1 citations · 1 across the 9 of their papers we have counts for
13 papers
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Guanghui Min, Liang Wu, Mingjia Shi +4
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing pr…
Grounding Memory Summarization in Utility Intent
Zhenyu Lei, Mingjia Shi, Xingbo Fu +3
Existing summarizers for memory systems are typically optimized for human-facing criteria such as faithfulness, which misaligns with their true objective: preserving the evidence n…
Dive Into the Implicit Biases of Low-rank Vision-language Alignment
Mingjia Shi, Shuo Wang, Xiaobo Wang +7
Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requiring full-parameter updates.…
Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning
Mingjia Shi, Yinhan He, Yaochen Zhu +1
Vision-language models (VLMs) aim to reason by jointly leveraging visual and textual modalities. While allocating additional inference-time computation has proven effective for lar…
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
Yinhan He, Yaochen Zhu, Mingjia Shi +5
Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-tr…
Mano Technical Report
Tianyu Fu, Anyang Su, Chenxu Zhao +20
Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements…
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Zhiyuan Liang, Dongwen Tang, Yuhao Zhou +11
Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate o…
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Ziqiao Wang, Wangbo Zhao, Yuhao Zhou +9
Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy -- representation alignment (REPA) that matches D…
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
Zekai Li, Xinhao Zhong, Samir Khaki +49
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning
Sifan Zhou, Shuo Wang, Zhihang Yuan +3
Large Language Models (LLMs) fine-tuning technologies have achieved remarkable results. However, traditional LLM fine-tuning approaches face significant challenges: they require la…
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
Mingjia Shi, Yuhao Zhou, Ruiji Yu +8
Vision Mamba has shown close to state of the art performance on computer vision tasks, drawing much interest in increasing it's efficiency. A promising approach is token reduction…
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
Xinghao Wu, Jianwei Niu, Xuefeng Liu +4
Federated Learning (FL) faces challenges due to data heterogeneity, which limits the global model's performance across diverse client distributions. Personalized Federated Learning…
A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
Kai Wang, Mingjia Shi, Yukun Zhou +6
Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a clos…