Gaze Video
👀
Estimates gaze in a video
Madeleine Muller
mlmPenguin
·
AI & ML interests
None yet
Recent Activity
updated
a Space
about 24 hours ago
mlmPenguin/gaze-video
published
a Space
about 24 hours ago
mlmPenguin/gaze-video
updated
a Space
8 days ago
mlmPenguin/Telephone
Organizations
None yet
mlmPenguin's activity
updated
a
Space
about 24 hours ago
published
a
Space
about 24 hours ago
updated
a
Space
8 days ago
published
a
Space
8 days ago
published
a
Space
16 days ago
updated
a
Space
20 days ago
published
a
Space
20 days ago
reacted to
fuzzy-mittenz's
post with 🔥🚀❤️
29 days ago
Post
2621
Not many seemed to notice but what was probably meant to be a WIN for artist's rights in the US Office of Copyright has solved some fundamental issues for the community.
In our recent article I outline how Companies like Suno, OpenAI, Midjourney etc can no longer claim any right to copy your work that you create with their platforms
We also look at other ways this study and new rules for AI will fundamentally effect creators who use it and companies incentives to give them control over certain aspects might change because of this. it's broken down pretty well here: https://huggingface.co./blog/fuzzy-mittenz/copyright-in-ai
In our recent article I outline how Companies like Suno, OpenAI, Midjourney etc can no longer claim any right to copy your work that you create with their platforms
We also look at other ways this study and new rules for AI will fundamentally effect creators who use it and companies incentives to give them control over certain aspects might change because of this. it's broken down pretty well here: https://huggingface.co./blog/fuzzy-mittenz/copyright-in-ai
liked
2
models
about 1 month ago
liked
a
model
about 2 months ago
updated
2
Spaces
about 2 months ago
reacted to
singhsidhukuldeep's
post with 👀🚀
2 months ago
Post
2115
Groundbreaking Research Alert: Revolutionizing Document Ranking with Long-Context LLMs
Researchers from Renmin University of China and Baidu Inc . have introduced a novel approach to document ranking that challenges conventional sliding window methods. Their work demonstrates how long-context Large Language Models can process up to 100 documents simultaneously, achieving superior performance while reducing API costs by 50%.
Key Technical Innovations:
- Full ranking strategy enables processing all passages in a single inference
- Multi-pass sliding window approach for comprehensive listwise label construction
- Importance-aware learning objective that prioritizes top-ranked passage IDs
- Support for context lengths up to 128k tokens using models like LLaMA 3.1-8B-Instruct
Performance Highlights:
- 2.2 point improvement in NDCG@10 metrics
- 29.3% reduction in latency compared to traditional methods
- Significant API cost savings through elimination of redundant passage processing
Under the hood, the system leverages advanced long-context LLMs to perform global interactions among passages, enabling more nuanced relevance assessment. The architecture incorporates a novel importance-aware loss function that assigns differential weights based on passage ranking positions.
The research team's implementation demonstrated remarkable versatility across multiple datasets, including TREC DL and BEIR benchmarks. Their fine-tuned model, RankMistral, showcases the practical viability of full ranking approaches in production environments.
This advancement marks a significant step forward in information retrieval systems, offering both improved accuracy and computational efficiency. The implications for search engines and content recommendation systems are substantial.
Researchers from Renmin University of China and Baidu Inc . have introduced a novel approach to document ranking that challenges conventional sliding window methods. Their work demonstrates how long-context Large Language Models can process up to 100 documents simultaneously, achieving superior performance while reducing API costs by 50%.
Key Technical Innovations:
- Full ranking strategy enables processing all passages in a single inference
- Multi-pass sliding window approach for comprehensive listwise label construction
- Importance-aware learning objective that prioritizes top-ranked passage IDs
- Support for context lengths up to 128k tokens using models like LLaMA 3.1-8B-Instruct
Performance Highlights:
- 2.2 point improvement in NDCG@10 metrics
- 29.3% reduction in latency compared to traditional methods
- Significant API cost savings through elimination of redundant passage processing
Under the hood, the system leverages advanced long-context LLMs to perform global interactions among passages, enabling more nuanced relevance assessment. The architecture incorporates a novel importance-aware loss function that assigns differential weights based on passage ranking positions.
The research team's implementation demonstrated remarkable versatility across multiple datasets, including TREC DL and BEIR benchmarks. Their fine-tuned model, RankMistral, showcases the practical viability of full ranking approaches in production environments.
This advancement marks a significant step forward in information retrieval systems, offering both improved accuracy and computational efficiency. The implications for search engines and content recommendation systems are substantial.
upvoted
a
collection
2 months ago
liked
a
model
3 months ago
liked
a
Space
3 months ago