1 citations · 4 across the 7 of their papers we have counts for
8 papers
SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question Answering
Davit Soselia, Joseph JaJa, Amitabh Varshney
3D Gaussian language fields provide an explicit, spatially grounded representation for 3D visual question answering (VQA), but their dense semantic features can require tens of tho…
ChartAB: A Benchmark for Chart Grounding & Dense Alignment
Aniruddh Bansal, Davit Soselia, Dang Nguyen +1
Charts play an important role in visualization, reasoning, data analysis, and the exchange of ideas among humans. However, existing vision-language models (VLMs) still lack accurat…
OPTune: Efficient Online Preference Tuning
Lichang Chen, Jiuhai Chen, Chenxi Liu +6
Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLH…
ODIN: Disentangled Reward Mitigates Hacking in RLHF
Lichang Chen, Chen Zhu, Davit Soselia +6
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verb…
Reviving Shift Equivariance in Vision Transformers
Peijian Ding, Davit Soselia, Thomas Armstrong +2
Shift equivariance is a fundamental principle that governs how we perceive the world - our recognition of an object remains invariant with respect to shifts. Transformers have gain…
Learning UI-to-Code Reverse Generator Using Visual Critic Without Rendering
Davit Soselia, Khalid Saifullah, Tianyi Zhou
Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper,…
RNN-based Online Handwritten Character Recognition Using Accelerometer and Gyroscope Data
Davit Soselia, Shota Amashukeli, Irakli Koberidze +1
This abstract explores an RNN-based approach to online handwritten recognition problem. Our method uses data from an accelerometer and a gyroscope mounted on a handheld pen-like de…
Reproduction Report on "Learn to Pay Attention"
Levan Shugliashvili, Davit Soselia, Shota Amashukeli +1
We have successfully implemented the "Learn to Pay Attention" model of attention mechanism in convolutional neural networks, and have replicated the results of the original paper i…