11 papers
Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
Hengyu Shi, Tianyang Han, Peizhe Wang +3
LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to f…
Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards
Tianyang Han, Hengyu Shi, Junjie Hu +3
Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal wh…
Replacement Learning: Training Neural Networks with Fewer Parameters
Yuming Zhang, Peizhe Wang, Tianyang Han +5
End-to-end training with full-depth backpropagation remains the dominant paradigm for optimizing deep neural networks, but its efficiency deteriorates as models grow deeper. Since…
Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions
Junhao Su, Yuanliang Wan, Junwei Yang +4
Tool-augmented large language models (LLMs) are usually trained with supervised imitation or coarse-grained reinforcement learning that optimizes single tool calls. Current self-re…
MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
Junhao Su, Feiyu Zhu, Hengyu Shi +5
Deep learning typically relies on end-to-end backpropagation for training, a method that inherently suffers from issues such as update locking during parameter optimization, high G…
PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
Jianyu Lai, Sixiang Chen, Jialin Gao +7
Recent advancements in the text-rendering capabilities of image generation models have made the end-to-end creation of graphic design content, such as posters, increasingly feasibl…