1 citations · 1 across the 11 of their papers we have counts for
12 papers
Tensor Cache: Eviction-conditioned Associative Memory for Transformers
Kabir Swain, Sijie Han, Daniel Karl I. Weidele +2
Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the…
From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain
Yuval Golbari, Navve Wasserman, Matias Cosarinsky +5
Identifying which brain regions represent a visual concept in the human brain is a central challenge in neuroscience. Existing approaches have localized coarse functional regions (…
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Shaden Alshammari, Kevin Wen, Abrar Zainal +5
Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in size, language coverage, and t…
End-to-End Training for Unified Tokenization and Latent Denoising
Shivam Duggal, Xingjian Bai, Zongze Wu +5
Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer m…
The Dual Mechanisms of Spatial Variable Binding in Vision-Language Models
Kelly Cui, Nikhil Prakash, Shoval Messica +4
Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations. Ye…
Fairness Aware Reward Optimization
Ching Lam Choi, Vighnesh Subramaniam, Phillip Isola +2
Demographic skews in human preference data propagate systematic unfairness through reward models into aligned LLMs. We introduce Fairness Aware Reward Optimization (Faro), an in-pr…
Separating Knowledge and Perception with Procedural Data
Adrián Rodríguez-Muñoz, Manel Baradad, Phillip Isola +1
We train representation models with procedural data only, and apply them on visual similarity, classification, and semantic segmentation tasks without further training by using vis…
Single-pass Adaptive Image Tokenization for Minimum Program Search
Shivam Duggal, Sanghyun Byun, William T. Freeman +2
According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low K…
Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
Shivam Duggal, Yushi Hu, Oscar Michel +7
Despite the unprecedented progress in the field of 3D generation, current systems still often fail to produce high-quality 3D assets that are visually appealing and geometrically a…
Adaptive Length Image Tokenization via Recurrent Allocation
Shivam Duggal, Phillip Isola, Antonio Torralba +1
Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large langu…
Characterizing Model Robustness via Natural Input Gradients
Adrián Rodríguez-Muñoz, Tongzhou Wang, Antonio Torralba
Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is us…
Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
Tianhang Cheng, Wei-Chiu Ma, Kaiyu Guan +2
Our world is full of identical objects (\emphe.g., cans of coke, cars of same model). These duplicates, when seen together, provide additional and strong cues for us to effectively…