MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
Paper
•
2502.17422
•
Published
•
4
Daniel Huynh PRO
dhuynh95
AI & ML interests
None yet
Recent Activity
updated
a collection
about 10 hours ago
cool-papers
upvoted
a
paper
about 10 hours ago
MLLMs Know Where to Look: Training-free Perception of Small Visual
Details with Multimodal LLMs
upvoted
a
paper
about 10 hours ago
Introducing Visual Perception Token into Multimodal Large Language Model
Organizations
dhuynh95's activity
upvoted
3
papers
about 10 hours ago
upvoted
2
papers
about 21 hours ago
upvoted
2
papers
3 days ago
upvoted
10
papers
7 days ago
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Paper
•
2502.08235
•
Published
•
54
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper
•
2502.14499
•
Published
•
167
Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
Paper
•
2502.09083
•
Published
•
4
Intuitive physics understanding emerges from self-supervised pretraining on natural videos
Paper
•
2502.11831
•
Published
•
16
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Paper
•
2502.08826
•
Published
•
16
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training
Paper
•
2502.11196
•
Published
•
21
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper
•
2502.12215
•
Published
•
16
Small Models Struggle to Learn from Strong Reasoners
Paper
•
2502.12143
•
Published
•
27
Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering
Paper
•
2502.13962
•
Published
•
27
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
Paper
•
2502.14802
•
Published
•
11
upvoted
3
papers
13 days ago