SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published 4 days ago • 63
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding Paper • 2502.08946 • Published 30 days ago • 184
DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image Inpainting Paper • 2411.17223 • Published Nov 26, 2024 • 7
Edge Weight Prediction For Category-Agnostic Pose Estimation Paper • 2411.16665 • Published Nov 25, 2024 • 6
LLMs Do Not Think Step-by-step In Implicit Reasoning Paper • 2411.15862 • Published Nov 24, 2024 • 10
From CISC to RISC: language-model guided assembly transpilation Paper • 2411.16341 • Published Nov 25, 2024 • 14
SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis Paper • 2411.16443 • Published Nov 25, 2024 • 12
Best of Both Worlds: Advantages of Hybrid Graph Sequence Models Paper • 2411.15671 • Published Nov 23, 2024 • 9
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages Paper • 2411.16508 • Published Nov 25, 2024 • 11
TEXGen: a Generative Diffusion Model for Mesh Textures Paper • 2411.14740 • Published Nov 22, 2024 • 17
Knowledge Transfer Across Modalities with Natural Language Supervision Paper • 2411.15611 • Published Nov 23, 2024 • 17