LINs-lab
Learning and INference Systems (LINs) Laboratory
Built from LINs-lab's public GitHub profile, China. Not on Take My Repo yet, so there are no posts or updates here.
[ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
[Preprint] UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
[CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm
Graduate Course at Westlake University
[ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
[Preprint] Self-Adversarial One Step Generation via Condition Shifting
[ICLR 2023] Test-time Robust Personalization for Federated Learning
[ICLR 2026] Any-step Generation via N-th Order Recursive Consistent Velocity Field Estimation
A comprehensive framework for benchmarking single and multi-agent systems across a wide range of tasks—evaluating performance, accuracy, and efficiency with built-in visualization and tool integration.
[Preprint] Efficient Generative Model Training via Embedded Representation Warmup
[ICLR 2026] Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
[ICML 2023] FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
[CVPR 2026] IOMM: Fast Pre-training of Unified Multimodal Models without Text-Image Pairs
[Preprint] A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
[preprint] Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
[NeurIPS 2024] Efficiency for Free: Ideal Data Are Transportable Representations
[ICLR 2025] ELICIT: LLM Augmentation Via External In-context Capability