Sun, Jiang Liu +7
Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this…