Mechanistic tracing shows text suppresses but does not erase audio representations in late layers of Audio LLMs; back-patching reduces text dominance.
When language overrules: Modality imbalance in vlms
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
ELF-S2T applies audio-conditioned flow-matching on continuous text latents from pre-trained ELF to achieve competitive ASR and S2TT results, with analysis showing shared close-distance confusion in latent space.
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
MoIR mitigates modality dominance in VLMs by explicitly enriching low-information tokens with routed data from stronger modalities prior to LLM processing, yielding more balanced contributions and improved robustness under degradation.
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
Filtering post-training data to visually grounded questions improves VLM video understanding performance by up to 6.2 points using 69% of the data.
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.
CAAD internalizes contrastive audio-aware decoding into student SLM weights via synchronized teacher-forcing, delivering an 8% relative gain over standard knowledge distillation on Dynamic-SUPERB while reducing linguistic bias on MCR-BENCH.
citing papers explorer
-
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
Mechanistic tracing shows text suppresses but does not erase audio representations in late layers of Audio LLMs; back-patching reduces text dominance.
-
Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation
ELF-S2T applies audio-conditioned flow-matching on continuous text latents from pre-trained ELF to achieve competitive ASR and S2TT results, with analysis showing shared close-distance confusion in latent space.
-
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
-
Information Router for Mitigating Modality Dominance in Vision-Language Models
MoIR mitigates modality dominance in VLMs by explicitly enriching low-information tokens with routed data from stronger modalities prior to LLM processing, yielding more balanced contributions and improved robustness under degradation.
-
Counting to Four is still a Chore for VLMs
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
-
Watch Before You Answer: Learning from Visually Grounded Post-Training
Filtering post-training data to visually grounded questions improves VLM video understanding performance by up to 6.2 points using 69% of the data.
-
Token-Efficient Multimodal Reasoning via Image Prompt Packaging
IPPg embeds text into images to reduce multimodal model inference costs by 35.8-91% with competitive accuracy on many VQA and code benchmarks.
-
CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models
CAAD internalizes contrastive audio-aware decoding into student SLM weights via synchronized teacher-forcing, delivering an 8% relative gain over standard knowledge distillation on Dynamic-SUPERB while reducing linguistic bias on MCR-BENCH.