Too Good to be Bad: On the Failure of LLMs to Role-Play Villains
Paper
•
2511.04962
•
Published
•
52
Zhao
Hanyu66
AI & ML interests
CV, NLP
Recent Activity
liked
a model
13 days ago
InstantX/Qwen-Image-ControlNet-Union
updated
a collection
26 days ago
AwesomeLLMs
liked
a model
29 days ago
jay-jnp/F-ViTA_KAIST
Organizations
None yet
upvoted
5
papers
about 1 month ago
DeepEyesV2: Toward Agentic Multimodal Model
Paper
•
2511.05271
•
Published
•
42
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
Paper
•
2511.05017
•
Published
•
7
Visual Spatial Tuning
Paper
•
2511.05491
•
Published
•
50
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
Paper
•
2510.25897
•
Published
•
16
upvoted
a
paper
about 2 months ago
upvoted
a
collection
about 1 year ago
upvoted
a
paper
about 1 year ago
upvoted
a
collection
about 1 year ago
upvoted
6
papers
over 1 year ago
Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models
Paper
•
2308.13437
•
Published
•
4
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities
Paper
•
2308.12966
•
Published
•
11
Zero-Shot and Few-Shot Video Question Answering with Multi-Modal Prompts
Paper
•
2309.15915
•
Published
•
2
Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants
Paper
•
2310.00653
•
Published
•
3
An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Paper
•
2309.09958
•
Published
•
19
Improved Baselines with Visual Instruction Tuning
Paper
•
2310.03744
•
Published
•
39