Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
Visual representations inside the language model.arXiv preprint arXiv:2510.04819
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 5roles
background 2polarities
background 2representative citing papers
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
Decoder-based VLMs hallucinate because visual embeddings are over-aligned to a text manifold; projecting out the top principal components of a universal linguistic subspace reduces this bias and improves benchmark performance.
VLMs bypass visual comparison by recovering semantic labels for nameable entities and hallucinate on unnamable ones, as shown by performance gaps and Logit Lens analysis.
Mull-Tokens are modality-agnostic latent tokens that enable free-form multimodal thinking and deliver up to 16% gains on spatial reasoning benchmarks.
citing papers explorer
-
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Unified multimodal models exhibit pseudo-unification due to modality-asymmetric entropy encoding and pattern-split responses between text and image generation.
-
Do multimodal models imagine electric sheep?
Fine-tuning VLMs to output action sequences for puzzles causes emergent internal visual representations that improve performance when integrated into reasoning.
-
When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models
Decoder-based VLMs hallucinate because visual embeddings are over-aligned to a text manifold; projecting out the top principal components of a universal linguistic subspace reduces this bias and improves benchmark performance.
-
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
VLMs bypass visual comparison by recovering semantic labels for nameable entities and hallucinate on unnamable ones, as shown by performance gaps and Logit Lens analysis.
-
Mull-Tokens: Modality-Agnostic Latent Thinking
Mull-Tokens are modality-agnostic latent tokens that enable free-form multimodal thinking and deliver up to 16% gains on spatial reasoning benchmarks.