5 citations · 6 across the 30 of their papers we have counts for
34 papers
LLM Agents for Automated Post-Training via Structured Recipe Optimization
Ruohong Liu, Bohan Tang, Lekang Jiang +2
Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a recipe of…
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
Alan Wu, Wei Tao, Yiwen Guo
Large language model agents are emerging as an important new class of users of desktop applications. However, existing desktop interfaces were designed for human end users or appli…
Real-Time Joint Audio-Video Generation by Parallel Adapter Composition
Jingyu Li, Xiaoxiao Xiang, Yiwen Guo
Deploying a joint audio-video diffusion transformer for real-time, interactive generation normally requires two essential modifications: block-autoregressive attention, so frames c…
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Weixian Waylon Li, Jiaxin Zhang, Han Zhou +4
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipel…
GameWAM: A World Action Model for Video Games
Yuncheng Guo, Zhanqiu Zhang, Yiwen Guo +1
Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task contex…
Progressive Agent Skill Generation via Reinforcement Learning
Junhao Shen, Zhanqiu Zhang, Chengzhi Piao +2
Recent large language model agents often use external skills as modular procedural units that condition inference and improve complex task solving. Thus, automatically generating h…
CONDUIT: A Unified Residual-Stream Restoration Framework for KV Cache Reuse in Vision-Language Models
Pengan Chen, Kaisheng Zheng, Liang Hong +10
Vision-language models (VLMs) often answer new questions about recurring visual content, where reusing the key-value (KV) cache can avoid re-encoding expensive visual prefixes. Exa…
Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence
Haoyu Zhang, Zhipeng Li, Xiaoying Tang +2
Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, but a spoken answer still leaves the agent visually absent. We introduce \textbf{Ex-Omni-…
MemDefrag: Latent Memory Defragmentation for Large Language Models
Ruiyi Yan, Zhuoyuan Mao, Yiwen Guo
Latent memory, which stores past knowledge fragments as per-layer hidden states, has emerged as a promising paradigm (e.g., MemoryLLM and M+) for long-term memory in large language…
Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue
Chengqian Ma, Wei Tao, Haoyu Zhang +1
An avatar that holds a conversation should decide what to say and to move while saying it, yet these abilities live in separate model families: spoken dialogue models produce speec…
Preference Optimization for Non-Verbal Vocalization Synthesis
Haoyang Li, Chenglin Xu, Junchuan Zhao +4
Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive TTS, but the effectiveness of preference optimization for NV generation remains po…
EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis
Tianchi Liu, Zeyang Song, Tianrui Wang +3
Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotion…
ADIAS: Automated Design of Interactive Agentic Systems
Lekang Jiang, Bohan Tang, Stephan Goetz +1
Self-evolving agents can improve without updating model weights by iteratively optimizing the harness based on evaluation feedback. Existing methods are largely candidate-centric:…
MemoryForge: Synthesize Lifelong Memory for Human-Like LLM Agents
Bohan Tang, Yiwen Guo
Equipping Large Language Models (LLMs) with human-like personas is crucial for agentic applications, such as role-play and user simulation. Traditional prompt-based methods rely on…
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World
Qing Zong, Yue Guo, Mengxin Yang +2
This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive litera…
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling
Dazhi Fu, Jiuding Yang, Yiwen Guo +1
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompos…
One-Step Token-to-Waveform Generation with MeanFlow in Latent Space
Zheqi Dai, Guangyan Zhang, Zhen Ye +5
Neural audio codecs are central to modern LLM-based Text-to-Speech (TTS) and multimodal systems. As low-bitrate semantic codecs gain prominence, the Token-to-Waveform (Token2Wav) d…
Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output
Guozheng Li, Xiyan Fu, Yiwen Guo
Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM). While effective, scalar rewards are often noisy…
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Yucheng Zhou, Wei Tao, Yiwen Guo +1
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can genera…
UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment
Yuanyuan Wang, Dongchao Yang, Yayue Deng +4
Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While…
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Weixian Waylon Li, Jiaxin Zhang, Xianan Jim Yang +2
Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete m…
Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
Xingwu Chen, Zhanqiu Zhang, Yiwen Guo +1
While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in multi-turn interactions. Specif…
Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
Haoyu Zhang, Zhipeng Li, Yiwen Guo +1
Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet extending them to jointly produce speech and 3D facial animation remains largely…
SemanticAudio: Audio Generation and Editing in Semantic Space
Zheqi Dai, Guangyan Zhang, Haolin He +5
In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, exis…