22 papers
The Mechanistic Emergence of Symbol Grounding in Language Models
Shuyu Wu, Ziqiao Ma, Xiaoxi Luo +4
Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary e…
UniCanvas: A Diffusion-base Unified Model for Text-in-Image Joint Generation
Zeyuan Yang, Hao-Wei Chen, Xueyang Yu +5
Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single architecture. While autoregressiv…
Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues
Zory Zhang, Pinyuan Feng, Bingyang Wang +7
Where someone looks is a nonverbal communication cue that children and adults readily use. How well can Vision-Language Models (VLMs) infer gaze targets? To construct evaluation st…
Fast Spatial Memory with Elastic Test-Time Training
Ziqiao Ma, Xueyang Yu, Haoyu Zhen +3
Large Chunk Test-Time Training (LaCT) has shown strong performance on long-context 3D reconstruction, but its fully plastic inference-time updates remain vulnerable to catastrophic…
A Very Big Video Reasoning Suite
Maijunxian Wang, Ruisi Wang, Juyi Lin +53
Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally c…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1144
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…