Paper-Conference

TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
In this paper, we present TransMLA, a framework that seamlessly converts any GQA-based pre-trained model into an MLA-based model. Our …
PDF Code
Reconsidering the Performance of GAE in Link Prediction
Recent advancements in graph neural networks (GNNs) for link prediction have introduced sophisticated training techniques and model …
PDF Code
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
Decoder-only models generate tokens autoregressively by caching key/value vectors, but as the cache grows, inference becomes …
PDF
Geometric Representation Condition Improves Equivariant Molecule Generation
Recent advances in molecular generative models have demonstrated great promise for accelerating scientific discovery, particularly in …
PDF Code
Griffin: Towards a Graph-Centric Relational Database Foundation Model
We introduce Griffin, the first foundation model designed specifically for Relational Databases (RDBs). Unlike previous smaller models …
PDF Code
3D-SubG: A 3D Stacked Hybrid Processing Near/In-Memory Accelerator for Subgraph GNNs
GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
Foundation models, such as Large Language Models (LLMs) or Large Vision Models (LVMs), have emerged as one of the most powerful tools …
PDF Code
Number Cookbook: Number Understanding of Language Models and How to Improve It
Large language models (LLMs) can solve an increasing number of complex reasoning tasks while making surprising mistakes in basic …
PDF Code
On the Completeness of Invariant Geometric Deep Learning Models
Invariant models, one important class of geometric deep learning models, are capable of generating meaningful geometric representations …
PDF
VACT: A Video Automatic Causal Testing System and a Benchmark
With the rapid advancement of text-conditioned Video Generation Models (VGMs), the quality of generated videos has significantly …
PDF