Search Results for author:
Found 14 papers, 6 papers with code
OpenThoughts: Data Recipes for Reasoning Models
Yet, there are still many open questions about the best training recipes for reasoning since state-of-the-art models often rely on proprietary datasets with little to no public information available.
Should VLMs be Pre-trained with Image Data?
We find that pre-training with a mixture of image and text data allows models to perform better on vision-language tasks while maintaining strong performance on text-only evaluations.
Espresso: High Compression For Rich Extraction From Videos for Your Vision-Language Model
Recent advances in vision-language models (VLMs) have shown great promise in connecting images and text, but extending these models to long videos remains challenging due to the rapid growth in token counts.
DataComp-LM: In search of the next generation of training sets for language models
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models.
Linearizing Large Language Models
Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost.
Language models scale reliably with over-training and on downstream tasks
Second, we relate the perplexity of a language model to its downstream task performance by proposing a power law.
Residual Q-Learning: Offline and Online Policy Customization without Value
Specifically, we formulate the customization problem as a Markov Decision Process (MDP) with a reward function that combines 1) the inherent reward of the demonstration; and 2) the add-on reward specified by the downstream task.
RAP: Risk-Aware Prediction for Robust Planning
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions.
Control-Aware Prediction Objectives for Autonomous Driving
Autonomous vehicle software is typically structured as a modular pipeline of individual components (e. g., perception, prediction, and planning) to help separate concerns into interpretable sub-tasks.
Dynamics-Aware Comparison of Learned Reward Functions
The ability to learn reward functions plays an important role in enabling the deployment of intelligent agents in the real world.
Higher Order Linear Transformer
Following up on the linear transformer part of the article from Katharopoulos et al., that takes this idea from Shen et al., the trick that produces a linear complexity for the attention mechanism is re-used and extended to a second-order approximation of the softmax normalization.
Social Attention for Autonomous Decision-Making in Dense Traffic
We study the design of learning architectures for behavioural planning in a dense traffic setting.
Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting
This paper presents a novel vehicle motion forecasting method based on multi-head attention.
Kinematic Single Vehicle Trajectory Prediction Baselines and Applications with the NGSIM Dataset
This article is meant to be used along with the published code to establish baselines for further work.
