5 papers
Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
Senjie Jin, Peixin Wang, Boyang Liu +8
While token-level entropy is commonly recognized as effective for credit assignment in text-only reinforcement learning with verifiable rewards (RLVR), it remains unclear whether t…
Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild
Derek Ming Siang Tan, Shailesh, Boyang Liu +8
To perform outdoor visual navigation and search, a robot may leverage satellite imagery to generate visual priors. This can help inform high-level search strategies, even when such…
Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization
Boyang Liu, Yifan Hu, Senjie Jin +5
Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding…
Reconstructing Satellites in 3D from Amateur Telescope Images
Zhiming Chang, Boyang Liu, Yifei Xia +3
Monitoring space objects is crucial for space situational awareness, yet reconstructing 3D satellite models from ground-based telescope images is challenging due to atmospheric tur…
EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection
Yuhao Zhou, Sirui Song, Boyang Liu +6
Rotary Position Embedding (RoPE) enables each attention head to capture multi-frequency information along the sequence dimension and is widely applied in foundation models. However…