FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
SocialIQA is the first large-scale benchmark with 38k crowdsourced questions testing commonsense about social interactions, where pretrained language models trail humans by over 20% but transfer to improve performance on Winograd Schemas and COPA.
RELO formulates visual object tracking localization as a Markov decision process solved by reinforcement learning with combined IoU and AUC rewards, augmented by layer-aligned temporal token propagation, and reports 57.5% AUC on LaSOText without template updates.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
Fine-tuned language models store knowledge in parameters to answer questions competitively with retrieval-based open-domain QA systems.
citing papers explorer
-
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
FiBeR adds a closed-form filter-aware correction A(ω)σ_w² to the second-moment term for temporally filtered DP gradients, improving adaptive optimization performance.
-
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
-
SocialIQA: Commonsense Reasoning about Social Interactions
SocialIQA is the first large-scale benchmark with 38k crowdsourced questions testing commonsense about social interactions, where pretrained language models trail humans by over 20% but transfer to improve performance on Winograd Schemas and COPA.
-
RELO: Reinforcement Learning to Localize for Visual Object Tracking
RELO formulates visual object tracking localization as a Markov decision process solved by reinforcement learning with combined IoU and AUC rewards, augmented by layer-aligned temporal token propagation, and reports 57.5% AUC on LaSOText without template updates.
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
-
How Much Knowledge Can You Pack Into the Parameters of a Language Model?
Fine-tuned language models store knowledge in parameters to answer questions competitively with retrieval-based open-domain QA systems.