13 papers
MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement
Daiqing Wu, Dongbao Yang, Jiashu Yao +4
Affective Image Content Analysis (AICA) aims to recognize and understand emotions elicited by visual content, representing an indispensable step toward Artificial General Intellige…
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Yingyu Shan, Yuhang Guo, Zihao Cheng +7
Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform c…
PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
Yingyu Shan, Zeming Liu, Silin Li +4
Recent advancements in Large Language Models (LLMs) have empowered home assistants with natural language interaction capabilities. However, current assistants overlook the progress…
Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms
Jiashu Yao, Heyan Huang, Daiqing Wu +5
GUI agents today assume a static screen, where the world is frozen between two actions. However, real interfaces such as short-video applications violate this assumption, as their…
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
Jiashu Yao, Heyan Huang, Daiqing Wu +2
To encourage diverse exploration in reinforcement learning (RL) for large language models (LLMs) without compromising accuracy, we propose Policy Split, a novel paradigm that bifur…
Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
Jiashu Yao, Heyan Huang, Zeming Liu +1
To overcome the sparse reward challenge in reinforcement learning (RL) for agents based on large language models (LLMs), we propose Mutual Information Self-Evaluation (MISE), an RL…