8 papers
V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
Haoxiang Sun, Zhihang Yi, Langxuan Deng +6
Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existin…
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
Jindi Lv, Hao Li, Jie Li +11
Vision-language-action (VLA) models have advanced robot manipulation through large-scale pretraining, but real-world deployment remains challenging due to partial observability and…
NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
Jian Lan, Zhicheng Liu, Xinpeng Wang +5
The ability to derive precise spatial and physical insights is a cornerstone of vision-language models (VLMs), yet their poor performances in related spatial intelligence tasks suc…
Multi-Path Collaborative Reasoning via Reinforcement Learning
Jindi Lv, Yuhao Zhou, Zheng Zhu +3
Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determini…
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Zekai Li, Xinhao Zhong, Samir Khaki +49
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…