5 papers
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang +15
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation (OPD), and sampling-heavy evalua…
GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler
Minghan Wang, Ye Bai, Thuy-Trang Vu +2
Inference-time scaling (ITS) in latent reasoning models typically relies on heuristic perturbations, such as dropout or fixed Gaussian noise, to generate diverse candidate trajecto…
Discrete Minds in a Continuous World: Do Language Models Know Time Passes?
Minghan Wang, Ye Bai, Thuy-Trang Vu +2
While Large Language Models (LLMs) excel at temporal reasoning tasks like event ordering and duration estimation, their ability to perceive the actual passage of time remains unexp…
MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning
Ye Bai, Minghan Wang, Thuy-Trang Vu
Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thoug…
SpeechDialogueFactory: Generating High-Quality Speech Dialogue Data to Accelerate Your Speech-LLM Development
Minghan Wang, Ye Bai, Yuxia Wang +3
High-quality speech dialogue datasets are crucial for Speech-LLM development, yet existing acquisition methods face significant limitations. Human recordings incur high costs and p…