12 papers
HaPRL: Human-Anchored Process Reinforcement Learning for Visual Search Agent
Zhangquan Chen, Yaoxin Niu, Xiang An +5
Multi-turn visual search agents answer questions about high-resolution images by iteratively deciding where to look. Reinforcement learning for these agents rewards only the final…
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception
Yaoxin Niu, Zhangquan Chen, Yang Zhang +5
Fine-grained visual perception enables vision-language models to distinguish subtle attributes and ground their answers in visual evidence. In high-resolution scenes, processing th…
Adaptive Hierarchical Representation Alliance for Multimodal Learning
Chunlei Meng, Pengbin Feng, Jacqueline J. Pang +5
Multimodal models often align language, vision, and audio in a single final-layer latent space, implicitly assuming that task-relevant evidence emerges at the same semantic depth a…
The Objective Decides: When a Learned Dynamics Model Uses a Conserved Quantity
Chih-Ting Liao, Xin Cao
A linear probe that recovers a conserved quantity from a learned dynamics model's activations is routinely read as evidence that the model uses that quantity. We show this inferenc…
Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History
Chih-Ting Liao, Xin Cao
A frozen vision-language-action model (VLA) receives recent observations at every decision step, yet prior work has focused on adding memory rather than asking how existing history…
Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources
Chih-Ting Liao, Xin Cao
Vision-language models (VLMs) increasingly read news and web content as images, where the publisher's identity is visually present. We show that VLMs carry a strong source-credibil…
Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning
Chih-Ting Liao, Fei Shen, Xin Cao +1
The standard way to read latent knowledge out of a model, a linear probe confirmed by a steering recovery, can systematically overstate what a vision-language model (VLM) actually…
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
Xi Xiao, Chen Liu, Chih-Ting Liao +9
Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. Despite inheriting strong reason…
SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments
Chih-Ting Liao, Xi Xiao, Chunlei Meng +6
Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where b…
Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning
Zhikai Pan, Chih-Ting Liao, Chunrui Liu +5
Whether large language models (LLMs) construct internal spatial world models from pure-text descriptions remains contested, and whether such capabilities transfer across languages…
Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving
Dapeng Zhang, Zhenlong Yuan, Zhangquan Chen +5
Vision-Language-Action (VLA) models have recently shown strong decision-making capabilities in autonomous driving. However, existing VLAs often struggle with achieving efficient in…
Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration
Chih-Ting Liao, Zhangquan Chen, Chunlei Meng +3
Recent unified multi-modal encoders align a wide range of modalities into a shared representation space, enabling diverse cross-modal tasks. Despite their impressive capabilities,…