What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Paper
•
2410.23743
•
Published
•
59
•
4
Tianyi Zhou
zhoutianyi
AI & ML interests
ML, NLP, RL, Multi-modality
Recent Activity
authored
a paper
9 days ago
GUI Agents: A Survey
upvoted
a
paper
9 days ago
GUI Agents: A Survey
authored
a paper
22 days ago
Florence-VL: Enhancing Vision-Language Models with Generative Vision
Encoder and Depth-Breadth Fusion
Organizations
zhoutianyi's activity
commented
a
paper
about 2 months ago
commented
5
papers
2 months ago
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Paper
•
2410.13674
•
Published
•
15
•
3
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion
Paper
•
2410.13674
•
Published
•
15
•
3
BenTo: Benchmark Task Reduction with In-Context Transferability
Paper
•
2410.13804
•
Published
•
19
•
3
BenTo: Benchmark Task Reduction with In-Context Transferability
Paper
•
2410.13804
•
Published
•
19
•
3
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
Paper
•
2410.10814
•
Published
•
48
•
2
commented
3
papers
3 months ago
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Paper
•
2410.07484
•
Published
•
48
•
3
WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents
Paper
•
2410.07484
•
Published
•
48
•
3
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA
Paper
•
2410.06524
•
Published
•
4
•
2
commented
a
paper
10 months ago