Large Language Model
Linguistic Collapse: Neural Collapse in (Large) Language Models
Convergence to a simplex ETF: Class means tend towards equinorm and equiangular vectors when centred about the global average.
ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition Mohammadreza Salehi Jae Sung Park
Each video in the dataset is paired with a question and four or five choices.
processing enables human-like zero-shot generalization to random dot stimuli
Motion is a powerful cue that humans use to detect and segment visual objects.
Unchosen Experts Can Contribute Too: Unleashing MoE Models ' Power by Self-Contrast
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency.
Aligning LLM Agents by Learning Latent Preference from User Edits Ge Gao Alexey T aymanov Eduardo Salinas Paul Mineiro Dipendra Misra Department of Computer Science, Cornell University
The inferred user preference descriptions are used to define prompts for generating responses in the future.
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
This renders them impractical to use in a wide range of use-cases, limiting who can benefit from them to a handful of big corporations. As an attempt to mitigate this issue, Touvron et al.
