collaborators

10 papers

cs.MA2025

Simulation-Free PSRO: Removing Game Simulation from Policy Space Response Oracles

Yingzhuo Liu, Shuodi Liu, Weijun Luo +2

Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, th…

cs.LG2025

Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders

Qingsen Ma, Dianyun Wang, Jiaming Lyu +8

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose…

cs.CV2025

Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis

Qingsen Ma, Chen Zou, Dianyun Wang +3

Under extremely low-light conditions, novel view synthesis (NVS) faces severe degradation in terms of geometry, color consistency, and radiometric stability. Standard 3D Gaussian S…

cs.CL2025

Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models

Shuodi Liu, Yingzhuo Liu, Zi Wang +4

Large language models (LLMs) have demonstrated remarkable reasoning and planning capabilities, driving extensive research into task decomposition. Existing task decomposition metho…

cs.AI2025

GUI Knowledge Bench: Revealing the Knowledge Gap of VLMs in GUI Tasks

Chenrui Shi, Zedong Yu, Zhi Gao +7

Vision language models (VLMs) have advanced graphical user interface (GUI) task automation but still lag behind humans. We hypothesize this gap stems from missing core GUI knowledg…

cs.AI2025

OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing

Fuqing Bie, Shiyu Huang, Xijia Tao +6

While generalist foundation models like Gemini and GPT-4o demonstrate impressive multi-modal competence, existing evaluations fail to test their intelligence in dynamic, interactiv…