Towards Understanding Sycophancy in Language ModelsControlled Decoding from Language Models

LLM-FP4: 4-Bit Floating-Point Quantized TransformersDetecting Pretraining Data from Large Language Models

Matryoshka Diffusion ModelsDissecting In-Context Learning of Translations in GPTsWoo...

FreeNoise: Tuning-Free Longer Video Diffusion Via Noise ReschedulingHallusionBench: You See What You Think? Or You Think What You See? An Im...

H2O Open Ecosystem for State-of-the-art Large Language ModelsLet's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language ...

Think before you speak: Training Language Models With Pause TokensTowards Self-Assembling Artificial Neural Networks through Neural Developm...

Enable Language Models to Implicitly Learn Self-Improvement From DataPixArt-alpha: Fast Training of Diffusion Transformer for Photorealistic...

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingDecaf: Monocular Deformation Capture for Face and Hand Interactions<...

Effective Long-Context Scaling of Foundation ModelsDemystifying CLIP DataVision Tran...

NeuRBF: A Neural Fields Representation with Adaptive Radial Basis FunctionsEmu: Enhancing Image Generation Models Using Photogenic Needles i...

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer ModelsAligning Large Multimodal Models wi...

CoRF : Colorizing Radiance Fields using Knowledge DistillationThe Cambridge Law Corpus: A Corpus for Legal AI Research

Parallelizing non-linear sequential models over the sequence lengthFast Feedforward Networks

FreeU: Free Lunch in Diffusion U-NetNeurons in Large Language Models: Dead, N-gram, Positional

Graph Neural Networks Use Graphs When They Shouldn'tLarge Language Models for Compiler Optimization

Textbooks Are All You Need II: phi-1.5 technical reportDiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior...

Large-Scale Automatic Audiobook CreationCityDreamer: Compositional Generative Model of Unbounded 3D Cities

Large Language Models as OptimizersFLM-101B: An Open LLM and How to Train It with $100K Budget

SLiMe: Segment Like MeMatcha-TTS: A fast TTS architecture with conditional flow matching

One Wide Feedforward is All You NeedEfficient RLHF: Reducing the Memory Usage of PPO...

Fast Inference from Transformers via Speculative DecodingYaRN: Efficient Context Window Extension of Large Language Models

The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language VariantsAny-Size-Diffusion: Toward Efficient Text-Driven Sy...

WeatherBench 2: A benchmark for the next generation of data-driven global weather modelsRoboTAP: Tracking Arbitrary Points for Few-Shot Visu...

Reward-Respecting Subtasks for Model-Based Reinforcement LearningRelightify: Relightable 3D Faces from a Single Image via Diffusion Models

Break-A-Scene: Extracting Multiple Concepts from a Single ImageThe Poison of Alignment