5 papers
Internalizing LLM Reasoning via Discovery and Replay of Latent Actions
Zhenning Shi, Yijia Zhu, Junhan Shi +3
The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering…
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
Ziwei Luo, Ziqi Jin, Lei Wang +2
This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling algorithm enabling effective sampling of masked diffusion language models (MDLMs). Our alg…
MagicView: Multi-View Consistent Identity Customization via Priors-Guided In-Context Learning
Hengjia Li, Jianjin Xu, Keli Cheng +5
Recent advances in personalized generative models have demonstrated impressive capabilities in producing identity-consistent images of the same individual across diverse scenes. Ho…
FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation
Fatema Siddika, Md Anwar Hossen, J. Pablo Muñoz +3
Parameter-efficient fine-tuning (PEFT) adapts large pre-trained models by updating only a small subset of parameters. Recently, Representation Fine-Tuning (ReFT) has emerged as an…
Talking-to-Build: How LLM-Assisted Interface Shapes Player Performance and Experience in Minecraft
Xin Sun, Lei Wang, Yue Li +5
With large language models (LLMs) on the rise, in-game interactions are shifting from rigid commands to natural conversations. However, the impacts of LLMs on player performance an…