activity
20242026
collaborators

7 papers

cs.LG2026

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior

Zeyi Huang, Xuehai He, LiLiang Ren +8

We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden state from the previous token as…

cs.LG2025

ThetaEvolve: Test-time Learning on Open Problems

Yiping Wang, Shao-Rong Su, Zhiyuan Zeng +13

Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to im…

cs.LG2025

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Yiping Wang, Qing Yang, Zhiyuan Zeng +11

We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language…

cs.AI2025

Bridging the Gap Between Multimodal Foundation Models and World Models

Xuehai He

Humans understand the world through the integration of multiple sensory modalities, enabling them to perceive, reason about, and imagine dynamic physical processes. Inspired by thi…

cs.CL2025

ViQA-COVID: COVID-19 Machine Reading Comprehension Dataset for Vietnamese

Hai-Chung Nguyen-Phung, Ngoc C. Lê, Van-Chien Nguyen +2

After two years of appearance, COVID-19 has negatively affected people and normal life around the world. As in May 2022, there are more than 522 million cases and six million death…

cs.CL2025

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

Zhen Zhang, Xuehai He, Weixiang Yan +5

Human cognition typically involves thinking through abstract, fluid concepts rather than strictly using discrete linguistic tokens. Current reasoning models, however, are constrain…