297 citations · 697 across the 15 of their papers we have counts for
17 papers
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai
Parinthapat Pengpun, Can Udomcharoenchaikit, Weerayut Buaphet +1
We present a synthetic data approach for instruction-tuning large language models (LLMs) for low-resource languages in a data-efficient manner, specifically focusing on Thai. We id…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
Continuous diffusion for categorical data
Sander Dieleman, Laurent Sartran, Arman Roshannai +11
Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges…
Self-conditioned Embedding Diffusion for Text Generation
Robin Strudel, Corentin Tallec, Florent Altché +8
Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can si…
Step-unrolled Denoising Autoencoders for Text Generation
Nikolay Savinov, Junyoung Chung, Mikolaj Binkowski +2
In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion…
Imitating Interactive Intelligence
Josh Abramson, Arun Ahuja, Iain Barr +26
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…
Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction
Nikolay Savinov, Lubor Ladicky, Christian Haene +1
Dense semantic 3D reconstruction is typically formulated as a discrete or continuous problem over label assignments in a voxel grid, combining semantic and depth likelihoods in a M…
RNN-based Generative Model for Fine-Grained Sketching
Andrin Jenal, Nikolay Savinov, Torsten Sattler +1
Deep generative models have shown great promise when it comes to synthesising novel images. While they can generate images that look convincing on a higher-level, generating fine-g…
Episodic Curiosity through Reachability
Nikolay Savinov, Anton Raichuk, Raphaël Marinier +4
Rewards are sparse in the real world and most of today's reinforcement learning algorithms struggle with such sparsity. One solution to this problem is to allow the agent to create…
Conditional Affordance Learning for Driving in Urban Environments
Axel Sauer, Nikolay Savinov, Andreas Geiger
Most existing approaches to autonomous driving fall into one of two categories: modular pipelines, that build an extensive model of the environment, and imitation learning approach…
Semi-parametric Topological Memory for Navigation
Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun
We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological…
Matching neural paths: transfer from recognition to correspondence search
Nikolay Savinov, Lubor Ladicky, Marc Pollefeys
Many machine learning tasks require finding per-part correspondences between objects. In this work we focus on low-level correspondences - a highly ambiguous matching problem. We p…
Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark
Timo Hackel, Nikolay Savinov, Lubor Ladicky +3
This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods.…
Quad-networks: unsupervised learning to rank for interest point detection
Nikolay Savinov, Akihito Seki, Lubor Ladicky +2
Several machine learning tasks require to represent the data using only a sparse set of interest points. An ideal detector is able to find the corresponding interest points even if…
TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks
Dmitry Laptev, Nikolay Savinov, Joachim M. Buhmann +1
In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to eff…
Semantic 3D Reconstruction with Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint
Nikolay Savinov, Christian Haene, Lubor Ladicky +1
We propose an approach for dense semantic 3D reconstruction which uses a data term that is defined as potentials over viewing rays, combined with continuous surface area penalizati…