Search Results for author:
Found 5 papers, 2 papers with code
ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions
The ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions served as a rigorous platform to evaluate and benchmark state-of-the-art semantic segmentation models under challenging conditions for autonomous driving.
Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning
In this paper, we start with the hypothesis that much smaller LMs, which are weak at multi-step reasoning, can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task.
Ranked #12 on
Math Word Problem Solving
on SVAMP
(using extra training data)
IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
larger label set with a 4-level label hierarchy to capture unstructured traffic conditions.
Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning
Additionally, we show that DaSLaM is not limited by the solver's capabilities as a function of scale; e. g., solver LMs with diverse sizes give significant performance improvement with our solver-agnostic decomposition technique.
Ranked #6 on
Overall - Test
on JEEBench
(using extra training data)
Semantic Map Injected GAN Training for Image-to-Image Translation
Specifically, we train with original input and output modalities and inject a few epochs of training for translation from input to semantic map.
Generative Adversarial Network
Image-to-Image Translation
+2
