Temporal Preference Optimization for Long-Form Video Understanding
Paper
•
2501.13919
•
Published
•
22
•
3
Simeon Emanuilov PRO
s-emanuilov
AI & ML interests
Software Engineer & Ph.D. candidate | Specializing in ML/DL system development & applying AI to solve real-world business problems.
Recent Activity
updated
a dataset
40 minutes ago
s-emanuilov/Tucan-BG-Eval-v1.0
reacted
to
danielhanchen's
post
with 🔥
about 20 hours ago
Mistral releases Magistral, their new reasoning models! 🔥
GGUFs to run: https://huggingface.co/unsloth/Magistral-Small-2506-GGUF
Magistral-Small-2506 excels at mathematics and coding.
You can run the 24B model locally with just 32GB RAM by using our Dynamic GGUFs.
updated
a model
about 21 hours ago
s-emanuilov/Tucan-27B-v1.0
Organizations
s-emanuilov's activity
commented
8
papers
5 months ago
IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
Paper
•
2501.13920
•
Published
•
17
•
2
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Paper
•
2501.09751
•
Published
•
49
•
2
Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
Paper
•
2501.09012
•
Published
•
10
•
2
MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents
Paper
•
2501.08828
•
Published
•
32
•
2
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
Paper
•
2501.09019
•
Published
•
12
•
2
HALoGEN: Fantastic LLM Hallucinations and Where to Find Them
Paper
•
2501.08292
•
Published
•
17
•
2
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
Paper
•
2501.01427
•
Published
•
55
•
3