2024/12/20

• DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation
• AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
• UIP2P: Unsupervised Instruction-based Image Editing via Cycle Edit Consistency
• Move-in-2D: 2D-Conditioned Human Motion Generation

2024/12/19

• Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
• Mix-LN: Unleashing the Power of Deep Layers by Combining Pre-LN and Post-LN
• ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers

2024/12/18

• Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models
• VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
• MIVE: New Design and Benchmark for Multi-Instance Video Editing

2024/12/17

• Byte Latent Transformer: Patches Scale Better Than Tokens
• ColorFlow: Retrieval-Augmented Image Sequence Colorization
• Causal Diffusion Transformers for Generative Modeling
• Smaller Language Models Are Better Instruction Evolvers
• IDArb: Intrinsic Decomposition for arbitrary number of input views and illuminations
• SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
• Reliable, Reproducible, and Really Fast Leaderboards with Evalica

2024/12/12

• POINTS1.5: Building a Vision-Language Model towards Real World Applications
• StreamChat: Chatting with Streaming Video
• 3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark

2024/12/11

• DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation

2024/12/10

• Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
• Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation
• Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation

2024/12/09

• Moto: Latent Motion Token as the Bridging Language for Robot Manipulation
• SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion
• Mind the Time: Temporally-Controlled Multi-Event Video Generation

2024/12/06

• Evaluating Language Models as Synthetic Data Generators
• Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion
• Negative Token Merging: Image-based Adversarial Feature Guidance
• MV-Adapter: Multi-view Consistent Image Generation Made Easy
• Densing Law of LLMs
• OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

2024/12/05

• PaliGemma 2: A Family of Versatile VLMs for Transfer
• TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
• MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

2024/12/04

• Free Process Rewards without Process Labels
• Scaling Image Tokenizers with Grouped Spherical Quantization
• VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval

2024/12/03

• Open-Sora Plan: Open-Source Large Video Generation Model
• TinyFusion: Diffusion Transformers Learned Shallow
• o1-Coder: an o1 Replication for Coding
• Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis

2024/11/29

• Free2Guide: Gradient-Free Path Integral Control for Enhancing Text-to-Video Generation with Large Vision-Language Models
• TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models

2024/11/28

• Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
• UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing
• Optimizing Brain Tumor Segmentation with MedNeXt: BraTS 2024 SSA and Pediatrics
• VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
• Adaptive Blind All-in-One Image Restoration

2024/11/27

• TEXGen: a Generative Diffusion Model for Mesh Textures
• SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE
• Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
• FineCaption: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

2024/11/26

• Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
• Knowledge Transfer Across Modalities with Natural Language Supervision
• VisualLens: Personalization through Visual History

2024/11/25

• Style-Friendly SNR Sampler for Style-Driven Generation
• Tülu 3: Pushing Frontiers in Open Language Model Post-Training
• A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection
• OminiControl: Minimal and Universal Control for Diffusion Transformer
• VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection
• BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games

2024/11/22

• Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
• OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
• UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages
• MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

2024/11/21

• SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration
• Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
• When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training
• 𝕍⁢𝕚⁢𝔹⁢𝕖: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
• ORID: Organ-Regional Information Driven Framework for Radiology Report Generation

2024/11/20

• Continuous Speculative Decoding for Autoregressive Image Generation
• RedPajama: an Open Dataset for Training Large Language Models

2024/11/19

• Generative World Explorer
• Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering
• Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering
• SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers
• VeGaS: Video Gaussian Splatting