Submitted by akhaliq 41 ScreenAI: A Vision-Language Model for UI and Infographics Understanding · 10 authors 4
Submitted by akhaliq 26 LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation · 6 authors 3
Submitted by akhaliq 22 EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss · 3 authors 1
Submitted by akhaliq 15 CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay · 7 authors 1
Submitted by akhaliq 14 The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry · 4 authors 3
Submitted by akhaliq 2 Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers · 7 authors 1