5 citations · 5 across the 15 of their papers we have counts for
16 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…
FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection
Kaixiang Zhao, Tianrun Yu, Aoxu Zhang +3
The proliferation of sophisticated image editing tools and generative artificial intelligence models has made verifying the authenticity of digital images increasingly challenging,…
Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models
Tianyang Han, Junhao Su, Junjie Hu +4
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowle…
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…
LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation
Hengyu Shi, Junhao Su, Tianyang Han +2
Conditional layout generation aims to automatically generate visually appealing and semantically coherent layouts from user-defined constraints. While recent methods based on gener…
Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning
Xiuyuan Guo, Chengqi Xu, Guinan Guo +6
Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and s…
Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters
Yuming Zhang, Peizhe Wang, Shouxin Zhang +3
Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. Howe…
Momentum Auxiliary Network for Supervised Local Learning
Junhao Su, Changpeng Cai, Feiyu Zhu +4
Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network p…
HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
Junhao Su, Chenghao He, Feiyu Zhu +3
Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural n…
GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detection
Yuming Zhang, Dongzhi Guan, Shouxin Zhang +3
Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of arti…
MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network
Yuming Zhang, Shouxin Zhang, Peizhe Wang +5
Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and diffi…
Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
Feiyu Zhu, Yuming Zhang, Xiuyuan Guo +4
Local learning offers an alternative to traditional end-to-end back-propagation in deep neural networks, significantly reducing GPU memory consumption. Although it has shown promis…
SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation
Changpeng Cai, Guinan Guo, Jiao Li +7
Most earlier researches on talking face generation have focused on the synchronization of lip motion and speech content. However, head pose and facial emotions are equally importan…