21 papers
Loop the Loopies!
Zitian Gao, Yilong Chen, Yihao Xiao +4
We present the Loopie series, consisting of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6B-parameter model with 0.6B active parameter…
ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation
Yao Chen, Yinqi Yang, Junyuan Shang +6
Hybrid architectures combining full attention (FA) and sliding-window attention (SWA) are a promising paradigm for efficient LLM inference. However, existing methods typically rely…
MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection
Xueying Ding, Simon Klüttermann, Haomin Wen +2
Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological choices. Outlier detection (OD) o…
Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding
Yuchen Feng, Zhenyu Zhang, Naibin Gu +8
Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, per…
VIP-COP: Context Optimization for Tabular Foundation Models
Yilong Chen, Xueying Ding, Leman Akoglu
Tabular foundation models (TFMs) have emerged as a powerful paradigm for in-context learning on structured data, enabling direct prediction on new tabular tasks without task-specif…
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
Naibin Gu, Zhenyu Zhang, Yuchen Feng +8
Mixture-of-Experts (MoE) models typically fix the number of activated experts at both training and inference. However, real-world deployments often face heterogeneous hardware,…