aimagelab/Mappet-I-8B
9B • Updated • 10
AI & ML interests
None defined yet.
Recent Activity
Papers
Mind the Heads: Topological Representation Alignment for Multimodal LLMs
ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
williamraccagni
updated a
model 16 days ago
williamraccagni
updated a
collection 16 days ago
williamraccagni
published a
model 16 days ago
williamraccagni
updated a
model 16 days ago
williamraccagni
published a
model 16 days ago
williamraccagni
updated a
collection 16 days ago
williamraccagni
updated a
model 16 days ago
williamraccagni
published a
model 16 days ago
lzini
authored 6
papers about 1 month ago
SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation
Paper • 2609.03806 • Published
SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-Resolution
Paper • 2609.03813 • Published • 1
SVGauge: Towards Human-Aligned Evaluation for SVG Generation
Paper • 2509.07127 • Published
Diffusion Language Models: An Experimental Analysis
Paper • 2606.19475 • Published • 1
A Scalable Vector Graphics Latent Space
Paper • 2608.21893 • Published
GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution
Paper • 2604.25457 • Published • 1
tobi1modna
authored 3
papers about 2 months ago
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
Paper • 2606.05290 • Published
CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models
Paper • 2601.04778 • Published
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
Paper • 2505.15323 • Published
tobi1modna
updated a
collection about 2 months ago