14 papers
LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models
Zeyu Xu, Xingzhong Hou, Pengkai Guo +6
Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding. However, scaling dense or sparse Mixture-of-Experts (MoE) models to improve performance lim…
IACM-RL: Intent-Aware Context Management and Reinforcement Learning for Complex Tool Invocation under Dynamic Intent Fluctuations
Dingwei Zhu, Jiahan Li, Chengjun Pan +22
Executing long-horizon tool invocations in real-world environments is severely challenged by dynamic user intent noise. Existing methods attempt robustness via implicit history sca…
AMR: Adaptive Modality Routing for Multimodal Polyglot Speaker Identification
Chuxiao Zuo, Yao Zhu, Minqiang Xu +3
Multimodal speaker identification systems face two key challenges in real-world deployment: missing modalities and language mismatch between training and testing conditions. In pra…
Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control
Jiazheng Zhang, Ziche Fu, Junrui Shen +17
Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existi…
MagicAgent: Towards Generalized Agent Planning
Xuhui Ren, Shaokang Dong, Chen Yang +21
The evolution of Large Language Models (LLMs) from passive text processors to autonomous agents has established planning as a core component of modern intelligence. However, achiev…
Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
Qiannian Zhao, Chen Yang, Jinhao Jing +5
Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks. In practice, these models are predominantly trained via Reinforcement Learni…
DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
Dingwei Zhu, Zhiheng Xi, Shihan Dou +17
Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM…
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
Dingwei Zhu, Zhiheng Xi, Shihan Dou +15
Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex a…
From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling
Yifei Cao, Changhao Jiang, Jiabao Zhuang +11
Assessing the perceptual quality of synthetic speech is crucial for guiding the development and refinement of speech generation models. However, it has traditionally relied on huma…
MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning
Liujian Tang, Shaokang Dong, Yijia Huang +21
This paper presents MagicGUI, a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environme…
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
Daiye Miao, Yufang Liu, Jie Wang +6
LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often in…
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
Dingwei Zhu, Shihan Dou, Zhiheng Xi +16
Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stability and generalization. Such noi…
What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
Xiaoran Fan, Zhichao Sun, Yangfan Gao +19
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal ali…
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition
Yuming Yang, Wantong Zhao, Caishuang Huang +11
Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent stu…