11 papers
How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study
Zhen Yang, Ping Jian, Zhongbin Guo +5
Over the past year, spatial intelligence has drawn increasing attention. Many prior works study it from the perspective of visual-spatial intelligence, where models have access to…
Look, Listen and Segment: Towards Weakly Supervised Audio-visual Semantic Segmentation
Chengzhi Li, Heyan Huang, Ping Jian +1
Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic…
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
Yonghong Deng, Zhen Yang, Ping Jian +4
With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain v…
Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT
Jiacheng Wang, Ping Jian, Zhijie Liu +5
Large language models are commonly adapted to downstream tasks through supervised fine-tuning (SFT), but substantial distribution mismatch between downstream supervision and a mode…
Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions
Zhongbin Guo, Zhen Yang, Yushan Li +6
Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate f…
LISA-3D: Lifting Language-Image Segmentation to 3D via Multi-View Consistency
Zhongbin Guo, Jiahe Liu, Wenyu Gao +4
Text-driven 3D reconstruction requires masks that understand free-form instructions and remain stable under viewpoint changes. We present LISA-3D, a two-stage framework that adapts…
Beyond Flatlands: Unlocking Spatial Intelligence by Decoupling 3D Reasoning from Numerical Regression
Zhongbin Guo, Jiahe Liu, Yushan Li +5
Existing Vision Language Models (VLMs) architecturally rooted in "flatland" perception, fundamentally struggle to comprehend real-world 3D spatial intelligence. This failure stems…
Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
Chengzhi Li, Heyan Huang, Ping Jian +3
Large language models (LLMs) often generate self-contradictory outputs, which severely impacts their reliability and hinders their adoption in practical applications. In video-lang…
TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models
Zhongbin Guo, Yuhao Wang, Ping Jian +4
Temporal Change Description (TCD) and Future Satellite Image Forecasting (FSIF) are critical, yet historically disjointed tasks in Satellite Image Time Series (SITS) analysis. Both…
Thought-Path Contrastive Learning via Premise-Oriented Data Augmentation for Logical Reading Comprehension
Chenxu Wang, Ping Jian, Zhen Yang
Logical reading comprehension is a challenging task that entails grasping the underlying semantics of text and applying reasoning to deduce the correct answer. Prior researches hav…
Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition
Chenxu Wang, Ping Jian, Mu Huang
Implicit Discourse Relation Recognition (IDRR), which infers discourse relations without the help of explicit connectives, is still a crucial and challenging task for discourse par…