new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Apr 26

Submitted by

akhaliq

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

·
13 authors

Submitted by

akhaliq

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

·
27 authors

5

Submitted by

akhaliq

Make Your LLM Fully Utilize the Context

·
5 authors

Submitted by

akhaliq

Interactive3D: Create What You Want by Interactive 3D Generation

·
6 authors

Submitted by

akhaliq

ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

·
11 authors

Submitted by

akhaliq

Tele-FLM Technical Report

·
20 authors

Submitted by

akhaliq

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

·
11 authors

Submitted by

akhaliq

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

·
11 authors

Submitted by

akhaliq

NeRF-XL: Scaling NeRFs with Multiple GPUs

·
4 authors

Submitted by

akhaliq

SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension

·
6 authors