EP18 - I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization

EP17 - Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers

EP16 - Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

EP15 - SelfEval: Leveraging the discriminative nature of generative models for evaluation

EP14 - Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections

EP13 - Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

EP12 - MetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry and Texture

EP11 - Testing Language Model Agents Safely in the Wild

EP10 - Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

EP9 - UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework

EP8 - UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs

EP7 - Adaptive Shells for Efficient Neural Radiance Field Rendering

EP6 - Contrastive Chain-of-Thought Prompting

EP5 - JaxMARL: Multi-Agent RL Environments in JAX

EP4 - Tied-Lora: Enhacing parameter efficiency of LoRA with weight tying

EP3 - Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives

EP2 - The Chosen One: Consistent Characters in Text-to-Image Diffusion Models

EP1 - ML-Bench: Large Language Models Leverage Open-source Libraries for Machine Learning Tasks