3

Video Unlearning via Low-Rank Refusal Vector
Video generative models democratize the creation of visual content through intuitive instruction following, but they also inherit the …
Cite arXiv GitHub
Video Unlearning via Low-Rank Refusal Vector
Implicit Inversion turns CLIP into a Decoder
CLIP is a discriminative model trained to align images and text in a shared embedding space. Due to its multimodal structure, it serves …
Cite arXiv GitHub
Implicit Inversion turns CLIP into a Decoder
Navigating the Latent Space Dynamics of Neural Models
Neural networks transform high-dimensional data into compact, structured representations, often modeled as elements of a lower …
Cite arXiv
Navigating the Latent Space Dynamics of Neural Models
Activation Patching for Interpretable Steering in Music Generation
Understanding how large audio models represent music, and using that understanding to steer generation, is both challenging and …
Cite arXiv
Activation Patching for Interpretable Steering in Music Generation
MASS: MoErging through Adaptive Subspace Selection
Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set …
Cite arXiv
MASS: MoErging through Adaptive Subspace Selection
Decoding RNA-RNA Interactions: The Role of Low-Complexity Repeats and a Deep Learning Framework for Sequence-Based Prediction
RNA-RNA interactions (RRIs) are fundamental to gene regulation and RNA processing, yet their molecular determinants remain unclear. In …
Cite bioRxiv GitHub
Decoding RNA-RNA Interactions: The Role of Low-Complexity Repeats and a Deep Learning Framework for Sequence-Based Prediction
Humanity's Last Exam
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are …
Cite URL GitHub arXiv
Humanity's Last Exam
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations …
Cite arXiv GitHub
COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations
ATM: Improving Model Merging by Alternating Tuning and Merging
Model merging has recently emerged as a cost-efficient paradigm for multi-task learning. Among current approaches, task arithmetic …
Cite arXiv GitHub
ATM: Improving Model Merging by Alternating Tuning and Merging
ResiDual Transformer Alignment with Spectral Decomposition
When examined through the lens of their residual streams, a puzzling property emerges in transformer networks: residual contributions …
Cite arXiv
ResiDual Transformer Alignment with Spectral Decomposition