SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
•
2502.14786
•
Published
•
82
Young-Jun Lee PRO
passing2961
AI & ML interests
Social Dialogue System, Multi-Modal Dialogue
Recent Activity
upvoted
a
paper
26 minutes ago
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
upvoted
a
paper
26 minutes ago
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Organizations
None yet
passing2961's activity
upvoted
3
papers
26 minutes ago
upvoted
a
paper
2 days ago
upvoted
2
papers
8 days ago
published
a
dataset
9 days ago
updated
a
dataset
9 days ago
upvoted
8
papers
10 days ago
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper
•
2502.06703
•
Published
•
133
Agency Is Frame-Dependent
Paper
•
2502.04403
•
Published
•
21
FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
Paper
•
2502.05179
•
Published
•
22
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
Paper
•
2502.05003
•
Published
•
41
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper
•
2502.05171
•
Published
•
113
Ola: Pushing the Frontiers of Omni-Modal Language Model with Progressive Modality Alignment
Paper
•
2502.04328
•
Published
•
26
BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Paper
•
2502.03860
•
Published
•
23
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper
•
2502.04128
•
Published
•
23
updated
a
collection
12 days ago