7 papers
UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling
Chuanbo Zhu, Wuyou Zhou, Rongxiu Zhong +4
Speech editing aims to modify specific portions of an utterance while preserving the remaining speech. Existing approaches primarily focus on word-level content modification and ty…
3D Primitives are a Spatial Language for VLMs
Junze Liu, Kun Qian, Florian Dubost +8
Vision-language models (VLMs) exhibit a striking paradox: they can generate executable code that reconstructs a 3D scene from geometric primitives with correct object counts, class…
LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
Jiacheng Lin, Kun Qian, Arvind Srinivasan +15
Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete pi…
SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing
Jianyi Chen, Rongxiu Zhong, Shilei Zhang +4
Composing coherent long-form music remains a significant challenge due to the complexity of modeling long-range dependencies and the prohibitive memory and computational requiremen…
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs
Jiacheng Lin, Zhongruo Wang, Kun Qian +14
Supervised Fine-Tuning (SFT) on domain-specific datasets is a common approach to adapt Large Language Models (LLMs) to specialized tasks but is often believed to degrade their gene…
Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
Yimeng Zhang, Tian Wang, Jiri Gesi +14
Large Language Models (LLMs) have recently demonstrated strong potential in generating 'believable human-like' behavior in web environments. Prior work has explored augmenting trai…
Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning
Jiacheng Lin, Tian Wang, Kun Qian
We propose Rec-R1, a general reinforcement learning framework that bridges large language models (LLMs) with recommendation systems through closed-loop optimization. Unlike prompti…