9 papers
Learning What to Remember: Test-Time Training via Context Distillation
Zixuan Wang, Xingyu Dang, Rui-Jie Zhu +4
Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later. Test-time training (TTT) is an a…
EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments
Deyao Zhu, Xin Zhou, Shengling Qin +44
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less unders…
Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs
Zixin Wen, Yifu Cai, Kyle Lee +5
Visual design is an essential application of state-of-the-art multi-modal AI systems. Improving these systems requires high-quality vision-language data at scale. Despite the abund…
Learn Hard Problems During RL with Reference Guided Fine-tuning
Yangzhen Wu, Shanda Li, Zixin Wen +5
Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from r…
On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
Yu Huang, Zixin Wen, Yuejie Chi +4
Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mystery how rewards based solely on…
Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization
Yu Huang, Zixin Wen, Aarti Singh +2
The ability to reason lies at the core of artificial intelligence (AI), and challenging problems usually call for deeper and longer reasoning to tackle. A crucial question about AI…
Scaling Latent Reasoning via Looped Language Models
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training…
Faster WIND: Accelerating Iterative Best-of- Distillation for LLM Alignment
Tong Yang, Jincheng Mei, Hanjun Dai +5
Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-N distillation (BOND). However, the iterative BOND algo…
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
Yu Huang, Zixin Wen, Yuejie Chi +1
Self-supervised learning has become a cornerstone in computer vision, primarily divided into reconstruction-based methods like masked autoencoders (MAE) and discriminative methods…