Submitted by iseesaw 41 Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization · 10 authors 26
Submitted by wingrune 34 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding · 2 authors 2
Submitted by vinthony 19 DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation · 8 authors 2
Submitted by lx865712528 18 Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning · 4 authors 3
Submitted by Borchmann 16 In Case You Missed It: ARC 'Challenge' Is Not That Challenging · 1 authors 2
Submitted by jt-zhang 16 ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing · 3 authors 2
Submitted by silentchen 15 PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models · 7 authors 2
Submitted by amanchadha 9 SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval · 5 authors 2
Submitted by wang-sj16 6 MotiF: Making Text Count in Image Animation with Motion Focal Loss · 6 authors 2