new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Dec 19

Submitted by

akhaliq

Gemini: A Family of Highly Capable Multimodal Models

·
942 authors

Submitted by

akhaliq

VecFusion: Vector Font Generation with Diffusion

·
8 authors

Submitted by

akhaliq

SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

·
5 authors

Submitted by

akhaliq

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

·
11 authors

Submitted by

akhaliq

Rich Human Feedback for Text-to-Image Generation

·
18 authors

Submitted by

akhaliq

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

·
7 authors

Submitted by

akhaliq

M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts

·
8 authors

Submitted by

akhaliq

MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising

·
7 authors

Submitted by

akhaliq

A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise

·
22 authors

Submitted by

akhaliq

Paloma: A Benchmark for Evaluating Language Model Fit

·
16 authors

Submitted by

akhaliq

MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance

·
5 authors

Submitted by

akhaliq

Silkie: Preference Distillation for Large Visual Language Models

·
9 authors

Submitted by

akhaliq

VidToMe: Video Token Merging for Zero-Shot Video Editing

·
4 authors

Submitted by

akhaliq

Cascade Speculative Drafting for Even Faster LLM Inference

·
6 authors

Submitted by

akhaliq

Catwalk: A Unified Language Model Evaluation Framework for Many Datasets

·
10 authors

Submitted by

akhaliq

ProTIP: Progressive Tool Retrieval Improves Planning

·
6 authors

Submitted by

akhaliq

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

·
4 authors

Submitted by

akhaliq

Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method

·
5 authors

Submitted by

akhaliq

VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder

·
7 authors

Submitted by

akhaliq

GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis

·
7 authors