Paper Review10 posts
- AIVLASpec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
- AIVisionGTA1: GUI Test-time Scaling Agent
- AIVisionCATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
- AIVisionImagePiece: Content-aware Re-tokenization for Efficient Image Recognition
- AILLMAdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
- AIRLTTRL: Test-Time Reinforcement Learning
- AILLMTest-Time Learning for Large Language Models
- AIDiffusionSANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
- AIDiffusionQuantizationSVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
- AIDiffusionPixArt-ฮฃ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Tip4 posts
Study8 posts
Talk3 posts
Algorithm9 posts