ICCV2023

ICCV2023's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

AdinaY 

posted an update about 7 hours ago

view post

Post

391

Excited to see Alibaba DAMO Academy release a multimodel dataset for vision language pretraining on the hub🔥

Paper: 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining (2501.00958)
Dataset: DAMO-NLP-SG/multimodal_textbook

✨ 6.5M images + 0.8B text from 22k hours of instructional videos
✨ Covers subjects like math, physics, and chemistry
✨ Apache 2.0

See translation

• 

🔥

1

1

🤗

1

1

+

Reply

hysts 

updated a Space 5 days ago

Running

56

🦀

ICCV2023 Papers

risashinoda 

authored 2 papers 7 days ago

OpenAnimalTracks: A Dataset for Animal Track Recognition

Paper • 2406.09647 • Published Jun 14, 2024

SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images

Paper • 2412.17606 • Published 14 days ago • 5

AdinaY 

posted an update 12 days ago

view post

Post

3521

The Chinese community is shipping 🚢

DeepSeek V3 (685 B MoE) has quietly released on the hub!
Base: deepseek-ai/DeepSeek-V3-Base
Instruct: deepseek-ai/DeepSeek-V3

Can’t wait to see what’s next!

See translation

• 

• 
• 1 reply

·

🔥

13

13

🚀

7

7

👍

3

3

❤️

2

2

🤗

2

2

👀

1

1

+

Reply

AdinaY 

posted an update 13 days ago

view post

Post

2948

QvQ-72B-Preview🎄 an open weight model for visual reasoning just released by Alibaba_Qwen team
Qwen/qvq-676448c820912236342b9888
✨ Combines visual understanding & language reasoning.
✨ Scores 70.3 on MMMU
✨ Outperforms Qwen2-VL-72B-Instruct in complex problem-solving

See translation

• 

🔥

11

11

👀

5

5

❤️

1

1

🚀

1

1

+

Reply

AtAndDev 

posted an update 19 days ago

view post

Post

378

@s3nh Hey man check your discord! Got some news.

See translation

• 
• 
• 4 replies

·

👍

1

1

+

Reply

katanaxu 

authored 12 papers 21 days ago

FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces

Paper • 1909.06122 • Published Sep 13, 2019

Zero-Day Backdoor Attack against Text-to-Image Diffusion Models via Personalization

Paper • 2305.10701 • Published May 18, 2023

FakeLocator: Robust Localization of GAN-Based Face Manipulations

Paper • 2001.09598 • Published Jan 27, 2020

Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models

Paper • 2307.10236 • Published Jul 16, 2023 • 1

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Paper • 2404.06247 • Published Apr 9, 2024

Introducing v0.5 of the AI Safety Benchmark from MLCommons

Paper • 2404.12241 • Published Apr 18, 2024 • 10

Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models

Paper • 2405.21050 • Published May 31, 2024

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models

Paper • 2407.11282 • Published Jul 15, 2024 • 1

Pixel-Space Post-Training of Latent Diffusion Models

Paper • 2409.17565 • Published Sep 26, 2024 • 20

Movie Gen: A Cast of Media Foundation Models

Paper • 2410.13720 • Published Oct 17, 2024 • 90

Apollo: An Exploration of Video Understanding in Large Multimodal Models

Paper • 2412.10360 • Published 24 days ago • 136

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

Paper • 2412.09856 • Published 25 days ago • 9

AdinaY 

posted an update 21 days ago

view post

Post

541

Megrez-3B-Omni 🔥 an on-device multimodal LLM by Infinigence AI, another startup emerging from the Tsinghua University ecosystem.
Model: Infinigence/Megrez-3B-Omni
Demo: Infinigence/Megrez-3B-Omni
✨Supports analysis of image, text, and audio modalities
✨Leads in bilingual speech ( English & Chinese ) input, multi-turn conversations, and voice-based queries
✨Outperforms in scene understanding and OCR across major benchmarks

See translation

• 
• 

🔥

3

3

+

Reply